diff --git "a/open-llm-leaderboard.json" "b/open-llm-leaderboard.json" --- "a/open-llm-leaderboard.json" +++ "b/open-llm-leaderboard.json" @@ -1,4 +1,73 @@ [ + { + "T": "\ud83d\udd36", + "Model": "davidkim205\/Rhea-72b-v0.5", + "Average \u2b06\ufe0f": 81.22, + "ARC": 79.78, + "HellaSwag": 91.15, + "MMLU": 77.95, + "TruthfulQA": 74.5, + "Winogrande": 87.85, + "GSM8K": 76.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": true, + "Model sha": "fda5cf998a0f2d89b53b5fa490793e3e50bb8239", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "davidkim205\/Rhea-72b-v0.4", + "Average \u2b06\ufe0f": 81.09, + "ARC": 78.5, + "HellaSwag": 90.75, + "MMLU": 78.01, + "TruthfulQA": 73.91, + "Winogrande": 86.74, + "GSM8K": 78.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5502123c46485914a580d6794eeb5fb3554b46aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "MTSAIR\/MultiVerse_70B", + "Average \u2b06\ufe0f": 81.0, + "ARC": 78.67, + "HellaSwag": 89.77, + "MMLU": 78.22, + "TruthfulQA": 75.18, + "Winogrande": 87.53, + "GSM8K": 76.65, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ea2b4ff8e5acd7a48993f56b2d7b99e049eb6939", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "binbi\/Ein-72B-v0.1", @@ -22,6 +91,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MTSAIR\/MultiVerse_70B", + "Average \u2b06\ufe0f": 80.98, + "ARC": 78.58, + "HellaSwag": 89.74, + "MMLU": 78.27, + "TruthfulQA": 75.09, + "Winogrande": 87.37, + "GSM8K": 76.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ea2b4ff8e5acd7a48993f56b2d7b99e049eb6939", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "davidkim205\/Rhea-72b-v0.2", + "Average \u2b06\ufe0f": 80.95, + "ARC": 77.56, + "HellaSwag": 90.84, + "MMLU": 77.98, + "TruthfulQA": 74.5, + "Winogrande": 86.35, + "GSM8K": 78.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c51bcf1a3dc3c5e512e805f52d5e15384d798ba7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "davidkim205\/Rhea-72b-v0.3", + "Average \u2b06\ufe0f": 80.85, + "ARC": 76.79, + "HellaSwag": 89.98, + "MMLU": 77.47, + "TruthfulQA": 75.93, + "Winogrande": 85.08, + "GSM8K": 79.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7db39c93177958d94ebc3b719f8bfc75826b345e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "SF-Foundation\/Ein-72B-v0.11", @@ -39,8 +177,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, "Model sha": "40d451f32b1a6c9ad694b32ba8ed4822c27f3022", "Flagged": false, "MoE": false @@ -62,8 +200,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, "Model sha": "1f302e0e15f3d3711778cd61686eb9b28b0c72ae", "Flagged": false, "MoE": false @@ -108,8 +246,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, "Model sha": "84d38e29fec0dc9c274237968fdafe9396702f9b", "Flagged": false, "MoE": false @@ -131,7 +269,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 351.0, + "Hub \u2764\ufe0f": 430.0, "Available on the hub": true, "Model sha": "54a8c35600ec5cb30ca2129247854ece23e57f57", "Flagged": false, @@ -154,7 +292,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "4df251a558c53b6b6a4c459045b161951cfc3c4e", "Flagged": false, @@ -177,7 +315,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 61.0, + "Hub \u2764\ufe0f": 67.0, "Available on the hub": true, "Model sha": "c64edea08b27be1e7e2ae6a95bcdd74849cb887e", "Flagged": false, @@ -200,12 +338,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "cd29cfa124072c96ba8601230bead65d76e04dcb", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v1.0", + "Average \u2b06\ufe0f": 77.74, + "ARC": 77.47, + "HellaSwag": 91.88, + "MMLU": 68.1, + "TruthfulQA": 79.17, + "Winogrande": 87.45, + "GSM8K": 62.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "ba3403eaafc6d1f6e3a73245314ee96025c08d96", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "HanNayeoniee\/LHK_DPO_v1", @@ -223,11 +384,11 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 14.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "4e2c0a8fb1a1654312a573e85fec79832bfa489c", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -246,12 +407,58 @@ "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "e8e558b5fd4ac9da839577b1295d10ca75fc2663", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v0.2", + "Average \u2b06\ufe0f": 77.51, + "ARC": 76.71, + "HellaSwag": 91.61, + "MMLU": 68.27, + "TruthfulQA": 79.8, + "Winogrande": 87.06, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "59243de958296a4516f72ebfb1b597188dd59229", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zhengr\/MixTAO-7Bx2-MoE-v8.1", + "Average \u2b06\ufe0f": 77.5, + "ARC": 73.81, + "HellaSwag": 89.22, + "MMLU": 64.92, + "TruthfulQA": 78.57, + "Winogrande": 87.37, + "GSM8K": 71.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "2d8cff968dbfb31e0c1ccc42053ccc4d2698a390", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "yunconglong\/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B", @@ -269,7 +476,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 38.0, + "Hub \u2764\ufe0f": 46.0, "Available on the hub": true, "Model sha": "915651208ea9f40c65a60d1f971a09f9461ee691", "Flagged": false, @@ -292,7 +499,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "7dd3ddea090bd63f3143e70d7d6237cc40c046e4", "Flagged": false, @@ -315,7 +522,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "e1cdc5b02c662c5f29a50d0b22c64a8902ca856b", "Flagged": false, @@ -338,12 +545,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "6c7ec6d2ca1c0d126a26963fedc9bbdf5210b0d1", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v0.1", + "Average \u2b06\ufe0f": 77.32, + "ARC": 76.79, + "HellaSwag": 91.79, + "MMLU": 68.18, + "TruthfulQA": 76.7, + "Winogrande": 87.53, + "GSM8K": 62.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "88a47c498102132f5262581803fe1ed9252a16bc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Tess-72B-v1.5b", @@ -361,35 +591,12 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "dc092ecc5d5a424678eac445a9f4443069776691", "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udcac", - "Model": "moreh\/MoMo-70B-lora-1.8.6-DPO", - "Average \u2b06\ufe0f": 77.29, - "ARC": 70.14, - "HellaSwag": 86.03, - "MMLU": 77.4, - "TruthfulQA": 69.0, - "Winogrande": 84.37, - "GSM8K": 76.8, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "mit", - "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "76389d5d825c3743cc70bc75b902bbfdad11beba", - "Flagged": false, - "MoE": false - }, { "T": "\ud83d\udcac", "Model": "moreh\/MoMo-72B-lora-1.8.6-DPO", @@ -405,9 +612,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "76389d5d825c3743cc70bc75b902bbfdad11beba", "Flagged": false, @@ -415,7 +622,7 @@ }, { "T": "\ud83d\udd36", - "Model": "abacusai\/Smaugv0.1", + "Model": "abacusai\/Smaug-34B-v0.1", "Average \u2b06\ufe0f": 77.29, "ARC": 74.23, "HellaSwag": 86.76, @@ -428,17 +635,17 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "036927bc2b54d408bb9e9357c3df8353f5853ea8", + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "7b74a95019f01b59630cbd6469814c752d0e59e5", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "abacusai\/Smaug-34B-v0.1", + "Model": "abacusai\/Smaugv0.1", "Average \u2b06\ufe0f": 77.29, "ARC": 74.23, "HellaSwag": 86.76, @@ -451,11 +658,11 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "other", + "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 37.0, - "Available on the hub": true, - "Model sha": "7b74a95019f01b59630cbd6469814c752d0e59e5", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "036927bc2b54d408bb9e9357c3df8353f5853ea8", "Flagged": false, "MoE": false }, @@ -484,7 +691,76 @@ }, { "T": "\ud83d\udd36", - "Model": "ConvexAI\/Luminex-32B-v0.2", + "Model": "jefferylovely\/MoeLovely-13B", + "Average \u2b06\ufe0f": 77.25, + "ARC": 73.72, + "HellaSwag": 89.49, + "MMLU": 64.78, + "TruthfulQA": 78.74, + "Winogrande": 87.61, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ac4f0ad8a665eb6b54c286810a9b4551b0bcdc25", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v0.4", + "Average \u2b06\ufe0f": 77.23, + "ARC": 76.88, + "HellaSwag": 91.83, + "MMLU": 68.06, + "TruthfulQA": 76.72, + "Winogrande": 87.21, + "GSM8K": 62.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4c4342a9c3e8e793a0969b74222d887d53cb294e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/orthorus-125b-v2", + "Average \u2b06\ufe0f": 77.22, + "ARC": 73.63, + "HellaSwag": 89.04, + "MMLU": 75.99, + "TruthfulQA": 70.19, + "Winogrande": 85.48, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 125.35, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "95b3b4e432d98b804d64cfe42dd9fa6b67198e5b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Luminex-34B-v0.2", "Average \u2b06\ufe0f": 77.19, "ARC": 74.49, "HellaSwag": 86.76, @@ -499,7 +775,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "3880710724abcaffbdf8fa4031e1d02066fbfe9d", "Flagged": false, @@ -545,7 +821,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "354f0eb0a1299473c861c0505c2ede04ced90972", "Flagged": false, @@ -565,7 +841,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, @@ -639,7 +915,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "c5575550053c84a401baf56174cb2e5d5bd9e79a", "Flagged": false, @@ -662,7 +938,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "d3efc551679d7ec00da14722d44151c948a48d25", "Flagged": false, @@ -685,7 +961,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "d8d6a47f877fee3e638a158c2bd637c0013ed4e4", "Flagged": false, @@ -714,6 +990,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "4season\/alignment_model_test", + "Average \u2b06\ufe0f": 76.97, + "ARC": 78.24, + "HellaSwag": 89.68, + "MMLU": 68.08, + "TruthfulQA": 80.88, + "Winogrande": 86.5, + "GSM8K": 58.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "791a326ee0f6d5246962039803fd79b28608e54c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cloudyu\/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO", @@ -751,15 +1050,130 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "other", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "392d963e63267650f2aea7dc26c60ee6fd2b26d4", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "liminerity\/M7-7b", + "Average \u2b06\ufe0f": 76.82, + "ARC": 72.87, + "HellaSwag": 89.15, + "MMLU": 64.5, + "TruthfulQA": 77.93, + "Winogrande": 84.77, + "GSM8K": 71.72, + "Type": "continuously pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "23497a39fe5d290494fad49e5b8077f76440ad11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/Multiverse-Experiment-slerp-7b", + "Average \u2b06\ufe0f": 76.82, + "ARC": 72.87, + "HellaSwag": 89.15, + "MMLU": 64.5, + "TruthfulQA": 77.93, + "Winogrande": 84.77, + "GSM8K": 71.72, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2103c07a06ff4d6e7f4c031b98d4c1a455690436", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AurelPx\/Percival_01-7b-slerp", + "Average \u2b06\ufe0f": 76.79, + "ARC": 73.21, + "HellaSwag": 89.16, + "MMLU": 64.42, + "TruthfulQA": 77.97, + "Winogrande": 85.08, + "GSM8K": 70.89, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6d415ca49b7717b8e851ae3271f569e83d4de589", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "LewisDeBenoisIV\/Jason1903_SLERP", + "Average \u2b06\ufe0f": 76.77, + "ARC": 73.12, + "HellaSwag": 89.13, + "MMLU": 64.43, + "TruthfulQA": 78.13, + "Winogrande": 85.08, + "GSM8K": 70.74, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ea187cf89f44197d9007798316a087bc63286227", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Infinimol\/miiqu-f16", + "Average \u2b06\ufe0f": 76.77, + "ARC": 72.87, + "HellaSwag": 88.97, + "MMLU": 75.99, + "TruthfulQA": 69.37, + "Winogrande": 85.56, + "GSM8K": 67.85, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 90.37, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "395d6398cb2ab71621a43f5f5df8994de9c46175", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "JaeyeonKang\/CCK_Asura_v1.1.0", @@ -783,6 +1197,121 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nlpguy\/T3QM7", + "Average \u2b06\ufe0f": 76.75, + "ARC": 73.12, + "HellaSwag": 89.14, + "MMLU": 64.48, + "TruthfulQA": 77.96, + "Winogrande": 85.08, + "GSM8K": 70.74, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa6bd0d1019345cddabd90127c6a8f524a0d7a67", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bardsai\/jaskier-7b-dpo-v7.1", + "Average \u2b06\ufe0f": 76.74, + "ARC": 73.38, + "HellaSwag": 89.28, + "MMLU": 64.37, + "TruthfulQA": 78.28, + "Winogrande": 85.24, + "GSM8K": 69.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "305544e9edd98253540141e91653d308e9b135cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment26-7B", + "Average \u2b06\ufe0f": 76.74, + "ARC": 73.38, + "HellaSwag": 89.15, + "MMLU": 64.32, + "TruthfulQA": 78.24, + "Winogrande": 84.93, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 71.0, + "Available on the hub": true, + "Model sha": "bbaef291e93a7f6c9f8cb76a4dbd8c3c054d3f3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe9", + "Model": "ammarali32\/multi_verse_model", + "Average \u2b06\ufe0f": 76.74, + "ARC": 72.87, + "HellaSwag": 89.2, + "MMLU": 64.4, + "TruthfulQA": 77.92, + "Winogrande": 84.77, + "GSM8K": 71.27, + "Type": "continuously pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e2aa6fdad0b28a6019b0fc7c178a3579c3d671e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MTSAIR\/multi_verse_model", + "Average \u2b06\ufe0f": 76.74, + "ARC": 72.87, + "HellaSwag": 89.2, + "MMLU": 64.4, + "TruthfulQA": 77.92, + "Winogrande": 84.77, + "GSM8K": 71.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "a4ca706d1bbc263b95e223a80ad68b0f125840b3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "cloudyu\/Yi-34Bx2-MoE-60B", @@ -800,12 +1329,150 @@ "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 52.0, + "Hub \u2764\ufe0f": 59.0, "Available on the hub": true, "Model sha": "483359d70b3fef480cdaeb6d722a18626d34f0ce", "Flagged": true, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/T3QM7XP", + "Average \u2b06\ufe0f": 76.71, + "ARC": 73.04, + "HellaSwag": 89.12, + "MMLU": 64.45, + "TruthfulQA": 78.06, + "Winogrande": 85.0, + "GSM8K": 70.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1da031f9fdf04ea93b04e0bba7672560ea9d6255", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chihoonlee10\/T3Q-Mistral-Orca-Math-DPO", + "Average \u2b06\ufe0f": 76.7, + "ARC": 72.95, + "HellaSwag": 89.23, + "MMLU": 64.42, + "TruthfulQA": 78.41, + "Winogrande": 84.93, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f136ec75c9fb7c86c071291ddf418089c8f43da0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AurelPx\/Meliodas-7b-dare", + "Average \u2b06\ufe0f": 76.69, + "ARC": 72.87, + "HellaSwag": 89.11, + "MMLU": 64.43, + "TruthfulQA": 78.02, + "Winogrande": 84.77, + "GSM8K": 70.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2bae3c13529794307f17d9bfca4e6881736909a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_32-7B-slerp", + "Average \u2b06\ufe0f": 76.68, + "ARC": 72.95, + "HellaSwag": 89.0, + "MMLU": 64.52, + "TruthfulQA": 77.94, + "Winogrande": 85.0, + "GSM8K": 70.66, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "47f8a90a2c35e0affbba8bdaaf458e1aca3e3599", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment26-7B", + "Average \u2b06\ufe0f": 76.67, + "ARC": 73.12, + "HellaSwag": 89.12, + "MMLU": 64.3, + "TruthfulQA": 78.04, + "Winogrande": 85.0, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 71.0, + "Available on the hub": true, + "Model sha": "bbaef291e93a7f6c9f8cb76a4dbd8c3c054d3f3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "MSL7\/INEX12-7b", + "Average \u2b06\ufe0f": 76.66, + "ARC": 72.95, + "HellaSwag": 89.14, + "MMLU": 64.4, + "TruthfulQA": 78.04, + "Winogrande": 85.24, + "GSM8K": 70.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7c78dddda4c5b72bf5c6e0efb64f52772ff1ae84", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "cloudyu\/Mixtral_34Bx2_MoE_60B", @@ -823,12 +1490,58 @@ "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 102.0, + "Hub \u2764\ufe0f": 105.0, "Available on the hub": true, "Model sha": "f49d7cf0a7b99b15bc98b0ef4a681e7f0f4aa92c", "Flagged": true, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/experiment26-truthy-iter-0", + "Average \u2b06\ufe0f": 76.65, + "ARC": 73.29, + "HellaSwag": 89.11, + "MMLU": 64.35, + "TruthfulQA": 77.86, + "Winogrande": 84.93, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cd8bfad664fb7f9b017388d974dd3265f8c40396", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe9", + "Model": "NExtNewChattingAI\/Mutliverse_model_official", + "Average \u2b06\ufe0f": 76.64, + "ARC": 72.87, + "HellaSwag": 89.13, + "MMLU": 64.42, + "TruthfulQA": 77.93, + "Winogrande": 85.08, + "GSM8K": 70.43, + "Type": "continuously pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4b8f0409e2844641fe9bd6d45385f4e71e0ee940", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Eurdem\/megatron_2.1_MoE_2x7B", @@ -852,6 +1565,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/shadow-clown-7B-slerp", + "Average \u2b06\ufe0f": 76.64, + "ARC": 73.38, + "HellaSwag": 89.05, + "MMLU": 64.32, + "TruthfulQA": 77.95, + "Winogrande": 84.85, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "432ca89337ce47e2dd4703fffe1703f57d2b67d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nlpguy\/T3QM7X", + "Average \u2b06\ufe0f": 76.63, + "ARC": 73.12, + "HellaSwag": 89.14, + "MMLU": 64.45, + "TruthfulQA": 78.02, + "Winogrande": 85.08, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "299f7b97eb2791b3ef492e1addfe5706bff92e29", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "cloudyu\/Mixtral_34Bx2_MoE_60B", @@ -869,107 +1628,912 @@ "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 102.0, + "Hub \u2764\ufe0f": 105.0, "Available on the hub": true, "Model sha": "f49d7cf0a7b99b15bc98b0ef4a681e7f0f4aa92c", "Flagged": true, "MoE": true }, { - "T": "\ud83d\udcac", - "Model": "Undi95\/Miqu-70B-Alpaca-DPO", - "Average \u2b06\ufe0f": 76.6, - "ARC": 73.21, - "HellaSwag": 88.6, - "MMLU": 75.41, - "TruthfulQA": 69.44, - "Winogrande": 85.4, - "GSM8K": 67.55, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MixtureofMerges-MoE-2x7b-v6", + "Average \u2b06\ufe0f": 76.63, + "ARC": 73.38, + "HellaSwag": 89.16, + "MMLU": 64.53, + "TruthfulQA": 78.58, + "Winogrande": 84.77, + "GSM8K": 69.37, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "", - "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 5.0, - "Available on the hub": false, - "Model sha": "f7ee9b9099cd518060e9e61ff7ae11a39428bd93", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3dff5c8580d594e1da355a2745106c82f4b6e3d7", "Flagged": false, - "MoE": false + "MoE": true }, { - "T": "\ud83d\udcac", - "Model": "152334H\/miqu-1-70b-sf", - "Average \u2b06\ufe0f": 76.59, - "ARC": 73.04, - "HellaSwag": 88.61, - "MMLU": 75.49, - "TruthfulQA": 69.38, - "Winogrande": 85.32, - "GSM8K": 67.7, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment30-7B", + "Average \u2b06\ufe0f": 76.62, + "ARC": 73.38, + "HellaSwag": 89.13, + "MMLU": 64.28, + "TruthfulQA": 77.98, + "Winogrande": 84.93, + "GSM8K": 70.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": null, - "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 187.0, - "Available on the hub": false, - "Model sha": "97c24b15a7e26985fb18540800516aa2ac03ad03", - "Flagged": false, - "MoE": false - }, - { - "T": "\ud83d\udcac", - "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v7.0", - "Average \u2b06\ufe0f": 76.55, - "ARC": 74.23, - "HellaSwag": 89.37, - "MMLU": 64.54, - "TruthfulQA": 74.26, - "Winogrande": 87.77, - "GSM8K": 69.14, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "MixtralForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 11.0, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "69b9280ee4d2a20ef5645798621e62dd9777c139", + "Model sha": "ff261dadc107d0ce67b836a052d7131f9d9e4260", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", - "Model": "alchemonaut\/BoreanGale-70B", - "Average \u2b06\ufe0f": 76.48, - "ARC": 73.89, - "HellaSwag": 89.37, - "MMLU": 75.19, - "TruthfulQA": 68.6, - "Winogrande": 84.53, - "GSM8K": 67.32, + "Model": "yam-peleg\/Experiment28-7B", + "Average \u2b06\ufe0f": 76.62, + "ARC": 73.04, + "HellaSwag": 89.04, + "MMLU": 64.44, + "TruthfulQA": 78.49, + "Winogrande": 85.4, + "GSM8K": 69.29, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "other", - "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 4.0, + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "f7768207c1f37d3f4374dccc182d7a86c6539ead", + "Model sha": "5efde29924cf7158e4cbd642311a92a14e85597c", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "cloudyu\/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B", + "Model": "MaziyarPanahi\/Calme-7B-Instruct-v0.2", + "Average \u2b06\ufe0f": 76.61, + "ARC": 73.12, + "HellaSwag": 89.19, + "MMLU": 64.36, + "TruthfulQA": 78.0, + "Winogrande": 84.93, + "GSM8K": 70.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "a283f4e8169009d683b329ae1a96c9a77ce5936a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "automerger\/YamShadow-7B", + "Average \u2b06\ufe0f": 76.6, + "ARC": 72.53, + "HellaSwag": 88.9, + "MMLU": 64.64, + "TruthfulQA": 78.35, + "Winogrande": 85.0, + "GSM8K": 70.2, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "53746d4d0be4a0b0c2ec5decaeff28f692e06216", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/experiment26-truthy-iter-1", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.21, + "HellaSwag": 89.13, + "MMLU": 64.34, + "TruthfulQA": 77.66, + "Winogrande": 84.85, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cb04e33c4ff559b31767765100cd50c24ec2531c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "mayacinka\/yam-jom-7B", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.38, + "HellaSwag": 89.15, + "MMLU": 64.51, + "TruthfulQA": 78.04, + "Winogrande": 84.93, + "GSM8K": 69.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fdd98b8000db4e2a9112184fa384de812069b5cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Undi95\/Miqu-70B-Alpaca-DPO", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.21, + "HellaSwag": 88.6, + "MMLU": 75.41, + "TruthfulQA": 69.44, + "Winogrande": 85.4, + "GSM8K": 67.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "f7ee9b9099cd518060e9e61ff7ae11a39428bd93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mayacinka\/yam-jom-7B-dare", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.38, + "HellaSwag": 89.14, + "MMLU": 64.38, + "TruthfulQA": 78.04, + "Winogrande": 84.85, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5d79006083e269006e4cfdf8ebe2e902a258e6f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuralSirKrishna-7b", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.72, + "HellaSwag": 89.05, + "MMLU": 64.63, + "TruthfulQA": 75.6, + "Winogrande": 85.32, + "GSM8K": 71.27, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "38905a9bf8b4c000a99daaea69e63c15efbbc152", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/experiment26-truthy-iter-2", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.38, + "HellaSwag": 89.11, + "MMLU": 64.36, + "TruthfulQA": 77.3, + "Winogrande": 85.0, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1dc4edde961960f7263dc3bdd37ca9e9f7e451ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nlpguy\/AlloyIngotNeoY", + "Average \u2b06\ufe0f": 76.59, + "ARC": 72.78, + "HellaSwag": 89.12, + "MMLU": 64.32, + "TruthfulQA": 77.99, + "Winogrande": 85.08, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e90d4a4a13d5ff4d3bee099212ffc1e1985d8236", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chlee10\/T3Q-Merge-Mistral7B", + "Average \u2b06\ufe0f": 76.59, + "ARC": 72.95, + "HellaSwag": 89.15, + "MMLU": 64.44, + "TruthfulQA": 77.96, + "Winogrande": 85.0, + "GSM8K": 70.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "03405145ca06170f1b2e0acc838f573f0e090df8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "152334H\/miqu-1-70b-sf", + "Average \u2b06\ufe0f": 76.59, + "ARC": 73.04, + "HellaSwag": 88.61, + "MMLU": 75.49, + "TruthfulQA": 69.38, + "Winogrande": 85.32, + "GSM8K": 67.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 205.0, + "Available on the hub": false, + "Model sha": "97c24b15a7e26985fb18540800516aa2ac03ad03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LeroyDyer\/Mixtral_AI_Cyber_3.m1", + "Average \u2b06\ufe0f": 76.59, + "ARC": 74.06, + "HellaSwag": 88.96, + "MMLU": 64.45, + "TruthfulQA": 77.67, + "Winogrande": 85.0, + "GSM8K": 69.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0da1865ae1ce682d4002dd9935d20520e79ed520", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment31-7B", + "Average \u2b06\ufe0f": 76.58, + "ARC": 73.55, + "HellaSwag": 89.19, + "MMLU": 64.36, + "TruthfulQA": 78.31, + "Winogrande": 85.0, + "GSM8K": 69.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a27e0dfaf79af8da32fc4ff6c5eb8be46c9f5a13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralArjuna-7B-DT", + "Average \u2b06\ufe0f": 76.58, + "ARC": 73.12, + "HellaSwag": 88.97, + "MMLU": 64.63, + "TruthfulQA": 76.68, + "Winogrande": 85.24, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ac404e8a016bc77dce533c8746daedd5cefa8cb3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment31-7B", + "Average \u2b06\ufe0f": 76.57, + "ARC": 73.55, + "HellaSwag": 89.14, + "MMLU": 64.29, + "TruthfulQA": 78.43, + "Winogrande": 85.16, + "GSM8K": 68.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a27e0dfaf79af8da32fc4ff6c5eb8be46c9f5a13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment24-7B", + "Average \u2b06\ufe0f": 76.56, + "ARC": 73.81, + "HellaSwag": 89.06, + "MMLU": 64.34, + "TruthfulQA": 78.54, + "Winogrande": 85.16, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b7f5aa8d4c899c175a1dad40a03b4071df90bd8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v7.0", + "Average \u2b06\ufe0f": 76.55, + "ARC": 74.23, + "HellaSwag": 89.37, + "MMLU": 64.54, + "TruthfulQA": 74.26, + "Winogrande": 87.77, + "GSM8K": 69.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "69b9280ee4d2a20ef5645798621e62dd9777c139", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "bobofrut\/ladybird-base-7B-v8", + "Average \u2b06\ufe0f": 76.55, + "ARC": 73.21, + "HellaSwag": 89.19, + "MMLU": 64.39, + "TruthfulQA": 76.82, + "Winogrande": 85.32, + "GSM8K": 70.36, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4774173a54be9a648e1cf03248af3ae3d51a0434", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MixtureofMerges-MoE-2x7b-v7", + "Average \u2b06\ufe0f": 76.54, + "ARC": 73.21, + "HellaSwag": 89.05, + "MMLU": 64.63, + "TruthfulQA": 78.34, + "Winogrande": 84.93, + "GSM8K": 69.07, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "abf8d9dc6522658ab943bf69c475f899d66bcc20", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "222limin\/Nexim-7b", + "Average \u2b06\ufe0f": 76.53, + "ARC": 73.04, + "HellaSwag": 89.1, + "MMLU": 64.48, + "TruthfulQA": 77.68, + "Winogrande": 84.77, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a585b520352fc0d9fc68f811d3e2c903ef4230ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralContamination-7B-ties", + "Average \u2b06\ufe0f": 76.53, + "ARC": 73.46, + "HellaSwag": 88.9, + "MMLU": 64.76, + "TruthfulQA": 76.71, + "Winogrande": 85.0, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8e01722995275d4b8a6943fb207977a5bde0829e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Neural-Krishna-Multiverse-7b-v3", + "Average \u2b06\ufe0f": 76.53, + "ARC": 72.87, + "HellaSwag": 89.07, + "MMLU": 64.55, + "TruthfulQA": 77.39, + "Winogrande": 84.93, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "26b8fbb836dbc8a72412db625ab2de858c60bad4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment29-7B", + "Average \u2b06\ufe0f": 76.53, + "ARC": 73.12, + "HellaSwag": 89.06, + "MMLU": 64.49, + "TruthfulQA": 78.72, + "Winogrande": 85.0, + "GSM8K": 68.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "11a51df04f85047e166d63eb64cedc1ec02732a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "automerger\/Strangemerges_32Yamshadow-7B", + "Average \u2b06\ufe0f": 76.53, + "ARC": 72.95, + "HellaSwag": 88.88, + "MMLU": 64.52, + "TruthfulQA": 78.06, + "Winogrande": 84.77, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4efa1c02b2a14eda16906102992ae2fb7c6c06a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment30-7B", + "Average \u2b06\ufe0f": 76.53, + "ARC": 73.46, + "HellaSwag": 89.09, + "MMLU": 64.4, + "TruthfulQA": 77.76, + "Winogrande": 84.85, + "GSM8K": 69.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ff261dadc107d0ce67b836a052d7131f9d9e4260", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "automerger\/NeuralsirkrishnaExperiment26-7B", + "Average \u2b06\ufe0f": 76.52, + "ARC": 73.89, + "HellaSwag": 89.14, + "MMLU": 64.32, + "TruthfulQA": 77.25, + "Winogrande": 84.85, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d9d92b2ae2ce1dd459170896bb5eff9325660916", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_30-7B-slerp", + "Average \u2b06\ufe0f": 76.52, + "ARC": 74.15, + "HellaSwag": 89.15, + "MMLU": 64.65, + "TruthfulQA": 76.12, + "Winogrande": 84.85, + "GSM8K": 70.2, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "82906a18499932d2a6f029a2782839390e5ef811", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "automerger\/OgnoExperiment27-7B", + "Average \u2b06\ufe0f": 76.51, + "ARC": 73.38, + "HellaSwag": 89.4, + "MMLU": 64.43, + "TruthfulQA": 78.41, + "Winogrande": 84.85, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4c81b65d91016bbec6479f6ff839ebe6985abac8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/shadow-clown-7B-dare", + "Average \u2b06\ufe0f": 76.51, + "ARC": 72.61, + "HellaSwag": 88.86, + "MMLU": 64.44, + "TruthfulQA": 78.33, + "Winogrande": 85.24, + "GSM8K": 69.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f292aba5b64521ba8e0d5e8469d1380394ff22f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/pastiche-crown-clown-7b-dare-dpo", + "Average \u2b06\ufe0f": 76.5, + "ARC": 72.78, + "HellaSwag": 89.15, + "MMLU": 64.51, + "TruthfulQA": 78.8, + "Winogrande": 84.85, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e1cd6e84d02a9c1d70c2a2037f485bc2b646391", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisgrc\/Montebello_7B_SLERP", + "Average \u2b06\ufe0f": 76.5, + "ARC": 72.95, + "HellaSwag": 89.07, + "MMLU": 64.56, + "TruthfulQA": 79.33, + "Winogrande": 84.77, + "GSM8K": 68.31, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1097b6038dc48f86382cacb1a27c76faacf8f607", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Neural-Krishna-Multiverse-7b-v2", + "Average \u2b06\ufe0f": 76.49, + "ARC": 72.95, + "HellaSwag": 89.06, + "MMLU": 64.62, + "TruthfulQA": 77.35, + "Winogrande": 84.69, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8bacb25bdd4a81b7725c6d72845f5e1519b0a1b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MSL7\/INEX16-7b", + "Average \u2b06\ufe0f": 76.49, + "ARC": 73.12, + "HellaSwag": 89.1, + "MMLU": 64.56, + "TruthfulQA": 77.35, + "Winogrande": 84.45, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "def8a359e2fb6ee05ecda3577f158d9838b029c4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Calme-7B-Instruct-v0.1.1", + "Average \u2b06\ufe0f": 76.49, + "ARC": 72.95, + "HellaSwag": 89.26, + "MMLU": 64.32, + "TruthfulQA": 78.1, + "Winogrande": 85.16, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "22a9da7289d20a1d5452f77aa5bc49e97344af52", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/UltraMerge-7B", + "Average \u2b06\ufe0f": 76.49, + "ARC": 73.04, + "HellaSwag": 89.25, + "MMLU": 64.4, + "TruthfulQA": 78.17, + "Winogrande": 84.85, + "GSM8K": 69.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "cd343f0846ceb4180297920b2da50d6b28dcb242", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alchemonaut\/BoreanGale-70B", + "Average \u2b06\ufe0f": 76.48, + "ARC": 73.89, + "HellaSwag": 89.37, + "MMLU": 75.19, + "TruthfulQA": 68.6, + "Winogrande": 84.53, + "GSM8K": 67.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f7768207c1f37d3f4374dccc182d7a86c6539ead", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B", "Average \u2b06\ufe0f": 76.48, "ARC": 71.25, "HellaSwag": 85.24, @@ -990,6 +2554,167 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment27-7B", + "Average \u2b06\ufe0f": 76.47, + "ARC": 73.55, + "HellaSwag": 89.13, + "MMLU": 64.45, + "TruthfulQA": 78.7, + "Winogrande": 84.93, + "GSM8K": 68.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2b81b03b242a548e54e9e10af6a4c24f24a4c5fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/pastiche-crown-clown-7b-dare", + "Average \u2b06\ufe0f": 76.46, + "ARC": 73.81, + "HellaSwag": 89.09, + "MMLU": 64.65, + "TruthfulQA": 76.55, + "Winogrande": 84.85, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6e4720f8466ceb624e2a60986fe1fc00cf9a75cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "mayacinka\/yam-jom-7B-slerp", + "Average \u2b06\ufe0f": 76.45, + "ARC": 72.7, + "HellaSwag": 89.02, + "MMLU": 64.64, + "TruthfulQA": 77.77, + "Winogrande": 84.69, + "GSM8K": 69.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "24f3ae950139f9962e34003d567ba2825ec39e64", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "eren23\/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO", + "Average \u2b06\ufe0f": 76.45, + "ARC": 73.12, + "HellaSwag": 89.09, + "MMLU": 64.8, + "TruthfulQA": 77.45, + "Winogrande": 84.77, + "GSM8K": 69.45, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f92057866ff68bf215487d34ca1080707bb4e98c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "mayacinka\/yam-jom-7B-ties", + "Average \u2b06\ufe0f": 76.44, + "ARC": 73.21, + "HellaSwag": 89.05, + "MMLU": 64.77, + "TruthfulQA": 77.51, + "Winogrande": 84.53, + "GSM8K": 69.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f57717445a39fdaf5cae2eafb2c46576e4481e6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "eren23\/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2", + "Average \u2b06\ufe0f": 76.44, + "ARC": 73.12, + "HellaSwag": 89.07, + "MMLU": 64.8, + "TruthfulQA": 77.46, + "Winogrande": 84.69, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c00b0fa78ab41aec778209fdf7640ebbe6d83065", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "automerger\/ShadowYam-7B", + "Average \u2b06\ufe0f": 76.44, + "ARC": 73.21, + "HellaSwag": 89.07, + "MMLU": 64.49, + "TruthfulQA": 78.05, + "Winogrande": 84.77, + "GSM8K": 69.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0525f9aa8d500470fcf80f7b20390c1533c73a1c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cloudyu\/Yi-34Bx2-MoE-60B-DPO", @@ -1013,6 +2738,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "MSL7\/INEX8-7B", + "Average \u2b06\ufe0f": 76.44, + "ARC": 73.29, + "HellaSwag": 89.19, + "MMLU": 64.47, + "TruthfulQA": 77.83, + "Winogrande": 84.85, + "GSM8K": 68.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4b63f8040ad51f7d265722fa65758a4d7e6acec3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "macadeliccc\/SmaugDolphin-60B", @@ -1024,84 +2772,360 @@ "Winogrande": 83.5, "GSM8K": 70.96, "Type": "base merges and moerges", - "Architecture": "MixtralForCausalLM", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cf8bc1d4103c4fde2a3da0cf86bdfcec95f5fe35", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "chihoonlee10\/T3Q-EN-DPO-Mistral-7B", + "Average \u2b06\ufe0f": 76.43, + "ARC": 73.04, + "HellaSwag": 89.3, + "MMLU": 64.13, + "TruthfulQA": 78.71, + "Winogrande": 85.32, + "GSM8K": 68.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b1ec306bf85762b28ce29ac71924bb9a8fa01e5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/ogno-monarch-jaskier-merge-7b", + "Average \u2b06\ufe0f": 76.43, + "ARC": 73.04, + "HellaSwag": 89.09, + "MMLU": 64.78, + "TruthfulQA": 77.44, + "Winogrande": 84.77, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a1179e6c346ba93db60c45d6d219ca86f2260102", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisgrc\/Marengoli_7B_SLERP", + "Average \u2b06\ufe0f": 76.42, + "ARC": 73.63, + "HellaSwag": 89.24, + "MMLU": 64.68, + "TruthfulQA": 77.23, + "Winogrande": 85.08, + "GSM8K": 68.69, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "86b0adb1715855794161ba18db1c115f7ffa6ad7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Ramakrishna-7b-v3", + "Average \u2b06\ufe0f": 76.42, + "ARC": 73.63, + "HellaSwag": 89.0, + "MMLU": 64.57, + "TruthfulQA": 76.67, + "Winogrande": 84.45, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea88953423fb5a18feef2f27954c8af1a5b5a489", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/AiMaven-Merkaba-7b", + "Average \u2b06\ufe0f": 76.42, + "ARC": 73.21, + "HellaSwag": 89.03, + "MMLU": 64.53, + "TruthfulQA": 78.3, + "Winogrande": 84.61, + "GSM8K": 68.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af1576f357ce8c5c3ee2e8bda45f8ffd7e0535f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "automerger\/Experiment27Neuralsirkrishna-7B", + "Average \u2b06\ufe0f": 76.41, + "ARC": 73.21, + "HellaSwag": 89.04, + "MMLU": 64.62, + "TruthfulQA": 77.4, + "Winogrande": 84.85, + "GSM8K": 69.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6be791ab6dff0e9b0e222743d2973717ef5250c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AurelPx\/Pegasus-7b-slerp", + "Average \u2b06\ufe0f": 76.41, + "ARC": 72.7, + "HellaSwag": 89.05, + "MMLU": 64.47, + "TruthfulQA": 77.13, + "Winogrande": 85.0, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2c42b3c5aa99602ffe02ff1a0702d6a40e6cb426", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "arcee-ai\/Clown-DPO-Extended", + "Average \u2b06\ufe0f": 76.41, + "ARC": 73.12, + "HellaSwag": 89.09, + "MMLU": 64.52, + "TruthfulQA": 78.78, + "Winogrande": 84.69, + "GSM8K": 68.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6c74a9d47c1c311d8387877f85c4ae0f70eacca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bardsai\/jaskier-7b-dpo-v5.6", + "Average \u2b06\ufe0f": 76.41, + "ARC": 73.04, + "HellaSwag": 89.0, + "MMLU": 64.38, + "TruthfulQA": 77.81, + "Winogrande": 84.53, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "25c0f5c1edad0ed1ab02347adf02fe03e0a3b62a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Asura_v2.1", + "Average \u2b06\ufe0f": 76.41, + "ARC": 72.53, + "HellaSwag": 88.75, + "MMLU": 74.96, + "TruthfulQA": 67.33, + "Winogrande": 85.87, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "546cdd443abc56b48aaadb4ebb5fb9249015f0bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/Neurotic-Jomainotrik-7b-slerp", + "Average \u2b06\ufe0f": 76.4, + "ARC": 72.95, + "HellaSwag": 89.15, + "MMLU": 64.28, + "TruthfulQA": 77.64, + "Winogrande": 85.4, + "GSM8K": 68.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "other", - "#Params (B)": 60.81, + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "cf8bc1d4103c4fde2a3da0cf86bdfcec95f5fe35", + "Model sha": "c9925fc46ab14f2b2d3200802555d6bd3cc8c61b", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", - "Model": "eren23\/ogno-monarch-jaskier-merge-7b", - "Average \u2b06\ufe0f": 76.43, - "ARC": 73.04, - "HellaSwag": 89.09, - "MMLU": 64.78, - "TruthfulQA": 77.44, - "Winogrande": 84.77, - "GSM8K": 69.45, + "Model": "yam-peleg\/Experiment25-7B", + "Average \u2b06\ufe0f": 76.4, + "ARC": 73.21, + "HellaSwag": 89.01, + "MMLU": 64.45, + "TruthfulQA": 78.49, + "Winogrande": 85.4, + "GSM8K": 67.85, "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "cc-by-nc-4.0", + "Merged": false, + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "a1179e6c346ba93db60c45d6d219ca86f2260102", + "Available on the hub": true, + "Model sha": "aa6e42036cea01cb99426a9333481b353fd36e61", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "bardsai\/jaskier-7b-dpo-v5.6", - "Average \u2b06\ufe0f": 76.41, + "Model": "eren23\/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v3", + "Average \u2b06\ufe0f": 76.4, "ARC": 73.04, - "HellaSwag": 89.0, - "MMLU": 64.38, - "TruthfulQA": 77.81, - "Winogrande": 84.53, - "GSM8K": 69.67, + "HellaSwag": 89.11, + "MMLU": 64.79, + "TruthfulQA": 77.48, + "Winogrande": 84.77, + "GSM8K": 69.22, "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "25c0f5c1edad0ed1ab02347adf02fe03e0a3b62a", + "Model sha": "dd1a314a04b8b4faf33e7d5037a71246d3e65bad", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Kquant03\/Kaltsit-16x7B-bf16", + "Average \u2b06\ufe0f": 76.38, + "ARC": 73.46, + "HellaSwag": 88.92, + "MMLU": 64.62, + "TruthfulQA": 75.63, + "Winogrande": 84.53, + "GSM8K": 71.11, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 91.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fd3605c2b349939acfbd8a63bf08b8247b005485", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", - "Model": "JaeyeonKang\/CCK_Asura_v2.1", - "Average \u2b06\ufe0f": 76.41, - "ARC": 72.53, - "HellaSwag": 88.75, - "MMLU": 74.96, - "TruthfulQA": 67.33, - "Winogrande": 85.87, - "GSM8K": 68.99, + "Model": "CorticalStack\/neurotic-crown-clown-7b-tak-stack-dpo", + "Average \u2b06\ufe0f": 76.38, + "ARC": 72.44, + "HellaSwag": 88.73, + "MMLU": 64.56, + "TruthfulQA": 78.37, + "Winogrande": 83.82, + "GSM8K": 70.36, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-nc-4.0", - "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "546cdd443abc56b48aaadb4ebb5fb9249015f0bb", + "Model sha": "ec27a21a66dc4411f24f36d585787853ba2e6354", "Flagged": false, "MoE": false }, @@ -1151,6 +3175,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "jan-hq\/stealth-v2", + "Average \u2b06\ufe0f": 76.37, + "ARC": 73.89, + "HellaSwag": 89.26, + "MMLU": 64.94, + "TruthfulQA": 72.47, + "Winogrande": 88.0, + "GSM8K": 69.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d718acb1b95c85009db8dd34af1318bcaf23ebcd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "eldogbbhed\/NeuralBeagleJaskier", + "Average \u2b06\ufe0f": 76.37, + "ARC": 73.21, + "HellaSwag": 89.05, + "MMLU": 64.47, + "TruthfulQA": 77.08, + "Winogrande": 84.37, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b2102db3ca9307b5a84c5b89727e1341cdcd6ae7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralKrishnaMath-7B-slerp", + "Average \u2b06\ufe0f": 76.37, + "ARC": 73.29, + "HellaSwag": 88.92, + "MMLU": 64.67, + "TruthfulQA": 75.52, + "Winogrande": 84.93, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b2619e24f8b91f9e8328fc74f8259d4f87965351", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "bardsai\/jaskier-7b-dpo-v6.1", @@ -1168,7 +3261,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "aa3528c04c38fa49b5b65e1d064c46db3e9774f1", "Flagged": false, @@ -1220,6 +3313,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/strange_3236-7B", + "Average \u2b06\ufe0f": 76.35, + "ARC": 73.21, + "HellaSwag": 88.96, + "MMLU": 64.78, + "TruthfulQA": 77.6, + "Winogrande": 84.77, + "GSM8K": 68.76, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4f72a5270fadf90343354174bd37b796540b822e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "eren23\/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v4-test", + "Average \u2b06\ufe0f": 76.34, + "ARC": 73.12, + "HellaSwag": 89.09, + "MMLU": 64.79, + "TruthfulQA": 77.52, + "Winogrande": 84.69, + "GSM8K": 68.84, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ff89febead2585b2a1efae12b53887b18c283a8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chihoonlee10\/T3Q-DPO-Mistral-7B", + "Average \u2b06\ufe0f": 76.34, + "ARC": 72.78, + "HellaSwag": 89.29, + "MMLU": 64.25, + "TruthfulQA": 78.57, + "Winogrande": 84.93, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "87382cefca257137b983fd01d0e6a8839704d75e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "paulml\/OGNO-7B", @@ -1234,12 +3396,58 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "a5d97f2e6962dc2c539a5bbca6a1160f87ccce84", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_43-7B-dare_ties", + "Average \u2b06\ufe0f": 76.33, + "ARC": 73.55, + "HellaSwag": 89.05, + "MMLU": 64.8, + "TruthfulQA": 75.72, + "Winogrande": 84.77, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "be1fb5b492bb23ea2b58cbe3e598268013ce52db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ammarali32\/MultiVerse_LASER", + "Average \u2b06\ufe0f": 76.33, + "ARC": 72.53, + "HellaSwag": 88.81, + "MMLU": 64.52, + "TruthfulQA": 77.7, + "Winogrande": 84.93, + "GSM8K": 69.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", "Merged": false, "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "a5d97f2e6962dc2c539a5bbca6a1160f87ccce84", + "Available on the hub": false, + "Model sha": "7385d3aa94cebfb10f983bc905fea3e83c4a4e3c", "Flagged": false, "MoE": false }, @@ -1289,6 +3497,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralMergeTest-001", + "Average \u2b06\ufe0f": 76.32, + "ARC": 73.38, + "HellaSwag": 88.95, + "MMLU": 64.64, + "TruthfulQA": 75.82, + "Winogrande": 85.0, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "54bd62136c520275549b5feecd2e24d168551b24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BuckeyBarnes\/TriFusionNexus-7b", + "Average \u2b06\ufe0f": 76.32, + "ARC": 72.78, + "HellaSwag": 89.17, + "MMLU": 64.44, + "TruthfulQA": 78.13, + "Winogrande": 84.93, + "GSM8K": 68.46, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eb1fccccc6f51f19590fb24f320219915f1e9b87", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AtAndDev\/Ogno-Monarch-Neurotic-7B-Dare-Ties", + "Average \u2b06\ufe0f": 76.32, + "ARC": 73.21, + "HellaSwag": 88.99, + "MMLU": 64.58, + "TruthfulQA": 77.53, + "Winogrande": 84.53, + "GSM8K": 69.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4f49f24bfdbbcab0ec9195d62ff3cece08f93b26", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "eren23\/dpo-binarized-NeutrixOmnibe-7B", @@ -1352,12 +3629,35 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "1aaa8b8fd3f7a455be518c4d70b4a434b9977c87", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Jupiter-k-7B-slerp", + "Average \u2b06\ufe0f": 76.29, + "ARC": 74.23, + "HellaSwag": 88.82, + "MMLU": 65.01, + "TruthfulQA": 73.96, + "Winogrande": 85.24, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d696e99a2a4eeb13994c277f2fb113e9ddd1e632", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Gille\/StrangeMerges_21-7B-slerp", @@ -1381,6 +3681,121 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/Merkaba-Maven-0.1", + "Average \u2b06\ufe0f": 76.28, + "ARC": 72.87, + "HellaSwag": 89.2, + "MMLU": 64.45, + "TruthfulQA": 77.45, + "Winogrande": 84.93, + "GSM8K": 68.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "13377de9ab6ccde2b8bf4fec28f271d4e07a93bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/crown-clown-7b-slerp", + "Average \u2b06\ufe0f": 76.27, + "ARC": 73.46, + "HellaSwag": 89.26, + "MMLU": 64.13, + "TruthfulQA": 77.52, + "Winogrande": 84.93, + "GSM8K": 68.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bfe7413f586fe57ce629e04b2cb08b67a8775bc7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Neural-Krishna-Multiverse-7b", + "Average \u2b06\ufe0f": 76.27, + "ARC": 72.87, + "HellaSwag": 89.06, + "MMLU": 64.72, + "TruthfulQA": 76.75, + "Winogrande": 84.69, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f87fafa1e5df8a3b9dfb46c6dd0813b0c9e56e6b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralTrix-bf16", + "Average \u2b06\ufe0f": 76.26, + "ARC": 72.87, + "HellaSwag": 89.12, + "MMLU": 64.27, + "TruthfulQA": 79.54, + "Winogrande": 84.61, + "GSM8K": 67.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9bc11a59594b3a4c601f3e86d88ef363fb5000f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "liminerity\/Blur-7b-slerp-v1.46", + "Average \u2b06\ufe0f": 76.26, + "ARC": 73.29, + "HellaSwag": 89.07, + "MMLU": 64.37, + "TruthfulQA": 76.61, + "Winogrande": 84.53, + "GSM8K": 69.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "744c0e181c49b43857828fe1d14bdf9976d6c6a8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "mlabonne\/Monarch-7B", @@ -1398,12 +3813,35 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "1ccf1b7b37818c3b11d14dc0ef6fe4344a3cb4d5", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_42-7B-dare_ties", + "Average \u2b06\ufe0f": 76.24, + "ARC": 73.38, + "HellaSwag": 88.96, + "MMLU": 64.62, + "TruthfulQA": 75.44, + "Winogrande": 85.0, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "01eb01b50a5036f094e95cc20a0275ab60939ce3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Kukedlc\/NeuTrixOmniBe-7B-model-remix", @@ -1451,25 +3889,25 @@ "MoE": true }, { - "T": "\ud83d\udcac", - "Model": "moreh\/MoMo-70B-lora-1.8.4-DPO", + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralTrixlaser-bf16", "Average \u2b06\ufe0f": 76.23, - "ARC": 69.62, - "HellaSwag": 85.35, - "MMLU": 77.33, - "TruthfulQA": 64.64, - "Winogrande": 84.14, - "GSM8K": 76.27, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", + "ARC": 72.18, + "HellaSwag": 89.06, + "MMLU": 64.21, + "TruthfulQA": 78.69, + "Winogrande": 84.77, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "mit", - "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "a2c3a87dd53a87dc9fc622ce4ddbb05d3e9cf6a9", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "942b35ccb48ded2f0fd462c21b6e1df35b4ea910", "Flagged": false, "MoE": false }, @@ -1488,14 +3926,37 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "a2c3a87dd53a87dc9fc622ce4ddbb05d3e9cf6a9", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "u66u\/NeuralJaskier-7b-dpo", + "Average \u2b06\ufe0f": 76.22, + "ARC": 71.59, + "HellaSwag": 88.87, + "MMLU": 64.49, + "TruthfulQA": 78.42, + "Winogrande": 84.45, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc363869e472a853dc3d298e44f2098ab1e9b788", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "yleo\/ParrotOgno-7B", @@ -1579,10 +4040,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "a8871af9db183f2e7fe7c30bb2242b3b7827e53f", "Flagged": false, @@ -1659,7 +4120,7 @@ }, { "T": "\ud83d\udd36", - "Model": "mayacinka\/Buttercup-7b-dpo-slerp", + "Model": "mayacinka\/Buttercup-7b-dpo-ties", "Average \u2b06\ufe0f": 76.19, "ARC": 72.7, "HellaSwag": 89.09, @@ -1671,18 +4132,18 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "a9f4d04b59d764a45fabac9dd3d7f72b795967f0", + "Model sha": "608d7998c1b8f4707e065642a7cfa3d0ddb80100", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "mayacinka\/Buttercup-7b-dpo-ties", + "Model": "mayacinka\/Buttercup-7b-dpo-slerp", "Average \u2b06\ufe0f": 76.19, "ARC": 72.7, "HellaSwag": 89.09, @@ -1694,12 +4155,12 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "608d7998c1b8f4707e065642a7cfa3d0ddb80100", + "Model sha": "a9f4d04b59d764a45fabac9dd3d7f72b795967f0", "Flagged": false, "MoE": false }, @@ -1741,14 +4202,37 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "?", "#Params (B)": 87.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "b4b717be590394a4e70853cb444bd0964526c500", - "Flagged": true, + "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralCeptrix-7B-SLERP", + "Average \u2b06\ufe0f": 76.18, + "ARC": 72.44, + "HellaSwag": 89.3, + "MMLU": 64.5, + "TruthfulQA": 79.13, + "Winogrande": 85.08, + "GSM8K": 66.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e16e6c9f76d8521f1c535cb9b1e940c63449d0ff", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Gille\/StrangeMerges_27-7B-dare_ties", @@ -1812,7 +4296,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "055dc83f36a3a6c6d477dba1547f60a9592b3978", "Flagged": false, @@ -1835,7 +4319,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "853370b5907d272f93870b47e67a5622da643801", "Flagged": false, @@ -1855,14 +4339,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "mit", + "Merged": false, + "Hub License": "?", "#Params (B)": 60.81, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "1e61f28b326fe0080ad476ce2b1dd041ec9f147f", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -1927,7 +4411,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "a0d648c1bcc3f1615bb2f0a94c6d32e7abde355d", "Flagged": false, @@ -1947,15 +4431,38 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "f820ce616f062fa76c13845fb198490418676223", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/MergeCeption-7B-v3", + "Average \u2b06\ufe0f": 76.15, + "ARC": 72.95, + "HellaSwag": 89.18, + "MMLU": 64.59, + "TruthfulQA": 78.62, + "Winogrande": 85.0, + "GSM8K": 66.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c7df5c504a5e057be540470a27a02579338884fb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mlabonne\/NeuralMonarch-7B", @@ -2017,7 +4524,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 72.29, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -2042,7 +4549,7 @@ "Merged": false, "Hub License": "cc", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "099b9c3e105fbb579d561fe93174ae3bd75dac8d", "Flagged": false, @@ -2071,6 +4578,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuralKrishna-7B-v3", + "Average \u2b06\ufe0f": 76.13, + "ARC": 73.63, + "HellaSwag": 88.91, + "MMLU": 64.45, + "TruthfulQA": 74.11, + "Winogrande": 84.69, + "GSM8K": 70.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9e743423df10fe2b4dcc37ac0da13ad56e49a16c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "bardsai\/jaskier-7b-dpo-v3.3", @@ -2094,6 +4624,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralMarioMonarch-7B-slerp", + "Average \u2b06\ufe0f": 76.11, + "ARC": 73.81, + "HellaSwag": 89.04, + "MMLU": 64.61, + "TruthfulQA": 74.97, + "Winogrande": 85.0, + "GSM8K": 69.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8fca4987ba90d95544840e1921ebc819b880cc8d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "macadeliccc\/MonarchLake-7B", @@ -2108,10 +4661,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "f1dc346e4c117d73dd706971a50d6b393390984b", "Flagged": false, @@ -2134,7 +4687,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "5c649b6bbb8aa16d52dda26c5ce8574d1c7a3274", "Flagged": false, @@ -2154,8 +4707,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -2186,6 +4739,98 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "Kukedlc\/Fasciculus-Arcuatus-7B-slerp", + "Average \u2b06\ufe0f": 76.07, + "ARC": 73.55, + "HellaSwag": 88.95, + "MMLU": 64.65, + "TruthfulQA": 72.53, + "Winogrande": 85.71, + "GSM8K": 71.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5ceeb8b14477b15960c21443107befb46228b0b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuralExperiment-7b-dare-ties", + "Average \u2b06\ufe0f": 76.06, + "ARC": 73.63, + "HellaSwag": 88.87, + "MMLU": 64.66, + "TruthfulQA": 74.86, + "Winogrande": 84.45, + "GSM8K": 69.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3fc29ef22b0e7fc4d17250422804ed1b03eb9732", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/RoleBeagle-11B", + "Average \u2b06\ufe0f": 76.06, + "ARC": 72.35, + "HellaSwag": 89.77, + "MMLU": 66.35, + "TruthfulQA": 77.92, + "Winogrande": 84.06, + "GSM8K": 65.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "7637cbf40c746030910154e0b344c5358f35a878", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Calme-7B-Instruct-v0.5", + "Average \u2b06\ufe0f": 76.05, + "ARC": 72.87, + "HellaSwag": 88.77, + "MMLU": 64.69, + "TruthfulQA": 73.68, + "Winogrande": 84.37, + "GSM8K": 71.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7e26287665e6214be131f4e7ee20a312a07a4c1c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/Capricorn-7B-DPO", @@ -2232,6 +4877,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "rwitz\/experiment26-SPIN-iter-0", + "Average \u2b06\ufe0f": 76.04, + "ARC": 72.44, + "HellaSwag": 88.74, + "MMLU": 64.64, + "TruthfulQA": 74.9, + "Winogrande": 85.24, + "GSM8K": 70.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b7174ccf5c91095737cdb29f50853512017a1ac4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Neural-4-ARC-7b", + "Average \u2b06\ufe0f": 76.04, + "ARC": 74.06, + "HellaSwag": 89.05, + "MMLU": 64.93, + "TruthfulQA": 74.12, + "Winogrande": 84.77, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36a55a14cd7b3e4143b113b9aab4fe4085a78838", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "nlpguy\/AlloyIngotNeo", @@ -2255,6 +4946,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MixtureofMerges-MoE-4x7b-v5", + "Average \u2b06\ufe0f": 76.02, + "ARC": 73.89, + "HellaSwag": 89.0, + "MMLU": 64.69, + "TruthfulQA": 73.73, + "Winogrande": 85.08, + "GSM8K": 69.75, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "86fff26d9a2ad942ae1ca1ad31d659fbf8429db5", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_36-7B-slerp", + "Average \u2b06\ufe0f": 76.01, + "ARC": 72.61, + "HellaSwag": 88.83, + "MMLU": 64.77, + "TruthfulQA": 77.05, + "Winogrande": 84.29, + "GSM8K": 68.54, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f9fcbd3895d6c63aed550134353473de0bd9b662", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CultriX\/MonaTrix-v6", @@ -2278,6 +5015,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Kukedlc\/NeuralKrishna-7B-V2-DPO", + "Average \u2b06\ufe0f": 76.0, + "ARC": 74.06, + "HellaSwag": 88.97, + "MMLU": 64.41, + "TruthfulQA": 76.19, + "Winogrande": 84.29, + "GSM8K": 68.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c9beb3cba8030cb4fe7d96dd513c9e7ab40da126", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "paulml\/DPOB-NMTOB-7B", @@ -2301,6 +5061,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralMona_MoE-4x7B", + "Average \u2b06\ufe0f": 76.0, + "ARC": 73.72, + "HellaSwag": 89.03, + "MMLU": 64.3, + "TruthfulQA": 77.25, + "Winogrande": 84.29, + "GSM8K": 67.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "869c5cafb3f5002a0d273621519e3f352418eded", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "abideen\/AlphaMonarch-laser", @@ -2318,12 +5101,58 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "bff2cd7ba1f8a742cd22cd9df22485636c3b6410", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralGanesha-7b", + "Average \u2b06\ufe0f": 75.99, + "ARC": 73.98, + "HellaSwag": 88.85, + "MMLU": 64.41, + "TruthfulQA": 74.14, + "Winogrande": 84.06, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "16e76c8a0fcf0556441f4cf4cd1549613f8d2084", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralMona_MoE-4x7B", + "Average \u2b06\ufe0f": 75.99, + "ARC": 73.89, + "HellaSwag": 89.02, + "MMLU": 64.31, + "TruthfulQA": 77.27, + "Winogrande": 84.06, + "GSM8K": 67.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "869c5cafb3f5002a0d273621519e3f352418eded", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "mlabonne\/AlphaMonarch-7B", @@ -2341,7 +5170,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 78.0, + "Hub \u2764\ufe0f": 131.0, "Available on the hub": true, "Model sha": "9a1c8000e25d27264c66c58603590f0acb8ef168", "Flagged": false, @@ -2361,15 +5190,38 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "7eb4f63abc5c6891503008eb613287eff8c15e30", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/Blur-7b-slerp-v1.41", + "Average \u2b06\ufe0f": 75.98, + "ARC": 72.78, + "HellaSwag": 88.65, + "MMLU": 64.84, + "TruthfulQA": 74.23, + "Winogrande": 83.9, + "GSM8K": 71.49, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e76e89ba74eff149bc5f3ffbe7bc35beaef9269", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "touqir\/Cyrax-7B", @@ -2387,7 +5239,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "783a2f1231542b9fe8bc728dc676745c62f35b9f", "Flagged": false, @@ -2433,12 +5285,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "ca8c55fbbb2a0f7dd0de41579d98bbf24946b712", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Eric111\/UltraCatunaMayo-DPO", + "Average \u2b06\ufe0f": 75.96, + "ARC": 72.87, + "HellaSwag": 88.75, + "MMLU": 65.18, + "TruthfulQA": 76.44, + "Winogrande": 83.98, + "GSM8K": 68.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67f6f5ea337547b3f5e287e0ed1392ef0462e65a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "paulml\/OmniBeagleMBX-v3-7B", @@ -2485,6 +5360,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "abideen\/AlphaMonarch-daser", + "Average \u2b06\ufe0f": 75.94, + "ARC": 73.04, + "HellaSwag": 89.23, + "MMLU": 64.43, + "TruthfulQA": 78.01, + "Winogrande": 84.69, + "GSM8K": 66.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "5b806671b663295f5212704dfb7373ddfefe804f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Kukedlc\/NeuralFusion-7b-Dare-Ties", + "Average \u2b06\ufe0f": 75.94, + "ARC": 73.21, + "HellaSwag": 88.96, + "MMLU": 64.77, + "TruthfulQA": 73.32, + "Winogrande": 85.56, + "GSM8K": 69.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "58d3d87993899cb6fbdead56c7554ff897b9657c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v6.0", @@ -2531,6 +5452,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/UltraCatunaMayo", + "Average \u2b06\ufe0f": 75.93, + "ARC": 72.61, + "HellaSwag": 88.37, + "MMLU": 65.03, + "TruthfulQA": 74.06, + "Winogrande": 83.19, + "GSM8K": 72.33, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17de371a605ac49c69ba0130037251ba5a034192", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "paulml\/NeuralOmniBeagleMBX-v3-7B", @@ -2545,10 +5489,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "37084955ee092548abfe356be4e6cfc46daa9cb4", "Flagged": false, @@ -2568,10 +5512,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "ac42a1ab3cb135dd8ff9ab600d5562251e8c6986", "Flagged": false, @@ -2594,12 +5538,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 33.0, + "Hub \u2764\ufe0f": 35.0, "Available on the hub": true, "Model sha": "a619fd0fcbdfcc897054491c2f285677bee38a11", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v0.3", + "Average \u2b06\ufe0f": 75.91, + "ARC": 76.28, + "HellaSwag": 91.53, + "MMLU": 68.1, + "TruthfulQA": 69.44, + "Winogrande": 87.37, + "GSM8K": 62.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "89d77a1219490fc423615f3ca28c1888bb4845a5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "paulml\/OmniBeagleSquaredMBX-v3-7B", @@ -2617,12 +5584,35 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "88928f55d51c0819de3b64e6c37689b87a89aac4", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_40-7B-dare_ties", + "Average \u2b06\ufe0f": 75.91, + "ARC": 73.04, + "HellaSwag": 88.62, + "MMLU": 64.59, + "TruthfulQA": 77.21, + "Winogrande": 83.98, + "GSM8K": 68.01, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d5b6444180fe3c92b2ecb7647ca2fe15f30756f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "yam-peleg\/Experiment22-7B", @@ -2646,6 +5636,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/MyModelsMerge-7b", + "Average \u2b06\ufe0f": 75.9, + "ARC": 73.46, + "HellaSwag": 88.59, + "MMLU": 64.39, + "TruthfulQA": 74.47, + "Winogrande": 84.21, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cc04d33e0008214f7a2937c5236b14f98c2c8bda", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "YKM12\/Mistral-7B-summ-privatev1", @@ -2669,6 +5682,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Yi-34Bx2-MOE-200K", + "Average \u2b06\ufe0f": 75.89, + "ARC": 70.48, + "HellaSwag": 84.63, + "MMLU": 76.64, + "TruthfulQA": 68.19, + "Winogrande": 82.72, + "GSM8K": 72.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a5965f77bbb0fe23f16a5137918af27c753800af", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "vicgalleorg\/test1", + "Average \u2b06\ufe0f": 75.89, + "ARC": 72.27, + "HellaSwag": 89.52, + "MMLU": 66.67, + "TruthfulQA": 78.32, + "Winogrande": 83.9, + "GSM8K": 64.67, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "50b34c24addd4efd365e9d3f44f370c3b6b56c2e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NeverSleep\/MiquMaid-v2-2x70B-DPO", @@ -2686,7 +5745,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 125.35, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "30e44c452e38ff3d879d7ba92a130fa2cc072754", "Flagged": false, @@ -2707,14 +5766,83 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "?", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "bf4cb27f17bfc58aaf6011a8ba8393a1177ebbe7", - "Flagged": true, + "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/MoNeuTrix-7B-v1", + "Average \u2b06\ufe0f": 75.87, + "ARC": 72.87, + "HellaSwag": 88.98, + "MMLU": 64.65, + "TruthfulQA": 77.18, + "Winogrande": 84.37, + "GSM8K": 67.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5b1baedc23f57ba43c07c257fb665c171cc78cfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Kukedlc\/Brocae-Area-7B-slerp", + "Average \u2b06\ufe0f": 75.86, + "ARC": 73.81, + "HellaSwag": 88.98, + "MMLU": 64.55, + "TruthfulQA": 74.13, + "Winogrande": 85.08, + "GSM8K": 68.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "09f40713a4cbe65f4843b13d9ae8cf840b75da86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abideen\/AlphaMonarch-dora", + "Average \u2b06\ufe0f": 75.86, + "ARC": 73.21, + "HellaSwag": 89.26, + "MMLU": 64.47, + "TruthfulQA": 78.02, + "Winogrande": 84.45, + "GSM8K": 65.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "34e3f31067be2bcbf86c8af9d137db227b2ece20", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "alnrg2arg\/blockchainlabs_joe_bez_seminar", @@ -2761,6 +5889,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MSL7\/INEX4-7b", + "Average \u2b06\ufe0f": 75.84, + "ARC": 72.95, + "HellaSwag": 88.79, + "MMLU": 64.7, + "TruthfulQA": 74.42, + "Winogrande": 83.9, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4f256a193876920b54ac8d6c0fa67accb2dd25b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CultriX\/NeuralTrix-7B-v1", @@ -2784,6 +5935,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AiMavenAi\/Prometheus-1.3", + "Average \u2b06\ufe0f": 75.81, + "ARC": 72.61, + "HellaSwag": 89.02, + "MMLU": 64.26, + "TruthfulQA": 79.29, + "Winogrande": 85.16, + "GSM8K": 64.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c241960b69943b3d32b8af110bbed20508265334", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Kquant03\/Samlagast-7B-bf16", @@ -2876,6 +6050,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ChaoticNeutrals\/Prima-LelantaclesV7-experimental-7b", + "Average \u2b06\ufe0f": 75.76, + "ARC": 72.87, + "HellaSwag": 88.72, + "MMLU": 64.31, + "TruthfulQA": 74.62, + "Winogrande": 84.77, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "61bb0467d7026d9ab5354e6c33d8e6361ba00677", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/Capricorn-7B", @@ -2913,7 +6110,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, @@ -3051,10 +6248,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "ee2dba5b9877b3b6d8f5b28f2900e4bfd4152a1b", "Flagged": false, @@ -3097,7 +6294,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -3152,6 +6349,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Prima-LelantaclesV6.69-7b", + "Average \u2b06\ufe0f": 75.7, + "ARC": 72.61, + "HellaSwag": 88.65, + "MMLU": 64.53, + "TruthfulQA": 75.26, + "Winogrande": 84.69, + "GSM8K": 68.46, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "185e114fd89bd0d91805e5e14541d0e28a20b821", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Topxtral-4x7B-v0.1", + "Average \u2b06\ufe0f": 75.68, + "ARC": 72.53, + "HellaSwag": 88.33, + "MMLU": 64.96, + "TruthfulQA": 73.38, + "Winogrande": 83.19, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1a219935a01db03820ddabb2e29c199222a772e5", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "yleo\/EmertonOmniBeagle-7B-dpo", @@ -3175,6 +6418,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeoCortex-7B-slerp", + "Average \u2b06\ufe0f": 75.67, + "ARC": 72.87, + "HellaSwag": 88.68, + "MMLU": 64.71, + "TruthfulQA": 70.43, + "Winogrande": 85.56, + "GSM8K": 71.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "71060067cb047f4684ba82d2f42ca2533e616e8b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "rizla\/rizla-17", @@ -3198,6 +6464,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "vishnukv\/WestSeverusJaskier", + "Average \u2b06\ufe0f": 75.67, + "ARC": 71.76, + "HellaSwag": 88.16, + "MMLU": 64.94, + "TruthfulQA": 73.18, + "Winogrande": 82.87, + "GSM8K": 73.09, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d3c32e9c804c110986c4c526e50297d7a0545f03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/multimaster-7b-v6", + "Average \u2b06\ufe0f": 75.66, + "ARC": 72.78, + "HellaSwag": 88.77, + "MMLU": 64.74, + "TruthfulQA": 70.89, + "Winogrande": 86.42, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cc18e2b0b9764f255341d3e530d018545987544b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "mlabonne\/OmniBeagle-7B", @@ -3244,6 +6556,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "mlabonne\/Beyonder-4x7B-v3", + "Average \u2b06\ufe0f": 75.65, + "ARC": 71.67, + "HellaSwag": 88.86, + "MMLU": 64.87, + "TruthfulQA": 74.44, + "Winogrande": 83.5, + "GSM8K": 70.58, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 45.0, + "Available on the hub": true, + "Model sha": "d8f0911773d8d881ffa04dafc5c3120dc4c18a3c", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "YKM11\/Mistral-7B-adaptv0.9", @@ -3284,12 +6619,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "2f83b45077479bc3f663da50c4c40372894bf92e", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/OmniCorso-7B", + "Average \u2b06\ufe0f": 75.64, + "ARC": 72.44, + "HellaSwag": 88.78, + "MMLU": 65.08, + "TruthfulQA": 73.5, + "Winogrande": 83.5, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3f9de5b67315d1b35a377aa1a6ca8dad580a8370", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "daxiongshu\/Pluto_24B_DPO_63", @@ -3313,6 +6671,75 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/merge_7B_state_2", + "Average \u2b06\ufe0f": 75.58, + "ARC": 73.12, + "HellaSwag": 88.62, + "MMLU": 65.0, + "TruthfulQA": 71.37, + "Winogrande": 83.5, + "GSM8K": 71.87, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7b5b4c6ecd7e6698aac07f0d440ba90260ad202e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralShiva-7B-DT", + "Average \u2b06\ufe0f": 75.57, + "ARC": 72.7, + "HellaSwag": 88.68, + "MMLU": 64.66, + "TruthfulQA": 74.17, + "Winogrande": 84.14, + "GSM8K": 69.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "65bf4997806c3131ac8ff164503282e5bb6df795", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/pikus-pikantny-7B-dare", + "Average \u2b06\ufe0f": 75.56, + "ARC": 72.18, + "HellaSwag": 88.56, + "MMLU": 65.0, + "TruthfulQA": 73.29, + "Winogrande": 83.43, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae6673e66e35679c14f4cc09237568d852d43b3d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "kaitchup\/Mayonnaise-4in1-022", @@ -3376,12 +6803,81 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "d8b56411b045767511593f901179c01855e9d7e8", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_44-7B-dare_ties", + "Average \u2b06\ufe0f": 75.51, + "ARC": 71.76, + "HellaSwag": 87.84, + "MMLU": 65.61, + "TruthfulQA": 71.85, + "Winogrande": 83.74, + "GSM8K": 72.25, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7a55d23772bf5862603076df515f230970a53532", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/bruphin-lambda", + "Average \u2b06\ufe0f": 75.5, + "ARC": 72.35, + "HellaSwag": 88.22, + "MMLU": 64.9, + "TruthfulQA": 72.36, + "Winogrande": 84.45, + "GSM8K": 70.74, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "276d1c0358bdf051b0be4f3e8eb0146f8e863f36", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Smaug-Mixtral-v0.1", + "Average \u2b06\ufe0f": 75.49, + "ARC": 74.66, + "HellaSwag": 87.72, + "MMLU": 70.06, + "TruthfulQA": 66.95, + "Winogrande": 81.61, + "GSM8K": 71.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "98fdc8315906b0a8b9e7f24bad89914869fcfc20", + "Flagged": false, + "MoE": true + }, { "T": "\ud83e\udd1d", "Model": "vanillaOVO\/supermario_v2", @@ -3399,7 +6895,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "ae95b6254eee9bd1de68fc6f4881a7bb98d57235", "Flagged": false, @@ -3468,7 +6964,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": false, "Model sha": "5b96d5e0a38d25fe6bd72939a8eb193c34e59232", "Flagged": false, @@ -3491,12 +6987,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 113.66, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "583254a5a134243d7793b311c465da12b10a3ff2", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Paradigm_7B", + "Average \u2b06\ufe0f": 75.47, + "ARC": 73.63, + "HellaSwag": 88.66, + "MMLU": 64.02, + "TruthfulQA": 75.19, + "Winogrande": 84.53, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "33122df31c3aa5ae69d591ed51c9415342541225", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ibivibiv\/multimaster-7b-v4", @@ -3512,7 +7031,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 35.43, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -3537,7 +7056,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "ead4b4aedf94b98916f30388b85620a3583375e8", "Flagged": false, @@ -3558,10 +7077,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-2.0", + "Hub License": "cc0-1.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 134.0, + "Available on the hub": true, "Model sha": "cf06159aaaadda2ca50b19ce547a52424f7d47c3", "Flagged": false, "MoE": false @@ -3583,7 +7102,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "a704fa5a292b5f8667a23f2e818ae8cdcf51779b", "Flagged": false, @@ -3606,7 +7125,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "b82e05bf781ad9be0febdb2d8aaa4efbc7ca43fc", "Flagged": false, @@ -3629,7 +7148,7 @@ "Merged": true, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "5d6dd3a16f0469cff432410b29ec410167b71c49", "Flagged": false, @@ -3637,7 +7156,7 @@ }, { "T": "\ud83d\udd36", - "Model": "one-man-army\/UNA-34Beagles-32K-bf16-v1", + "Model": "fblgit\/UNA-34Beagles-32K-v1", "Average \u2b06\ufe0f": 75.41, "ARC": 73.55, "HellaSwag": 85.93, @@ -3652,15 +7171,15 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "d6024b97f624e9169a63f5faccb8c5ab121eb13a", + "Model sha": "e02a631564990af3d9c8b0232f979af11cd8b6f6", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "fblgit\/UNA-34Beagles-32K-v1", + "Model": "one-man-army\/UNA-34Beagles-32K-bf16-v1", "Average \u2b06\ufe0f": 75.41, "ARC": 73.55, "HellaSwag": 85.93, @@ -3675,9 +7194,9 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, - "Model sha": "e02a631564990af3d9c8b0232f979af11cd8b6f6", + "Model sha": "d6024b97f624e9169a63f5faccb8c5ab121eb13a", "Flagged": false, "MoE": false }, @@ -3765,9 +7284,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "fbf1c9958c47062e2db30276c723867c0d019652", "Flagged": false, @@ -3819,6 +7338,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Nitral-AI\/Lelanta-lake-7b", + "Average \u2b06\ufe0f": 75.39, + "ARC": 72.27, + "HellaSwag": 88.95, + "MMLU": 64.31, + "TruthfulQA": 73.05, + "Winogrande": 84.61, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9a99e78b811a98cb9929530b261fd4cdaed4c558", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "jsfs11\/MoEv4Config-TestWeightedTIES-7b", @@ -3882,12 +7424,35 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "e1ae2c1e9bea8b54f6b8bff41a4f50895625a6ed", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Nitral-AI\/Eris_PrimeV3.05-Vision-7B", + "Average \u2b06\ufe0f": 75.37, + "ARC": 72.78, + "HellaSwag": 88.48, + "MMLU": 65.09, + "TruthfulQA": 72.76, + "Winogrande": 83.66, + "GSM8K": 69.45, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fe0e9d11143618c06eba0b2756dce22491dc263f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "macadeliccc\/WestLake-7B-v2-laser-truthy-dpo", @@ -3905,7 +7470,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "e01fb197b4303ba63ba2f4d68a897006ec7ec4fd", "Flagged": false, @@ -3995,10 +7560,10 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-2.0", + "Hub License": "cc0-1.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 134.0, + "Available on the hub": true, "Model sha": "cf06159aaaadda2ca50b19ce547a52424f7d47c3", "Flagged": false, "MoE": false @@ -4020,7 +7585,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "b6c9416b0deeb567f59891db1a1dce7a59fc54e4", "Flagged": false, @@ -4043,12 +7608,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "23f8fc9ed8d1d5ff71695307e3e1dd43ae670549", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment23-7B", + "Average \u2b06\ufe0f": 75.31, + "ARC": 72.35, + "HellaSwag": 88.77, + "MMLU": 64.17, + "TruthfulQA": 78.87, + "Winogrande": 85.32, + "GSM8K": 62.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1442ca4e728892f18ef101c4987bdf11ef5bbae5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Kukedlc\/Neural4gsm8k", @@ -4135,7 +7723,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "c3fa3d4679f303bce6d56357abb9069fdf8b44c2", "Flagged": false, @@ -4181,7 +7769,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "c8ad8ee000e4e042d80e4cf53fb6d0815d7743dd", "Flagged": false, @@ -4211,25 +7799,25 @@ "MoE": false }, { - "T": "\ud83e\udd1d", - "Model": "BarryFutureman\/WildMarcoroni-Variant1-7B", + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-70B-v1.6", "Average \u2b06\ufe0f": 75.29, - "ARC": 73.98, - "HellaSwag": 88.61, - "MMLU": 64.81, - "TruthfulQA": 69.76, - "Winogrande": 84.29, - "GSM8K": 70.28, - "Type": "base merges and moerges", - "Architecture": "MistralForCausalLM", + "ARC": 71.33, + "HellaSwag": 87.06, + "MMLU": 74.76, + "TruthfulQA": 63.8, + "Winogrande": 83.98, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", - "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, - "Model sha": "288b2e327f81e6f97fe1d68e2f0f08a46cdbf6eb", + "Model sha": "031e9404b7a1467fdcc96bc109e05b640d573209", "Flagged": false, "MoE": false }, @@ -4256,9 +7844,32 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/WildMarcoroni-Variant1-7B", + "Average \u2b06\ufe0f": 75.29, + "ARC": 73.98, + "HellaSwag": 88.61, + "MMLU": 64.81, + "TruthfulQA": 69.76, + "Winogrande": 84.29, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "288b2e327f81e6f97fe1d68e2f0f08a46cdbf6eb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "alnrg2arg\/test2_4", + "Model": "alnrg2arg\/blockchainlabs_7B_merged_test2_4", "Average \u2b06\ufe0f": 75.28, "ARC": 73.55, "HellaSwag": 88.87, @@ -4271,17 +7882,17 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": true, - "Hub License": "apache-2.0", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "ed17cf5af87733ffd7836ab99f27991544ba2547", + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "eb671cc5e88553f568c17eaf0e60d1616665ed95", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "alnrg2arg\/blockchainlabs_7B_merged_test2_4", + "Model": "alnrg2arg\/test2_4", "Average \u2b06\ufe0f": 75.28, "ARC": 73.55, "HellaSwag": 88.87, @@ -4293,12 +7904,12 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "cc-by-nc-4.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, - "Model sha": "eb671cc5e88553f568c17eaf0e60d1616665ed95", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ed17cf5af87733ffd7836ab99f27991544ba2547", "Flagged": false, "MoE": false }, @@ -4342,7 +7953,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": false, "Model sha": "803a3e7f24f61e8cd53ef4133ae22c3ce2568a78", "Flagged": false, @@ -4366,7 +7977,7 @@ "Hub License": "?", "#Params (B)": 24.15, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "307a74cb147a9d93e20755b047e9b5be4293e017", "Flagged": false, "MoE": false @@ -4385,8 +7996,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -4509,9 +8120,32 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/WestMonarchLasers-7B-slerp", + "Average \u2b06\ufe0f": 75.23, + "ARC": 72.44, + "HellaSwag": 88.66, + "MMLU": 64.73, + "TruthfulQA": 72.4, + "Winogrande": 85.56, + "GSM8K": 67.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cce3df27caa1c26a96308e429c27d27465f6d6d2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.22", + "Model": "YouKnwMe\/Mistral-7B-Instruct-exp-e2", "Average \u2b06\ufe0f": 75.23, "ARC": 72.53, "HellaSwag": 88.5, @@ -4528,13 +8162,13 @@ "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "5bcce7562c547b81d8bc41363e1fedb15fde429c", + "Model sha": "9e85b1810b7e4c549711b217cadde6e93c6b60d8", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "YouKnwMe\/Mistral-7B-Instruct-exp-e2", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.23", "Average \u2b06\ufe0f": 75.23, "ARC": 72.53, "HellaSwag": 88.5, @@ -4551,13 +8185,13 @@ "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "9e85b1810b7e4c549711b217cadde6e93c6b60d8", + "Model sha": "c11553f07f16813545fe8c8eab410b164eb7cea3", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.21", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.22", "Average \u2b06\ufe0f": 75.23, "ARC": 72.53, "HellaSwag": 88.5, @@ -4574,13 +8208,13 @@ "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "15f7ace0735678feec75a36589ed4760bfa172bb", + "Model sha": "5bcce7562c547b81d8bc41363e1fedb15fde429c", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.23", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.21", "Average \u2b06\ufe0f": 75.23, "ARC": 72.53, "HellaSwag": 88.5, @@ -4597,7 +8231,7 @@ "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "c11553f07f16813545fe8c8eab410b164eb7cea3", + "Model sha": "15f7ace0735678feec75a36589ed4760bfa172bb", "Flagged": false, "MoE": false }, @@ -4687,7 +8321,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "e84cd31eaed755a286dee0c9ca2fe4308e693f64", "Flagged": false, @@ -4753,7 +8387,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, @@ -4877,6 +8511,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen10-mistral-7B", + "Average \u2b06\ufe0f": 75.19, + "ARC": 71.76, + "HellaSwag": 88.27, + "MMLU": 64.75, + "TruthfulQA": 72.23, + "Winogrande": 82.72, + "GSM8K": 71.42, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2d6906ecf27b829b66db8bd9900aca0be220910d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CultriX\/Wernicke-7B-v9", @@ -4940,7 +8597,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "e13a48ef1524ba35615d7f63834e7c9192fa1836", "Flagged": false, @@ -4963,7 +8620,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "cd2fa5c2188588b903fff2070a389db3b24031a4", "Flagged": true, @@ -4983,7 +8640,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -5038,6 +8695,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "jambroz\/sixtyoneeighty-FNCARL-7B-slerp", + "Average \u2b06\ufe0f": 75.14, + "ARC": 71.59, + "HellaSwag": 87.78, + "MMLU": 65.27, + "TruthfulQA": 71.52, + "Winogrande": 83.19, + "GSM8K": 71.49, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8030132398d72adcb005802cf7800d253c7ab32e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "SC56\/Mistral-7B-orca-dpo-8h", @@ -5078,7 +8758,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "5ecc835f4137adac99198831c61c2afff4f340cf", "Flagged": false, @@ -5101,7 +8781,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "538565474e9cf94b3ab4cd0b74a3537a338831f5", "Flagged": false, @@ -5130,6 +8810,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_6-7B-dare_ties", + "Average \u2b06\ufe0f": 75.12, + "ARC": 73.04, + "HellaSwag": 88.82, + "MMLU": 64.52, + "TruthfulQA": 72.0, + "Winogrande": 85.71, + "GSM8K": 66.64, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d4afbe8b1ac311c82f9f195b0bbb933d8c16cbb0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NeverSleep\/MiquMaid-v1-70B", @@ -5147,7 +8850,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "0dc1f9340fac9aadf883f52e6409e49e8d286af6", "Flagged": false, @@ -5306,7 +9009,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-4.0", + "Hub License": "?", "#Params (B)": 60.81, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -5329,33 +9032,10 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", - "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "d187b7bd6757d78bf89aaad8b0b5834ddbf29392", - "Flagged": false, - "MoE": false - }, - { - "T": "\ud83d\udd36", - "Model": "Weyaxi\/Bagel-Hermes-2x34b", - "Average \u2b06\ufe0f": 75.1, - "ARC": 69.8, - "HellaSwag": 85.26, - "MMLU": 77.24, - "TruthfulQA": 64.82, - "Winogrande": 84.77, - "GSM8K": 68.69, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MixtralForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, "Model sha": "d187b7bd6757d78bf89aaad8b0b5834ddbf29392", "Flagged": false, "MoE": true @@ -5452,6 +9132,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen5-mistral-7B", + "Average \u2b06\ufe0f": 75.05, + "ARC": 72.01, + "HellaSwag": 88.47, + "MMLU": 64.95, + "TruthfulQA": 72.17, + "Winogrande": 82.87, + "GSM8K": 69.83, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "327c3aa9b5c4dfd66b59f9b86eece1f87459ccf7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BarryFutureman\/WestLakeX-7B-EvoMerge-Variant2", @@ -5498,6 +9201,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/merge_7B_state_1", + "Average \u2b06\ufe0f": 75.04, + "ARC": 73.81, + "HellaSwag": 88.57, + "MMLU": 64.87, + "TruthfulQA": 69.11, + "Winogrande": 83.9, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9eacf25cbbd3aa9dac99322a6cf9152cdeb3c6c4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "flemmingmiguel\/MBX-7B", @@ -5521,6 +9247,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "4season\/alignment-model-test3", + "Average \u2b06\ufe0f": 75.03, + "ARC": 78.24, + "HellaSwag": 89.68, + "MMLU": 68.08, + "TruthfulQA": 80.88, + "Winogrande": 86.5, + "GSM8K": 46.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e29bc3a6d611c728fd1952cd73d1b8da50375c19", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v1.1", + "Average \u2b06\ufe0f": 75.03, + "ARC": 78.24, + "HellaSwag": 89.68, + "MMLU": 68.08, + "TruthfulQA": 80.88, + "Winogrande": 86.5, + "GSM8K": 46.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d1dda8b111024dc06eb3a7072100e74d5039a782", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "sumo43\/Yi-34b-x2", @@ -5605,7 +9377,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -5636,6 +9408,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/WONMSeverusDevil-TIES-7B", + "Average \u2b06\ufe0f": 74.97, + "ARC": 72.95, + "HellaSwag": 88.45, + "MMLU": 64.77, + "TruthfulQA": 72.0, + "Winogrande": 83.43, + "GSM8K": 68.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bbe4f09eb68a0f6f628b2cc54ba55d8ac5d34e5f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "andrijdavid\/Macaroni-7b-Tied", @@ -5653,7 +9448,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "6323cf53ed75eab25ca37b3636a0f38ee8d1ac30", "Flagged": false, @@ -5676,12 +9471,58 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "dd841bf2fc42cb4f872fab04a638465cb06a4b7a", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LewisDeBenoisIV\/BillyTheKid1803", + "Average \u2b06\ufe0f": 74.96, + "ARC": 71.84, + "HellaSwag": 88.09, + "MMLU": 65.07, + "TruthfulQA": 72.16, + "Winogrande": 82.32, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "23dab1dc473bc9a2d345f5a19e5a564528665d48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "saltlux\/luxia-21.4b-alignment-v1.1", + "Average \u2b06\ufe0f": 74.96, + "ARC": 78.24, + "HellaSwag": 89.69, + "MMLU": 68.22, + "TruthfulQA": 80.91, + "Winogrande": 86.66, + "GSM8K": 46.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 21.42, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d1dda8b111024dc06eb3a7072100e74d5039a782", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "ycros\/BagelMIsteryTour-v2-8x7B", @@ -5699,7 +9540,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "98a8b319707be3dab1659594da69a37ed8f8c148", "Flagged": false, @@ -5707,7 +9548,7 @@ }, { "T": "\ud83e\udd1d", - "Model": "Eric111\/CatunaMayo", + "Model": "eric111\/CatunaMayo", "Average \u2b06\ufe0f": 74.95, "ARC": 71.76, "HellaSwag": 87.9, @@ -5719,18 +9560,18 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9dc038fac8b37aac504e851c311bede4092afafd", "Flagged": false, "MoE": false }, { "T": "\ud83e\udd1d", - "Model": "eric111\/CatunaMayo", + "Model": "Eric111\/CatunaMayo", "Average \u2b06\ufe0f": 74.95, "ARC": 71.76, "HellaSwag": 87.9, @@ -5746,7 +9587,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "9dc038fac8b37aac504e851c311bede4092afafd", "Flagged": false, "MoE": false @@ -5769,7 +9610,7 @@ "Hub License": "?", "#Params (B)": 24.15, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b53163f2a7b562ce0191bdadd9d1f2e77a2b5a5e", "Flagged": false, "MoE": false @@ -5820,6 +9661,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "core-3\/kuno-dogwalker-7b", + "Average \u2b06\ufe0f": 74.94, + "ARC": 72.01, + "HellaSwag": 88.17, + "MMLU": 64.96, + "TruthfulQA": 71.39, + "Winogrande": 82.0, + "GSM8K": 71.11, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "65d8179cba89a9d4b28d943daea33a6ae2c2841f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "ConvexAI\/BurningBruce-004", @@ -5913,8 +9777,8 @@ "MoE": false }, { - "T": "\ud83e\udd1d", - "Model": "NLPinas\/yi-bagel-2x34b", + "T": "\ud83d\udcac", + "Model": "NLPinas\/yi-bagel-2x34b-moe", "Average \u2b06\ufe0f": 74.93, "ARC": 72.7, "HellaSwag": 85.44, @@ -5922,22 +9786,22 @@ "TruthfulQA": 71.42, "Winogrande": 82.72, "GSM8K": 60.73, - "Type": "base merges and moerges", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "other", + "Merged": false, + "Hub License": "?", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "ce6765e4a2a1f5914969c9fe48e2d1e8f3e3a247", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a6de6f3ccb21eeef12a354c720a9a85e5e53433d", "Flagged": false, - "MoE": false + "MoE": true }, { - "T": "\ud83d\udcac", - "Model": "NLPinas\/yi-bagel-2x34b-moe", + "T": "\ud83e\udd1d", + "Model": "NLPinas\/yi-bagel-2x34b", "Average \u2b06\ufe0f": 74.93, "ARC": 72.7, "HellaSwag": 85.44, @@ -5945,18 +9809,18 @@ "TruthfulQA": 71.42, "Winogrande": 82.72, "GSM8K": 60.73, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "base merges and moerges", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": true, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "a6de6f3ccb21eeef12a354c720a9a85e5e53433d", + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ce6765e4a2a1f5914969c9fe48e2d1e8f3e3a247", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -5981,6 +9845,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/complect-7B-slerp", + "Average \u2b06\ufe0f": 74.91, + "ARC": 72.27, + "HellaSwag": 88.19, + "MMLU": 64.89, + "TruthfulQA": 71.14, + "Winogrande": 84.53, + "GSM8K": 68.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8ade5b4a439b511ccb00d89d51b5c273f90b3449", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "nfaheem\/Marcoroni-7b-DPO-Merge", @@ -6004,6 +9891,98 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/Eris-Floramix-7b", + "Average \u2b06\ufe0f": 74.9, + "ARC": 73.12, + "HellaSwag": 88.28, + "MMLU": 64.63, + "TruthfulQA": 70.96, + "Winogrande": 84.69, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a20c4fa9027d5a622e2e6b6ea9a255d84f3a8228", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/Starling_Monarch_Westlake_Garten-7B-v0.1", + "Average \u2b06\ufe0f": 74.9, + "ARC": 71.76, + "HellaSwag": 88.15, + "MMLU": 65.07, + "TruthfulQA": 67.92, + "Winogrande": 84.53, + "GSM8K": 71.95, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ed346db1daac7abf9149020fd4c967c59783bdae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/Beagle_Turdus", + "Average \u2b06\ufe0f": 74.9, + "ARC": 73.63, + "HellaSwag": 88.82, + "MMLU": 64.62, + "TruthfulQA": 68.27, + "Winogrande": 86.03, + "GSM8K": 68.01, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "05216cc9edb1c697ee82d1343300874392f7ed69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tushar310\/Hippy-AAI-7B", + "Average \u2b06\ufe0f": 74.9, + "ARC": 71.84, + "HellaSwag": 88.04, + "MMLU": 65.17, + "TruthfulQA": 72.02, + "Winogrande": 82.32, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "798c990e93e7ec827037b806c52fbc30a7009894", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "SC44\/Mistral-7B-private-sia", @@ -6027,6 +10006,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "eldogbbhed\/NeuralMonarchCoderPearlBeagle-T3Q-Mistral-Orca-Math-DPO-7b", + "Average \u2b06\ufe0f": 74.89, + "ARC": 71.16, + "HellaSwag": 88.22, + "MMLU": 64.97, + "TruthfulQA": 71.45, + "Winogrande": 82.48, + "GSM8K": 71.04, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2c6ff7a8e0b026aa8c232a42bd77fea13bbeac73", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "core-3\/kuno-royale-v3-7b", + "Average \u2b06\ufe0f": 74.88, + "ARC": 71.76, + "HellaSwag": 88.23, + "MMLU": 65.06, + "TruthfulQA": 71.13, + "Winogrande": 82.32, + "GSM8K": 70.81, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5e5425d13bef73009854548e9b59db1c2a9cba83", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Pigris-7b-v0.3", + "Average \u2b06\ufe0f": 74.88, + "ARC": 71.5, + "HellaSwag": 88.15, + "MMLU": 64.53, + "TruthfulQA": 71.21, + "Winogrande": 84.14, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0553c5ef30d6f85ef021ebb013f108fc87230f64", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AA051612\/A0126", @@ -6073,6 +10121,75 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "ChaoticNeutrals\/Eris_Floramix_DPO_7B", + "Average \u2b06\ufe0f": 74.87, + "ARC": 73.04, + "HellaSwag": 88.28, + "MMLU": 64.71, + "TruthfulQA": 70.94, + "Winogrande": 84.69, + "GSM8K": 67.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "16e9d47cb25c33d57328638e5c56e257c6021ce1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tushar310\/Hippy-AAI-7B", + "Average \u2b06\ufe0f": 74.87, + "ARC": 71.59, + "HellaSwag": 88.07, + "MMLU": 65.15, + "TruthfulQA": 71.95, + "Winogrande": 82.32, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "798c990e93e7ec827037b806c52fbc30a7009894", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen13-mistral-7B", + "Average \u2b06\ufe0f": 74.86, + "ARC": 71.5, + "HellaSwag": 88.33, + "MMLU": 64.79, + "TruthfulQA": 72.34, + "Winogrande": 82.24, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "876d2ad8c5d29ccd9590b9c5df191b6e206a4b54", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "flemmingmiguel\/MDBX-7B", @@ -6110,7 +10227,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -6142,6 +10259,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Eris-Daturamix-7b", + "Average \u2b06\ufe0f": 74.83, + "ARC": 72.78, + "HellaSwag": 88.23, + "MMLU": 64.52, + "TruthfulQA": 71.05, + "Winogrande": 84.69, + "GSM8K": 67.7, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b41ce0efb1d6048fcaa257f00791c142f5d76093", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "BarryFutureman\/NeuralTurdusVariant1-7B", @@ -6165,6 +10305,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "core-3\/kuno-dogpark-7b", + "Average \u2b06\ufe0f": 74.82, + "ARC": 71.84, + "HellaSwag": 88.15, + "MMLU": 65.07, + "TruthfulQA": 71.14, + "Winogrande": 82.24, + "GSM8K": 70.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "962eef5f0f7116b41ed6542d8ffa15f4fb9c5147", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jsfs11\/MixtureofMerges-MoE-v2", @@ -6234,6 +10397,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/connate-7B-slerp", + "Average \u2b06\ufe0f": 74.8, + "ARC": 72.1, + "HellaSwag": 88.37, + "MMLU": 64.96, + "TruthfulQA": 71.16, + "Winogrande": 84.61, + "GSM8K": 67.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3c9699e0096679a7a23749d59a561c9bdc4a8ff1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "abhishekchohan\/SOLAR-10.7B-Instruct-Forest-DPO-v1", @@ -6274,7 +10460,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "0c670c988b61240e5f89ae9df0820db7dc572576", "Flagged": false, @@ -6320,7 +10506,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "09da1a24f84c96b8c09f2c07038986e28cc24ad5", "Flagged": true, @@ -6340,7 +10526,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -6372,6 +10558,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "core-3\/kuno-royale-v2-7b", + "Average \u2b06\ufe0f": 74.8, + "ARC": 72.01, + "HellaSwag": 88.15, + "MMLU": 65.07, + "TruthfulQA": 71.1, + "Winogrande": 82.24, + "GSM8K": 70.2, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ff99dd167bfbb5dd3e5d74bb72e09a007f365541", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Eris_PrimeV4-Vision-7B", + "Average \u2b06\ufe0f": 74.79, + "ARC": 72.78, + "HellaSwag": 88.47, + "MMLU": 65.13, + "TruthfulQA": 71.43, + "Winogrande": 83.82, + "GSM8K": 67.1, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fec915be390bd7304e0cddcf0aff216edd4ac87e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cognitivecomputations\/WestLake-7B-v2-laser", @@ -6389,12 +10621,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 30.0, + "Hub \u2764\ufe0f": 33.0, "Available on the hub": true, "Model sha": "c3227c2b48ac6b136c074871b72088677f2adca9", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen8-mistral-7B", + "Average \u2b06\ufe0f": 74.78, + "ARC": 71.93, + "HellaSwag": 88.06, + "MMLU": 64.92, + "TruthfulQA": 72.02, + "Winogrande": 82.24, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9655aca675b8dcf0062257cf818c71592aad65d0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "rizla\/raccoon-small", @@ -6409,14 +10664,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.19, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "79d748d0646f11bd18a8d785000c63279a9a5cde", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83e\udd1d", @@ -6481,7 +10736,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "a5d1b1f831efe38df3b6ac125764a87ed094e282", "Flagged": false, @@ -6551,7 +10806,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "94b36a4573657d7815f55b917b204e6b73f7a634", "Flagged": true, "MoE": false @@ -6573,7 +10828,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 60.81, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "ccd128942c5a6bb1672ceed21730d0e172655d77", "Flagged": false, @@ -6619,12 +10874,81 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 141.0, + "Hub \u2764\ufe0f": 146.0, "Available on the hub": true, "Model sha": "33f76dd61715c8fd89f138092a8e8c7f3b3dd905", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "core-3\/kuno-royale-7b", + "Average \u2b06\ufe0f": 74.74, + "ARC": 71.76, + "HellaSwag": 88.2, + "MMLU": 65.13, + "TruthfulQA": 71.12, + "Winogrande": 82.32, + "GSM8K": 69.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "450b2a9f247b2d8486c99b9c1f8777966ae2454c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "core-3\/kuno-royale-7B", + "Average \u2b06\ufe0f": 74.74, + "ARC": 71.76, + "HellaSwag": 88.2, + "MMLU": 65.13, + "TruthfulQA": 71.12, + "Winogrande": 82.32, + "GSM8K": 69.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "450b2a9f247b2d8486c99b9c1f8777966ae2454c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "saishf\/Multi-Verse-RP-7B", + "Average \u2b06\ufe0f": 74.73, + "ARC": 72.35, + "HellaSwag": 88.37, + "MMLU": 63.94, + "TruthfulQA": 73.19, + "Winogrande": 84.14, + "GSM8K": 66.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "ca05b22adfc6ef9a9af7d2a07d617ac8684b1b9a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "BarryFutureman\/NeuralLake-Variant1-7B", @@ -6671,6 +10995,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "ChaoticNeutrals\/Eris_Remix_DPO_7B", + "Average \u2b06\ufe0f": 74.71, + "ARC": 72.44, + "HellaSwag": 88.03, + "MMLU": 65.29, + "TruthfulQA": 68.92, + "Winogrande": 84.77, + "GSM8K": 68.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4c09542d0154eb09bf7be874e2c68189407114ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Eris_Remix_7B", + "Average \u2b06\ufe0f": 74.7, + "ARC": 72.35, + "HellaSwag": 88.04, + "MMLU": 65.26, + "TruthfulQA": 69.12, + "Winogrande": 84.77, + "GSM8K": 68.69, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "db7c693c872acfbf2244373d671745cc0d19e6e5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ibivibiv\/aegolius-acadicus-v1-30b", @@ -6691,7 +11061,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "fecd580eb4294525160e86b79d0f205a3a44e172", - "Flagged": true, + "Flagged": false, "MoE": true }, { @@ -6708,14 +11078,37 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "llama2", "#Params (B)": 29.79, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "1260e0b4085ce8f6fbbe41192c5932d084706be4", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Eric111\/CatunaLaserPi-DPO", + "Average \u2b06\ufe0f": 74.7, + "ARC": 72.95, + "HellaSwag": 88.33, + "MMLU": 64.95, + "TruthfulQA": 70.01, + "Winogrande": 82.64, + "GSM8K": 69.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "207cddf327154c23b484f1cbd972b3c7989b7554", + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -6734,7 +11127,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 34.0, + "Hub \u2764\ufe0f": 35.0, "Available on the hub": true, "Model sha": "08903c93d929829aabbde2681c7ad2465d7d4189", "Flagged": false, @@ -6757,7 +11150,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 81.0, + "Hub \u2764\ufe0f": 87.0, "Available on the hub": true, "Model sha": "fcc6ada5ea6dbf2f644d26b545ac402d2202cc74", "Flagged": false, @@ -6803,7 +11196,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 63.0, + "Hub \u2764\ufe0f": 85.0, "Available on the hub": true, "Model sha": "6df7bb2069432bcab0971ab105284a66b3ec1ce0", "Flagged": false, @@ -6827,34 +11220,11 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4e3eb8c21ff1689a348cc9ffdacd675aff3dde2b", "Flagged": true, "MoE": false }, - { - "T": "\ud83d\udd36", - "Model": "moreh\/MoMo-70B-LoRA-V1.4", - "Average \u2b06\ufe0f": 74.67, - "ARC": 69.2, - "HellaSwag": 85.07, - "MMLU": 77.12, - "TruthfulQA": 62.66, - "Winogrande": 83.74, - "GSM8K": 70.2, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "mit", - "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "66bf25995056155b5d0796f7c0981e243bdd48f3", - "Flagged": false, - "MoE": false - }, { "T": "\ud83d\udd36", "Model": "moreh\/MoMo-72B-LoRA-V1.4", @@ -6872,7 +11242,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 84.0, + "Hub \u2764\ufe0f": 86.0, "Available on the hub": true, "Model sha": "66bf25995056155b5d0796f7c0981e243bdd48f3", "Flagged": false, @@ -6993,6 +11363,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Calme-7B-Instruct-v0.4", + "Average \u2b06\ufe0f": 74.65, + "ARC": 70.73, + "HellaSwag": 87.75, + "MMLU": 64.4, + "TruthfulQA": 70.25, + "Winogrande": 82.08, + "GSM8K": 72.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "448255ff2397e04c62ecba4c4d982531eb42d241", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "kevin009\/llamaRAGdrama", @@ -7010,12 +11403,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "f1d27aab09086a6e691db6892d50ba809cbe0607", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Cedaros\/Test-7B", + "Average \u2b06\ufe0f": 74.65, + "ARC": 73.21, + "HellaSwag": 88.17, + "MMLU": 64.37, + "TruthfulQA": 69.91, + "Winogrande": 82.48, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b185bc8f6e30f2dc14e3e8c7f582cd19b4806f84", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Eris-Lelanacles-7b", + "Average \u2b06\ufe0f": 74.64, + "ARC": 71.67, + "HellaSwag": 87.91, + "MMLU": 64.9, + "TruthfulQA": 68.97, + "Winogrande": 83.9, + "GSM8K": 70.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c6a5ffb5b3ad65895301c3aec4f34f71cd6d0a90", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "vicgalle\/Mixtral-7Bx2-truthy", @@ -7037,7 +11476,7 @@ "Available on the hub": true, "Model sha": "4bfad083e96a4ab129cc202fc941994be2e3adc4", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", @@ -7056,7 +11495,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "d774c746ac8f9df026d106f2466dbeeae3a49337", "Flagged": false, @@ -7079,7 +11518,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 84.0, + "Hub \u2764\ufe0f": 86.0, "Available on the hub": true, "Model sha": "e5dd511955f4ac65bb1884f07426157740ad8574", "Flagged": false, @@ -7177,6 +11616,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/CatunaLaserPi", + "Average \u2b06\ufe0f": 74.59, + "ARC": 71.5, + "HellaSwag": 88.06, + "MMLU": 64.95, + "TruthfulQA": 67.83, + "Winogrande": 83.03, + "GSM8K": 72.18, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1285f3879ed0ccae4ac32a1ab3e54894de8f4c3a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen11-mistral-7B", + "Average \u2b06\ufe0f": 74.59, + "ARC": 70.99, + "HellaSwag": 88.06, + "MMLU": 65.06, + "TruthfulQA": 71.73, + "Winogrande": 82.16, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c32c932c9f61cef4452921c595ea20f067bbbdec", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "shadowml\/DareBeagle-7B", @@ -7200,6 +11685,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "mayacinka\/yam-sam-7B", + "Average \u2b06\ufe0f": 74.58, + "ARC": 70.9, + "HellaSwag": 87.92, + "MMLU": 65.39, + "TruthfulQA": 71.3, + "Winogrande": 83.03, + "GSM8K": 68.92, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c031f5e40b3e220c719e0430f63b6b11794084ae", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Gille\/StrangeMerges_3-7B-slerp", @@ -7237,7 +11745,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -7260,7 +11768,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -7286,7 +11794,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "d7a439cbd47cb966778bf35e3e8efde20d5cfe7f", "Flagged": false, @@ -7332,7 +11840,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "e61d2cc6475548244b9ab180e508246e3e577b66", "Flagged": false, @@ -7401,7 +11909,7 @@ "Merged": true, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "904ffe8106a3facbea0d0e61d9a53a525675871e", "Flagged": false, @@ -7447,7 +11955,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 81.0, + "Hub \u2764\ufe0f": 87.0, "Available on the hub": true, "Model sha": "fcc6ada5ea6dbf2f644d26b545ac402d2202cc74", "Flagged": false, @@ -7514,7 +12022,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -7562,7 +12070,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "645fa936256811f53f0c33f1e5298f6ad1095dce", "Flagged": false, @@ -7585,8 +12093,8 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 18.79, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, "Model sha": "96b27c4205881920289b29ac3d83ba5edf5cf672", "Flagged": false, "MoE": false @@ -7608,12 +12116,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "1d697d32ba4f6ed471cd2857669029f425b827bb", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "invalid-coder\/Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp", + "Average \u2b06\ufe0f": 74.45, + "ARC": 71.25, + "HellaSwag": 88.42, + "MMLU": 66.31, + "TruthfulQA": 71.94, + "Winogrande": 83.43, + "GSM8K": 65.35, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "39a1c76ddb5fa3a82c5b4071121d2e4866a25300", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "paulml\/NeuralOmniWestBeaglake-7B", @@ -7683,6 +12214,29 @@ "Flagged": true, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "seyf1elislam\/KuTrix-7b", + "Average \u2b06\ufe0f": 74.42, + "ARC": 70.48, + "HellaSwag": 87.94, + "MMLU": 65.28, + "TruthfulQA": 70.85, + "Winogrande": 81.93, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "37995fab81810aacdf8fa7db73c41c4673dd4794", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "jeonsworld\/CarbonVillain-en-10.7B-v2", @@ -7769,7 +12323,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.19, - "Hub \u2764\ufe0f": 31.0, + "Hub \u2764\ufe0f": 36.0, "Available on the hub": true, "Model sha": "092208b5bfab866b301545149a6b14fde48a0dd6", "Flagged": true, @@ -7861,7 +12415,7 @@ "Merged": true, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 26.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "cc4531a25fff7cbb146c0e12f2cf4e19189c37a2", "Flagged": false, @@ -7884,7 +12438,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 69.92, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "333524a8c6ed8415fd48f852e53c405cac82733d", "Flagged": false, @@ -7982,6 +12536,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen3", + "Average \u2b06\ufe0f": 74.36, + "ARC": 70.82, + "HellaSwag": 87.98, + "MMLU": 64.81, + "TruthfulQA": 70.69, + "Winogrande": 82.16, + "GSM8K": 69.67, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "37a181a04dcedf8402a5246b4189c88b2096323d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "flemmingmiguel\/DareBeagle-7B", @@ -8019,7 +12596,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -8028,6 +12605,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Franken-MoE-18B-v0.1", + "Average \u2b06\ufe0f": 74.35, + "ARC": 72.1, + "HellaSwag": 88.3, + "MMLU": 65.01, + "TruthfulQA": 67.51, + "Winogrande": 83.74, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a64d069a467516037179b16a010ff118ed66d370", + "Flagged": false, + "MoE": true + }, { "T": "\ud83e\udd1d", "Model": "ConvexAI\/Solutus-3x7B", @@ -8186,7 +12786,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "941b5a690781dd412eb435446b65e92048992abe", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -8281,6 +12881,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/Kindred-7B-slerp", + "Average \u2b06\ufe0f": 74.29, + "ARC": 71.76, + "HellaSwag": 87.78, + "MMLU": 64.76, + "TruthfulQA": 68.12, + "Winogrande": 83.11, + "GSM8K": 70.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "64da0f7bb5f6d772b7d682c99b5c510cb8681ff0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "kekmodel\/StopCarbon-10.7B-v4", @@ -8327,9 +12950,32 @@ "Flagged": true, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralExperiment-7b-MagicCoder-v7.5", + "Average \u2b06\ufe0f": 74.28, + "ARC": 71.33, + "HellaSwag": 87.94, + "MMLU": 64.62, + "TruthfulQA": 72.11, + "Winogrande": 83.5, + "GSM8K": 66.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43ea8d27d652dc15e4d27f665c5d636a5937780b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", - "Model": "jeonsworld\/CarbonVillain-en-13B-v1", + "Model": "jeonsworld\/CarbonVillain-en-10.7B-v1", "Average \u2b06\ufe0f": 74.28, "ARC": 71.25, "HellaSwag": 88.46, @@ -8338,13 +12984,13 @@ "Winogrande": 83.27, "GSM8K": 64.29, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "Unknown", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "a797e7e81f7929a31ca232858318d72b93b6abe0", "Flagged": false, @@ -8352,7 +12998,7 @@ }, { "T": "\ud83d\udcac", - "Model": "jeonsworld\/CarbonVillain-en-10.7B-v1", + "Model": "jeonsworld\/CarbonVillain-en-13B-v1", "Average \u2b06\ufe0f": 74.28, "ARC": 71.25, "HellaSwag": 88.46, @@ -8361,18 +13007,41 @@ "Winogrande": 83.27, "GSM8K": 64.29, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "cc-by-nc-4.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 5.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "a797e7e81f7929a31ca232858318d72b93b6abe0", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "ResplendentAI\/Datura_7B", + "Average \u2b06\ufe0f": 74.28, + "ARC": 72.1, + "HellaSwag": 88.27, + "MMLU": 64.15, + "TruthfulQA": 71.03, + "Winogrande": 84.53, + "GSM8K": 65.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "750463cf0946dd46c4504b302757f2bb6e2b4521", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/Patronum-7B", @@ -8436,12 +13105,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "02a497125bbf85fe0355eb22424315c920d1aec4", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "ResplendentAI\/Flora_DPO_7B", + "Average \u2b06\ufe0f": 74.26, + "ARC": 71.76, + "HellaSwag": 88.28, + "MMLU": 64.13, + "TruthfulQA": 71.08, + "Winogrande": 84.53, + "GSM8K": 65.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0d04b46ec6ce4c707bcdebb94b98e30fe8f4ae1d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Weyaxi\/SauerkrautLM-UNA-SOLAR-Instruct", @@ -8459,7 +13151,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 23.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "564c02554a8b1f91c0860096bdb830dc15ac7805", "Flagged": false, @@ -8480,7 +13172,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "", + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -8488,6 +13180,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Flora_7B", + "Average \u2b06\ufe0f": 74.26, + "ARC": 72.1, + "HellaSwag": 88.31, + "MMLU": 64.16, + "TruthfulQA": 71.19, + "Winogrande": 84.45, + "GSM8K": 65.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9c95dafc63de0e98627458369e87347df87fa17d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "macadeliccc\/SOLAR-math-2x10.7b-v0.2", @@ -8526,7 +13241,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "gpl", + "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -8548,7 +13263,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -8597,12 +13312,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "1d71eacdbfa5d4fe546bcc57d40e642dbac57cb7", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_45-7B-dare_ties", + "Average \u2b06\ufe0f": 74.23, + "ARC": 69.8, + "HellaSwag": 87.6, + "MMLU": 65.06, + "TruthfulQA": 67.79, + "Winogrande": 82.32, + "GSM8K": 72.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7d0905d7112b0e7c1cffd2bd41ea3152d5cc2bc8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "BryanSwk\/LaserPipe-7B-SLERP", @@ -8617,10 +13355,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "0c27fcb6770f2225e4dcc2277b8618e03810427e", "Flagged": false, @@ -8643,8 +13381,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, "Model sha": "875319a815400bdb73c309601c175d72997a4fa0", "Flagged": false, "MoE": false @@ -8663,8 +13401,8 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -8712,7 +13450,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 42.0, + "Hub \u2764\ufe0f": 44.0, "Available on the hub": true, "Model sha": "8b9615124a0bcadd7fa984eaadd066da0fb4fbae", "Flagged": false, @@ -8764,6 +13502,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Eris_PrimeV3-Vision-7B", + "Average \u2b06\ufe0f": 74.2, + "ARC": 70.65, + "HellaSwag": 87.87, + "MMLU": 65.32, + "TruthfulQA": 70.32, + "Winogrande": 83.35, + "GSM8K": 67.7, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "2a48395bb8bdeac6cf812fe51746c436c558039b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "upstage\/SOLAR-10.7B-Instruct-v1.0", @@ -8781,7 +13542,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 519.0, + "Hub \u2764\ufe0f": 554.0, "Available on the hub": true, "Model sha": "d3167df97a44b8632538b32ee8cd887893ea1435", "Flagged": false, @@ -8804,7 +13565,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "08d3f07da7160e9657630ba98531850905619def", "Flagged": false, @@ -8897,7 +13658,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9286f6fac1df497203e110070322c93dab33fdd2", "Flagged": true, "MoE": false @@ -8942,12 +13703,35 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 82.0, + "Hub \u2764\ufe0f": 84.0, "Available on the hub": true, "Model sha": "233b63015f389d0023cfa21727632b340cadbdb5", "Flagged": true, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "seyf1elislam\/WestKunai-X-7b", + "Average \u2b06\ufe0f": 74.18, + "ARC": 71.08, + "HellaSwag": 87.86, + "MMLU": 65.42, + "TruthfulQA": 68.01, + "Winogrande": 82.87, + "GSM8K": 69.83, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ca07b7bea2f28538d4112c989b1e4402c96c17ef", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "kyujinpy\/Sakura-SOLRCA-Math-Instruct-DPO-v2", @@ -8994,6 +13778,52 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ozayezerceli\/Lowke-2x7B-v1", + "Average \u2b06\ufe0f": 74.14, + "ARC": 71.5, + "HellaSwag": 87.3, + "MMLU": 64.4, + "TruthfulQA": 72.67, + "Winogrande": 82.08, + "GSM8K": 66.87, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "384d5117486aa7956943024cb2d821e1b9643cc2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Liberated-Qwen1.5-72B", + "Average \u2b06\ufe0f": 74.13, + "ARC": 65.7, + "HellaSwag": 84.62, + "MMLU": 77.13, + "TruthfulQA": 60.64, + "Winogrande": 83.03, + "GSM8K": 73.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 69.0, + "Available on the hub": true, + "Model sha": "8761e9acb20bc475c095455fd754bf632e0f88f0", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "ConvexAI\/Seraphim-8x10.7B-bf16", @@ -9080,7 +13910,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "f03ff71ca0b07edccda0d2f407049dcf18edfb4d", "Flagged": false, @@ -9132,6 +13962,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Liberated-Qwen1.5-72B", + "Average \u2b06\ufe0f": 74.11, + "ARC": 65.7, + "HellaSwag": 84.58, + "MMLU": 77.08, + "TruthfulQA": 60.56, + "Winogrande": 83.11, + "GSM8K": 73.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 69.0, + "Available on the hub": true, + "Model sha": "8761e9acb20bc475c095455fd754bf632e0f88f0", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "cloudyu\/19B_MATH_DPO", @@ -9147,12 +14000,35 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "other", "#Params (B)": 19.19, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "0a25a243957b41c7ac8d59af50294547151ae621", "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Eric111\/openchat-3.5-0106-128k-DPO_dpo-binarized-NeuralTrix-7B", + "Average \u2b06\ufe0f": 74.09, + "ARC": 70.99, + "HellaSwag": 87.06, + "MMLU": 65.57, + "TruthfulQA": 68.0, + "Winogrande": 82.87, + "GSM8K": 70.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e511b6a307d23c2a24bc7460231714ea7d0bee02", + "Flagged": false, "MoE": false }, { @@ -9192,10 +14068,10 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "0c27fcb6770f2225e4dcc2277b8618e03810427e", "Flagged": false, @@ -9264,7 +14140,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "c63d06344214886094d7ab6c7fd5692cc59fdf0d", "Flagged": false, @@ -9310,7 +14186,7 @@ "Merged": true, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "511cc63b3efca6f036fdbbe15f312d0e2b7e5cf5", "Flagged": false, @@ -9318,7 +14194,7 @@ }, { "T": "\ud83d\udd36", - "Model": "Yhyu13\/LMCocktail-10.7B-v1", + "Model": "yhyu13\/LMCocktail-10.7B-v1", "Average \u2b06\ufe0f": 74.06, "ARC": 70.65, "HellaSwag": 88.13, @@ -9327,21 +14203,21 @@ "Winogrande": 83.35, "GSM8K": 64.97, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "llama2", + "Hub License": "?", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 15.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "79ec3a42118f0715666b86bacab2688b62e1433b", - "Flagged": true, + "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "yhyu13\/LMCocktail-10.7B-v1", + "Model": "Yhyu13\/LMCocktail-10.7B-v1", "Average \u2b06\ufe0f": 74.06, "ARC": 70.65, "HellaSwag": 88.13, @@ -9350,16 +14226,16 @@ "Winogrande": 83.35, "GSM8K": 64.97, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "79ec3a42118f0715666b86bacab2688b62e1433b", - "Flagged": false, + "Flagged": true, "MoE": false }, { @@ -9408,6 +14284,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/SuperMente-7B-v4", + "Average \u2b06\ufe0f": 74.04, + "ARC": 70.48, + "HellaSwag": 87.63, + "MMLU": 63.35, + "TruthfulQA": 71.46, + "Winogrande": 82.08, + "GSM8K": 69.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "40740a963ca357bf8c37af460ce443b8564455ca", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-S3-v0.1", @@ -9425,7 +14324,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "cce7c94dc1d178234c3616730b203c2e52f80ed2", "Flagged": false, @@ -9494,7 +14393,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "29c9ff0a9f5daa5adc797a34508bcca50205f34f", "Flagged": true, @@ -9560,7 +14459,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, + "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 4.0, @@ -9606,7 +14505,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -9638,6 +14537,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/C0325-L", + "Average \u2b06\ufe0f": 73.96, + "ARC": 67.58, + "HellaSwag": 87.43, + "MMLU": 74.72, + "TruthfulQA": 58.66, + "Winogrande": 80.82, + "GSM8K": 74.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "CohereForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "130e9c0ef3ca571a17a07d18ac00d655f7880245", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuralMaths-Experiment-7b", + "Average \u2b06\ufe0f": 73.95, + "ARC": 69.71, + "HellaSwag": 87.48, + "MMLU": 65.01, + "TruthfulQA": 63.83, + "Winogrande": 82.48, + "GSM8K": 75.21, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f8a6b011d046f04f0ec6c5af909590553cc36170", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "zhengr\/MixTAO-7Bx2-MoE-DPO", @@ -9656,7 +14601,7 @@ "Hub License": "?", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "911149cad645ccb189cb403c16bbed98df18dfd6", "Flagged": false, "MoE": true @@ -9676,14 +14621,37 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "d933dcd7cbb19916f4732ae7e3892a656a8c3d27", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/ConfigurableSOLAR-10.7B", + "Average \u2b06\ufe0f": 73.94, + "ARC": 70.39, + "HellaSwag": 88.03, + "MMLU": 66.44, + "TruthfulQA": 72.34, + "Winogrande": 83.03, + "GSM8K": 63.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "df83494a4366e081563659e1142464029a0dec82", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "viethq188\/LeoScorpius-7B-Chat-DPO", @@ -9724,7 +14692,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "2513232abc84b071b83d0241e8decc69d18d721d", "Flagged": false, @@ -9767,7 +14735,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -9793,7 +14761,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 31.0, "Available on the hub": true, "Model sha": "72084679bda2e7679259e9c0fa2fdcd48ecb158c", "Flagged": false, @@ -9822,6 +14790,52 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/OpenBeagle-11B", + "Average \u2b06\ufe0f": 73.85, + "ARC": 70.48, + "HellaSwag": 88.76, + "MMLU": 66.94, + "TruthfulQA": 67.01, + "Winogrande": 83.5, + "GSM8K": 66.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b59ed47a8f30e7488f1faef65ff0a75597af0a44", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "InferenceIllusionist\/Excalibur-7b-DPO", + "Average \u2b06\ufe0f": 73.84, + "ARC": 70.9, + "HellaSwag": 87.93, + "MMLU": 65.46, + "TruthfulQA": 70.82, + "Winogrande": 82.48, + "GSM8K": 65.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f2a7ecb1f539bb41a61c254150e404820851005f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "nlpguy\/Westgate", @@ -9862,7 +14876,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "73b5302f1efc7ba87e123cfed0c9c998e098c16a", "Flagged": false, @@ -9911,7 +14925,7 @@ "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "fd230896bc3a1cfabdf37f8d8389cd670ea72faa", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -9937,6 +14951,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Sao10K\/Typhon-Mixtral-v1", + "Average \u2b06\ufe0f": 73.81, + "ARC": 71.84, + "HellaSwag": 87.47, + "MMLU": 71.11, + "TruthfulQA": 68.81, + "Winogrande": 81.77, + "GSM8K": 61.87, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "8483318133a7763eb2dedc59294559febbf657c9", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "fblgit\/LUNA-SOLARkrautLM-Instruct", @@ -9977,7 +15014,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "8dbf40c7be17ddb1b2a07e49c60c180fed741172", "Flagged": false, @@ -10046,7 +15083,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "e4b4ee3d952b1e8360a82d2b3506fd5b4ab68df9", "Flagged": false, @@ -10069,7 +15106,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 137.0, + "Hub \u2764\ufe0f": 142.0, "Available on the hub": true, "Model sha": "0ab5c875f0070d5aee8d36bc55f41de440a13f02", "Flagged": false, @@ -10092,7 +15129,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 36.1, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "479d3907a5bce4f3edb476d3ae05fe4b38a0a6e4", "Flagged": false, @@ -10112,7 +15149,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, + "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 18.52, "Hub \u2764\ufe0f": 0.0, @@ -10161,7 +15198,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 183.0, + "Hub \u2764\ufe0f": 215.0, "Available on the hub": true, "Model sha": "deb99d98742ec9691ef593418bea71a4437745a1", "Flagged": false, @@ -10190,6 +15227,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen11X-mistral-7B", + "Average \u2b06\ufe0f": 73.73, + "ARC": 71.16, + "HellaSwag": 88.23, + "MMLU": 64.81, + "TruthfulQA": 70.18, + "Winogrande": 82.16, + "GSM8K": 65.81, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ca3e210eea6e810365b9fafe4477c065a363dd40", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "decruz07\/kellemar-DPO-Orca-Distilled-7B-SLERP", @@ -10207,7 +15267,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "efb6caff9804383600563a658ba18720ec3b2d11", "Flagged": false, @@ -10227,7 +15287,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, @@ -10277,7 +15337,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "63b69bf2588f3b108d3427389d3c707f6b50d2ba", "Flagged": true, "MoE": false @@ -10322,12 +15382,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "dc7dfbece1b31665b0456476f67ef97a17bd2323", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Eris_7B", + "Average \u2b06\ufe0f": 73.68, + "ARC": 71.42, + "HellaSwag": 87.99, + "MMLU": 65.24, + "TruthfulQA": 66.95, + "Winogrande": 84.21, + "GSM8K": 66.26, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "30ffcfbdcab92da78fe1abf4ccf69b1a1a71c11a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ChaoticNeutrals\/Prodigy_7B", + "Average \u2b06\ufe0f": 73.68, + "ARC": 71.59, + "HellaSwag": 88.09, + "MMLU": 64.92, + "TruthfulQA": 68.57, + "Winogrande": 84.53, + "GSM8K": 64.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "11b85a26a0d04abd1282cf10fdadf2faefa93ee4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AiMavenAi\/MavenWest", @@ -10342,7 +15448,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -10437,7 +15543,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "baa14c82695e595b5d39f35068898feb6fdceb34", "Flagged": false, @@ -10529,7 +15635,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 308.0, + "Hub \u2764\ufe0f": 314.0, "Available on the hub": true, "Model sha": "f62c59844a8de3c27cf22735218d77e9fa9f6b17", "Flagged": false, @@ -10552,12 +15658,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "9cd172b853949228761dfa65dfec57746475d703", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "InferenceIllusionist\/Excalibur-7B", + "Average \u2b06\ufe0f": 73.6, + "ARC": 69.71, + "HellaSwag": 87.56, + "MMLU": 65.66, + "TruthfulQA": 67.24, + "Winogrande": 82.79, + "GSM8K": 68.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ceb9fd074f178fe25cb192d92f3f3bd1a3ff4bf1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "rombodawg\/Open_Gpt4_8x7B_v0.2", @@ -10575,7 +15704,7 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "3aba335d2131a014494a9df7c8a3d0783f50bad8", "Flagged": false, @@ -10618,8 +15747,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -10667,7 +15796,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 37.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": true, "Model sha": "df267682dbafe08a877602e6588bf461b6607d74", "Flagged": true, @@ -10690,7 +15819,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "ee6af302f1aa7b49a89f79ae2ae15e3a357099f0", "Flagged": false, @@ -10759,12 +15888,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "0219ef0ce5c8aaa6abe5e6c30f287edb777c7e8c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "seyf1elislam\/WestKunai-Hermes-7b", + "Average \u2b06\ufe0f": 73.51, + "ARC": 71.16, + "HellaSwag": 87.76, + "MMLU": 64.77, + "TruthfulQA": 65.25, + "Winogrande": 83.03, + "GSM8K": 69.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5f348a5ad4c996e22f0fcbdbb2a5326ffc069cc5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "abideen\/NexoNimbus-7B", @@ -10898,11 +16050,34 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b29298bbe30bba7c6aef25ef21cb9f4d470a10e2", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "mychen76\/mistral-7b-merged-dare_6x7", + "Average \u2b06\ufe0f": 73.46, + "ARC": 69.62, + "HellaSwag": 87.04, + "MMLU": 65.18, + "TruthfulQA": 66.98, + "Winogrande": 80.58, + "GSM8K": 71.34, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ec780be2797a51ba214f18f83b72adbdce2a78f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Neuronovo\/neuronovo-7B-v0.2", @@ -10926,6 +16101,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/bruphin-kappa", + "Average \u2b06\ufe0f": 73.44, + "ARC": 70.05, + "HellaSwag": 87.38, + "MMLU": 64.9, + "TruthfulQA": 65.99, + "Winogrande": 82.95, + "GSM8K": 69.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "09f8eda59034c027ebcbabb4e81f5de4cb08d061", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "cloudyu\/Mixtral-8x7B-Instruct-v0.1-DPO", @@ -10989,7 +16187,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 8.99, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "f4bfa8b298cbd0acc236117231d5b00de5f43240", "Flagged": false, @@ -11018,6 +16216,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Prima-LelantaclesV6-7b", + "Average \u2b06\ufe0f": 73.41, + "ARC": 71.5, + "HellaSwag": 87.65, + "MMLU": 64.64, + "TruthfulQA": 64.29, + "Winogrande": 84.85, + "GSM8K": 67.55, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5529f748fa5bbc1ab9d23487fecaac92c5ca74fe", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "argilla\/distilabeled-Marcoro14-7B-slerp-full", @@ -11081,7 +16302,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 8.99, - "Hub \u2764\ufe0f": 104.0, + "Hub \u2764\ufe0f": 106.0, "Available on the hub": true, "Model sha": "e09045608b2d68a6412185817306f4bb0cf3530c", "Flagged": true, @@ -11125,7 +16346,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 8.99, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -11150,7 +16371,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 8.99, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "aedfd66841e39a8db181d8549a42f4d2ee248b0a", "Flagged": false, @@ -11171,9 +16392,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 8.99, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "689dbca3e4bd977fa08b7a933e4e709277cd1394", "Flagged": false, @@ -11194,7 +16415,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 8.99, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -11249,31 +16470,31 @@ "MoE": true }, { - "T": "\ud83d\udd36", - "Model": "mlabonne\/Daredevil-7B", + "T": "\ud83e\udd1d", + "Model": "Sao10K\/Franziska-Mixtral-v1", "Average \u2b06\ufe0f": 73.36, - "ARC": 69.37, - "HellaSwag": 87.17, - "MMLU": 65.3, - "TruthfulQA": 64.09, - "Winogrande": 81.29, - "GSM8K": 72.93, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", + "ARC": 71.76, + "HellaSwag": 87.37, + "MMLU": 69.78, + "TruthfulQA": 70.07, + "Winogrande": 80.9, + "GSM8K": 60.27, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", - "#Params (B)": 7.24, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "015a362ee09e6370ad5b1b70fad8a7ebfcdc9e74", + "Model sha": "0121c0f6d769e8c0ecafeae0e85092855a4e95c9", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", - "Model": "shadowml\/Daredevil-7B", + "Model": "mlabonne\/Daredevil-7B", "Average \u2b06\ufe0f": 73.36, "ARC": 69.37, "HellaSwag": 87.17, @@ -11286,9 +16507,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": true, - "Hub License": "apache-2.0", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "015a362ee09e6370ad5b1b70fad8a7ebfcdc9e74", "Flagged": false, @@ -11311,12 +16532,81 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 244.0, + "Hub \u2764\ufe0f": 320.0, "Available on the hub": true, "Model sha": "566cdea53950f86eb51dae62812c29e79405cffe", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen13X-mistral-7B", + "Average \u2b06\ufe0f": 73.35, + "ARC": 69.88, + "HellaSwag": 87.28, + "MMLU": 64.99, + "TruthfulQA": 66.74, + "Winogrande": 82.0, + "GSM8K": 69.22, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "de54fcf7930b6edf974da6e4945981c71b4bc059", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Nitral-AI\/Eris_PrimeV4-Vision-7B", + "Average \u2b06\ufe0f": 73.35, + "ARC": 70.22, + "HellaSwag": 87.56, + "MMLU": 65.01, + "TruthfulQA": 67.76, + "Winogrande": 81.69, + "GSM8K": 67.85, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "afe74b909ecaa54b7d35ea0bde0b1626257085a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/DaturaCookie_7B", + "Average \u2b06\ufe0f": 73.35, + "ARC": 71.25, + "HellaSwag": 88.0, + "MMLU": 64.28, + "TruthfulQA": 68.48, + "Winogrande": 82.79, + "GSM8K": 65.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "755d702c80e5acee8c07676b4a4dee37de56e2a8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Gille\/MoE-StrangeMerges-2x7B", @@ -11340,6 +16630,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "mvpmaster\/kellemar-KrishnaHercules-0.1-7b-slerp", + "Average \u2b06\ufe0f": 73.33, + "ARC": 70.22, + "HellaSwag": 87.29, + "MMLU": 65.61, + "TruthfulQA": 63.03, + "Winogrande": 82.24, + "GSM8K": 71.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a5366279542a62faff7443f238f8490566517429", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "ryandt\/MusingCaterpillar", @@ -11377,14 +16690,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 35.43, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "777deaba78991d3786f3db6a513a63695170f52d", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udfe2", @@ -11401,7 +16714,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "?", "#Params (B)": 35.43, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -11432,6 +16745,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MixtureofMerges-MoE-2x7bRP-v8", + "Average \u2b06\ufe0f": 73.31, + "ARC": 71.33, + "HellaSwag": 88.06, + "MMLU": 64.33, + "TruthfulQA": 68.69, + "Winogrande": 82.95, + "GSM8K": 64.52, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cacdefef2b53baba4829920e430e994fa04724b8", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "cloudyu\/Mixtral_7Bx6_MoE_35B", @@ -11447,7 +16783,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "?", "#Params (B)": 35.43, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -11455,6 +16791,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "eldogbbhed\/Peagle-9b", + "Average \u2b06\ufe0f": 73.3, + "ARC": 71.5, + "HellaSwag": 87.34, + "MMLU": 64.36, + "TruthfulQA": 70.16, + "Winogrande": 80.35, + "GSM8K": 66.11, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3367f742a38a3d7a44594088d8805e781fd34136", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ibndias\/Nous-Hermes-2-MoE-2x34B", @@ -11542,7 +16901,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e5a0955eb36568aa850cd73debbe9815a9d1e60a", "Flagged": true, "MoE": false @@ -11562,7 +16921,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 8.99, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -11616,6 +16975,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "mychen76\/mistral-7b-merged-dare", + "Average \u2b06\ufe0f": 73.28, + "ARC": 69.71, + "HellaSwag": 87.05, + "MMLU": 65.07, + "TruthfulQA": 63.24, + "Winogrande": 81.61, + "GSM8K": 73.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "914aa317f9bee2fb8cf290b8e603394dfa8d3406", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "seyf1elislam\/WestKunai-XD-7b", + "Average \u2b06\ufe0f": 73.27, + "ARC": 71.25, + "HellaSwag": 87.59, + "MMLU": 64.69, + "TruthfulQA": 67.29, + "Winogrande": 82.24, + "GSM8K": 66.57, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "824e0c22a5f06a17d38251fa36be1d9ee7888d66", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Eric111\/NeuralBeagleOpenChat", @@ -11630,7 +17035,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -11639,6 +17044,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "carsenk\/flippa-exp26-v3-7b", + "Average \u2b06\ufe0f": 73.25, + "ARC": 68.09, + "HellaSwag": 86.5, + "MMLU": 64.42, + "TruthfulQA": 67.35, + "Winogrande": 84.77, + "GSM8K": 68.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2dda3515c5bbf02824addbe2e8f924a48ce21156", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "occultml\/CatMarcoro14-7B-slerp", @@ -11662,6 +17090,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Copium-Cola-9B", + "Average \u2b06\ufe0f": 73.25, + "ARC": 71.42, + "HellaSwag": 87.42, + "MMLU": 64.83, + "TruthfulQA": 68.6, + "Winogrande": 83.98, + "GSM8K": 63.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "df26b7dbe4567006b609da965d09a9175d8e3b04", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Kquant03\/Eukaryote-8x7B-bf16", @@ -11699,7 +17150,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 36.1, "Hub \u2764\ufe0f": 0.0, @@ -11722,7 +17173,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, @@ -11748,10 +17199,10 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "5197257333076dd80821a5055abae7d21a7dc844", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -11794,7 +17245,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 107.0, + "Hub \u2764\ufe0f": 111.0, "Available on the hub": true, "Model sha": "01f1a7861667c4869bb03251dfd10526bf846e9c", "Flagged": false, @@ -11910,11 +17361,34 @@ "Hub License": "?", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "86c89d182babd29521a41a54528e5bf8331ed4cd", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Cedaros\/BetaMonarch-10.7B", + "Average \u2b06\ufe0f": 73.18, + "ARC": 72.7, + "HellaSwag": 88.37, + "MMLU": 64.37, + "TruthfulQA": 76.85, + "Winogrande": 83.35, + "GSM8K": 53.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ca5d801cd3b457771f6b17342c323197e90dee91", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "CultriX\/MistralTrixTest", @@ -11930,7 +17404,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 8.99, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -12053,6 +17527,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Luna-2x7B-MoE", + "Average \u2b06\ufe0f": 73.13, + "ARC": 71.16, + "HellaSwag": 88.12, + "MMLU": 64.41, + "TruthfulQA": 68.66, + "Winogrande": 83.27, + "GSM8K": 63.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "9f9e4ae1c294ea4301eeefd3cf6222d156916144", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "brucethemoose\/Yi-34B-200K-DARE-merge-v7", @@ -12093,12 +17590,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 244.0, + "Hub \u2764\ufe0f": 320.0, "Available on the hub": true, "Model sha": "6ba531f1aec62375bf94ad9c7bb064953c4e9868", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "AurelPx\/Dare-k-7B-ties", + "Average \u2b06\ufe0f": 73.12, + "ARC": 69.11, + "HellaSwag": 87.08, + "MMLU": 65.02, + "TruthfulQA": 63.91, + "Winogrande": 82.0, + "GSM8K": 71.57, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "35851b86f6d9d367a23a0d9ff7ebd5ceb89ebf34", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "samir-fama\/SamirGPT-v1", @@ -12116,7 +17636,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "8e8abca2d9703dff2d60de78b013360a9a3f4d5e", "Flagged": false, @@ -12136,14 +17656,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "fa90ffb7fb57cb609d9d47719b3731693d23b312", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -12168,6 +17688,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "vishnukv\/newmerge", + "Average \u2b06\ufe0f": 73.1, + "ARC": 69.2, + "HellaSwag": 87.05, + "MMLU": 64.93, + "TruthfulQA": 65.99, + "Winogrande": 82.87, + "GSM8K": 68.54, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6f07d4c0e2ac155b568cff3dabfabdc0318e655", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "SanjiWatsuki\/Lelantos-DPO-7B", @@ -12191,6 +17734,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Steelskull\/Umbra-v3-MoE-4x11b", + "Average \u2b06\ufe0f": 73.09, + "ARC": 68.43, + "HellaSwag": 87.83, + "MMLU": 65.99, + "TruthfulQA": 69.3, + "Winogrande": 83.9, + "GSM8K": 63.08, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f8621d13b356eae26965173ae6146f8616ef38a3", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "ChaoticNeutrals\/Prima-LelantaclesV5-7b", @@ -12208,12 +17774,35 @@ "Merged": true, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "9d87945f984ee530cb1e062018906110e92dc470", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "mvpmaster\/Einstein-4d-Marcoro14-nddmpk-KrishnaHercules-7b-slerp", + "Average \u2b06\ufe0f": 73.08, + "ARC": 69.71, + "HellaSwag": 87.04, + "MMLU": 65.32, + "TruthfulQA": 64.37, + "Winogrande": 81.37, + "GSM8K": 70.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "597d83856e63194f19cd25c12408876f6e9263ec", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Eric111\/Mayo", @@ -12231,7 +17820,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "c9e75f7275ae8f8f8db94fea1d24a4855db96060", "Flagged": false, @@ -12274,11 +17863,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "4c0ea3e14e45c5f6aa0d8b409ccd9017501dee42", "Flagged": false, "MoE": false @@ -12301,7 +17890,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bd3924498c3ae041334be5018cd912b6537a633c", "Flagged": false, "MoE": false @@ -12323,8 +17912,8 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 17.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "1a68e2717bd4b42dc9860695c3a192845e388cf7", "Flagged": false, "MoE": false @@ -12352,9 +17941,32 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Prima-LelantaclesV7-7b", + "Average \u2b06\ufe0f": 73.03, + "ARC": 70.65, + "HellaSwag": 87.94, + "MMLU": 64.67, + "TruthfulQA": 67.45, + "Winogrande": 84.69, + "GSM8K": 62.77, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ff2a95f581cb60b85dbc376406d3ee6f56f705be", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "mlabonne\/Marcoro14-7B-slerp", + "Model": "shadowml\/Marcoro14-7B-ties", "Average \u2b06\ufe0f": 73.01, "ARC": 69.8, "HellaSwag": 87.13, @@ -12363,21 +17975,21 @@ "Winogrande": 81.61, "GSM8K": 70.89, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "cc-by-nc-4.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 20.0, - "Available on the hub": true, - "Model sha": "25f7e124456a5ad5c8c032088eb573d3e520d411", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "060737a4e7e8619b8d7c1180a6cc5b1a7c1d87fa", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "shadowml\/Marcoro14-7B-ties", + "Model": "mlabonne\/Marcoro14-7B-slerp", "Average \u2b06\ufe0f": 73.01, "ARC": 69.8, "HellaSwag": 87.13, @@ -12386,15 +17998,61 @@ "Winogrande": 81.61, "GSM8K": 70.89, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "25f7e124456a5ad5c8c032088eb573d3e520d411", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AbacusResearch\/RasGulla1-7b", + "Average \u2b06\ufe0f": 73.0, + "ARC": 69.71, + "HellaSwag": 87.4, + "MMLU": 64.94, + "TruthfulQA": 63.31, + "Winogrande": 80.9, + "GSM8K": 71.72, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3c71b5b8900e6271acceb30b2085b8a964f79473", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen9-mistral-7B", + "Average \u2b06\ufe0f": 73.0, + "ARC": 69.62, + "HellaSwag": 87.74, + "MMLU": 64.41, + "TruthfulQA": 68.54, + "Winogrande": 81.93, + "GSM8K": 65.73, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "060737a4e7e8619b8d7c1180a6cc5b1a7c1d87fa", + "Model sha": "e34f3768bf9ed4fdd0ac91cd3d71847cb45ed46c", "Flagged": false, "MoE": false }, @@ -12421,6 +18079,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/RoyalNoroichi-7B-slerp", + "Average \u2b06\ufe0f": 72.98, + "ARC": 70.48, + "HellaSwag": 87.38, + "MMLU": 64.78, + "TruthfulQA": 66.28, + "Winogrande": 82.24, + "GSM8K": 66.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ff742ddb9b730e68dd0d3c875ee207b2335d9046", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "argilla\/notux-8x7b-v1", @@ -12438,7 +18119,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 157.0, + "Hub \u2764\ufe0f": 161.0, "Available on the hub": true, "Model sha": "1f8562051647d5537dc950315e74534b363a0812", "Flagged": false, @@ -12482,7 +18163,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "gpl", + "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -12490,6 +18171,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/Cognate-7B-slerp", + "Average \u2b06\ufe0f": 72.96, + "ARC": 70.48, + "HellaSwag": 87.33, + "MMLU": 64.85, + "TruthfulQA": 65.16, + "Winogrande": 82.56, + "GSM8K": 67.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d2134aefee7d7bf22694991867bf2ba9ac992396", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "vicgalle\/NeuralBeagle-11B", @@ -12553,7 +18257,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 12.91, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "9cb2d09228ac87d761d23a1284c79b55f9f285d9", "Flagged": false, @@ -12645,7 +18349,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 44.0, "Available on the hub": true, "Model sha": "cc2f19f5bc9ad693d4447e42e9844d9931ab8e81", "Flagged": false, @@ -12720,6 +18424,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "eldogbbhed\/NeuralPearlBeagle", + "Average \u2b06\ufe0f": 72.88, + "ARC": 68.26, + "HellaSwag": 87.25, + "MMLU": 64.05, + "TruthfulQA": 62.85, + "Winogrande": 81.69, + "GSM8K": 73.16, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f2ef27a21d1e88981118c9f9ddba88affff4d41b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "samir-fama\/FernandoGPT-v1", @@ -12737,12 +18464,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "a26fbae35874a6aafb02e39fd8a623022b9e2a95", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Bianca-7b", + "Average \u2b06\ufe0f": 72.87, + "ARC": 69.71, + "HellaSwag": 86.11, + "MMLU": 65.25, + "TruthfulQA": 63.95, + "Winogrande": 80.9, + "GSM8K": 71.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c962dd3095ffa6ff247f3e3cef2b44f9ba500894", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Kukedlc\/NeuralKukedlc-7B-Labonned", @@ -12789,6 +18539,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen3X", + "Average \u2b06\ufe0f": 72.82, + "ARC": 70.14, + "HellaSwag": 87.37, + "MMLU": 64.69, + "TruthfulQA": 66.37, + "Winogrande": 80.98, + "GSM8K": 67.4, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15cdba52e2175b0d6003274642260d6b45cc57e1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Himitsui\/Kaiju-11B", @@ -12806,7 +18579,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "cb9c9b0fb1d49b085069617bd8dc9cdddfdba7fb", "Flagged": false, @@ -12835,6 +18608,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Azazelle\/Bianca-7b", + "Average \u2b06\ufe0f": 72.82, + "ARC": 69.45, + "HellaSwag": 86.08, + "MMLU": 65.08, + "TruthfulQA": 64.04, + "Winogrande": 81.06, + "GSM8K": 71.19, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c962dd3095ffa6ff247f3e3cef2b44f9ba500894", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AA051611\/O0201", @@ -12881,6 +18677,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "S-miguel\/The-Trinity-Coder-7B", + "Average \u2b06\ufe0f": 72.81, + "ARC": 69.37, + "HellaSwag": 86.17, + "MMLU": 64.9, + "TruthfulQA": 61.25, + "Winogrande": 81.77, + "GSM8K": 73.39, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cca19971f846c6d45e089dd1425f86fa4cb48f0a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "v1olet\/v1olet_marcoroni-go-bruins-merge-7B", @@ -12898,7 +18717,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": true, "Model sha": "aca5d9df596ac1f9ddffbec3de282ecbe3b32d68", "Flagged": true, @@ -12921,12 +18740,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "04c11fb1df83af9a52139e45fc2fc34b3386a37f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "logicker\/SkkuDS-DPO-72B-v3", + "Average \u2b06\ufe0f": 72.8, + "ARC": 66.04, + "HellaSwag": 86.11, + "MMLU": 77.34, + "TruthfulQA": 59.73, + "Winogrande": 82.64, + "GSM8K": 64.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5cf11f6e983a7c11b17c1b7c4aee6ff99e30ba82", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "PSanni\/MPOMixtral-8x7B-Instruct-v0.1", @@ -13036,7 +18878,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "ec060c6a4f5e45370cf2e2d65ecb388b048b0fdb", "Flagged": false, @@ -13065,6 +18907,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/RoyalMaid-7B-slerp", + "Average \u2b06\ufe0f": 72.75, + "ARC": 70.39, + "HellaSwag": 87.25, + "MMLU": 64.72, + "TruthfulQA": 64.18, + "Winogrande": 82.4, + "GSM8K": 67.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ec8bc0ad5bb403a29d9124cf6e3183ff423acc23", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cookinai\/OpenCM-14", @@ -13103,11 +18968,34 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "b4fef0d4a79ed1e5441d6a0d8fb06e0eda223d9e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Sao10K\/Skadi-Mixtral-v1", + "Average \u2b06\ufe0f": 72.74, + "ARC": 70.14, + "HellaSwag": 87.65, + "MMLU": 72.19, + "TruthfulQA": 60.43, + "Winogrande": 81.29, + "GSM8K": 64.75, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "b4fef0d4a79ed1e5441d6a0d8fb06e0eda223d9e", + "Model sha": "a6d56964be9b3d796515253e6b1fb86a3d025260", "Flagged": false, "MoE": false }, @@ -13194,13 +19082,36 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "b41d174c2041e8661086e4eb939480641a5c66dc", "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-Gamma-V2-9B", + "Average \u2b06\ufe0f": 72.72, + "ARC": 69.88, + "HellaSwag": 86.84, + "MMLU": 64.22, + "TruthfulQA": 68.85, + "Winogrande": 82.87, + "GSM8K": 63.68, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7af8365a3e990f2811231d9c521acf22a11381a9", + "Flagged": false, "MoE": false }, { @@ -13226,6 +19137,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "ChaoticNeutrals\/RP_Vision_7B", + "Average \u2b06\ufe0f": 72.71, + "ARC": 70.65, + "HellaSwag": 87.81, + "MMLU": 64.58, + "TruthfulQA": 68.5, + "Winogrande": 82.64, + "GSM8K": 62.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8bfd1e9425e1c12b95967197c8388f61d7961b07", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "mistralai\/Mixtral-8x7B-Instruct-v0.1", @@ -13243,7 +19177,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 3069.0, + "Hub \u2764\ufe0f": 3536.0, "Available on the hub": true, "Model sha": "125c431e2ff41a156b9f9076f744d2f35dd6e67a", "Flagged": false, @@ -13272,6 +19206,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/RPMix-4x7B-MoE", + "Average \u2b06\ufe0f": 72.68, + "ARC": 71.08, + "HellaSwag": 87.79, + "MMLU": 64.36, + "TruthfulQA": 67.29, + "Winogrande": 81.93, + "GSM8K": 63.61, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c9fb38c846ba1f1ce9a7a3560e491ea9d4a8d875", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "mvpmaster\/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp", + "Average \u2b06\ufe0f": 72.67, + "ARC": 69.28, + "HellaSwag": 86.59, + "MMLU": 65.13, + "TruthfulQA": 62.69, + "Winogrande": 80.9, + "GSM8K": 71.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "298b37e7607e7dbe6ca50ceacbf62c4f53300e7e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "SJ-Donald\/SJ-SOLAR-10.7b-DPO", @@ -13312,12 +19292,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "96e7c78544d7eca96e3ae60ff80c728f3109e8ba", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v5-34b", + "Average \u2b06\ufe0f": 72.65, + "ARC": 66.98, + "HellaSwag": 84.79, + "MMLU": 76.0, + "TruthfulQA": 62.68, + "Winogrande": 83.43, + "GSM8K": 62.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "05a9ef37686d678f267a15664b5ce66612b7996a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Fimbulvetr-11B-v2-Test-14", @@ -13339,8 +19342,54 @@ "Available on the hub": false, "Model sha": "4095b989123d28da44717f4ec8d4bd01055f4650", "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Sao10K\/Fimbulvetr-11B-v2", + "Average \u2b06\ufe0f": 72.63, + "ARC": 70.14, + "HellaSwag": 87.79, + "MMLU": 66.83, + "TruthfulQA": 63.43, + "Winogrande": 82.95, + "GSM8K": 64.67, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 73.0, + "Available on the hub": true, + "Model sha": "afc90bd0690d0cbedd01f22d1d6ef0e44f30b5f4", + "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/ComplectMaid-7B-slerp", + "Average \u2b06\ufe0f": 72.63, + "ARC": 69.97, + "HellaSwag": 87.34, + "MMLU": 64.62, + "TruthfulQA": 65.88, + "Winogrande": 82.08, + "GSM8K": 65.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ea7732f9ee3dbd7ef7c3dee9600eabab04837b4b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Gille\/StrangeMerges_4-7B-slerp", @@ -13364,6 +19413,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/WestMaid_HermesMonarchv0.1", + "Average \u2b06\ufe0f": 72.62, + "ARC": 70.22, + "HellaSwag": 87.42, + "MMLU": 64.31, + "TruthfulQA": 61.99, + "Winogrande": 82.16, + "GSM8K": 69.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a2c52c805979eac66e38a9e17d8fb19326665649", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mistralai\/Mixtral-8x7B-Instruct-v0.1", @@ -13381,7 +19453,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 3069.0, + "Hub \u2764\ufe0f": 3536.0, "Available on the hub": true, "Model sha": "3de0408ae8b591d9ac516a2384925dd98ebc66f4", "Flagged": false, @@ -13410,6 +19482,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen12-mistral-7B", + "Average \u2b06\ufe0f": 72.6, + "ARC": 69.03, + "HellaSwag": 87.34, + "MMLU": 64.92, + "TruthfulQA": 66.99, + "Winogrande": 80.9, + "GSM8K": 66.41, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fce30460b08824bdf1559a48cb2cdf1499c40e8b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/Severus-7B", @@ -13427,7 +19522,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "adf7c513e9cadbe25cc2be61c43f3f36f1b488e9", "Flagged": false, @@ -13473,7 +19568,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 11.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "7bd8487fc3a5c3bac022bfe8c34d2f630c123d40", "Flagged": false, @@ -13496,7 +19591,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "1b3a5c98381f37a2ec97ce80d1d88d472a7d1802", "Flagged": false, @@ -13519,7 +19614,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "db8fde5fb86be6414c42d71ff6d8bf44ae4275ad", "Flagged": false, @@ -13542,7 +19637,7 @@ "Merged": true, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "0823229057d02acb1c9dda173d6fb2ea3b46b0af", "Flagged": false, @@ -13571,6 +19666,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/bophades-mistral-7B", + "Average \u2b06\ufe0f": 72.54, + "ARC": 69.97, + "HellaSwag": 87.28, + "MMLU": 64.77, + "TruthfulQA": 59.83, + "Winogrande": 83.74, + "GSM8K": 69.67, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c368ff0333aadf3920633441993ae1e7fb4bdeb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "DreadPoor\/EveryNight-7B-slerp", @@ -13585,7 +19703,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -13611,7 +19729,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "067200540bfab02c1aad895e709075f1416279f7", "Flagged": false, @@ -13635,7 +19753,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6ec546141522aef9b42d1a014f1a539fcc485c45", "Flagged": false, "MoE": false @@ -13658,7 +19776,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "a0c0f4f9d4fbfe0a688d1d58b98b30f0ca6fc9bd", "Flagged": true, "MoE": false @@ -13704,11 +19822,57 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0223ffb3f70272009d0d76923f40cb31f3d2347e", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen9X-mistral-7B", + "Average \u2b06\ufe0f": 72.51, + "ARC": 69.54, + "HellaSwag": 87.46, + "MMLU": 64.7, + "TruthfulQA": 65.57, + "Winogrande": 81.53, + "GSM8K": 66.26, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "89da027ee512f974cedb6481920488867fc15afa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mychen76\/openmixtral-4x7b-merged", + "Average \u2b06\ufe0f": 72.51, + "ARC": 69.45, + "HellaSwag": 86.75, + "MMLU": 65.29, + "TruthfulQA": 61.33, + "Winogrande": 81.06, + "GSM8K": 71.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1a0afc53bd0643e098d88688e8520fc9f7f2f3f", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "rwitz2\/pee", @@ -13755,6 +19919,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/bruphin-iota", + "Average \u2b06\ufe0f": 72.5, + "ARC": 68.43, + "HellaSwag": 86.55, + "MMLU": 65.02, + "TruthfulQA": 66.17, + "Winogrande": 81.06, + "GSM8K": 67.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f9e91c9a891e87d9a8808cb4d73300c364be6402", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mvpmaster\/Einstein-4D-MoE-2x7b-test", + "Average \u2b06\ufe0f": 72.5, + "ARC": 69.71, + "HellaSwag": 86.52, + "MMLU": 65.41, + "TruthfulQA": 62.29, + "Winogrande": 81.45, + "GSM8K": 69.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "30e1c404409a838456b3ec24456653384bcb3bfc", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/bagel-dpo-8x7b-v0.2", @@ -13772,12 +19982,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "61822ea65b8a4c56d2b5622e2adf69e430fac29a", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "pabloce\/Dolphin-2.8-slerp", + "Average \u2b06\ufe0f": 72.48, + "ARC": 68.0, + "HellaSwag": 86.51, + "MMLU": 64.38, + "TruthfulQA": 65.2, + "Winogrande": 82.16, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7f1cdd89c9c1c59512e041c654e7314322ea274", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ignos\/Mistral-T5-7B-v1", @@ -13818,7 +20051,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 32.0, + "Hub \u2764\ufe0f": 54.0, "Available on the hub": true, "Model sha": "f55aef05f6632a1407fcddcbc6729613b07e87e2", "Flagged": false, @@ -13893,6 +20126,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen6-mistral-7B", + "Average \u2b06\ufe0f": 72.44, + "ARC": 69.2, + "HellaSwag": 86.99, + "MMLU": 64.17, + "TruthfulQA": 63.48, + "Winogrande": 81.29, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1729027e13f914361b151c4e91b1c02d2a4e63c9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "fhai50032\/RPLakeCoder-TxC", @@ -13939,6 +20195,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "Sao10K\/Fimbulvetr-11B-v2", + "Average \u2b06\ufe0f": 72.4, + "ARC": 70.14, + "HellaSwag": 87.77, + "MMLU": 66.68, + "TruthfulQA": 63.42, + "Winogrande": 82.72, + "GSM8K": 63.68, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 73.0, + "Available on the hub": true, + "Model sha": "afc90bd0690d0cbedd01f22d1d6ef0e44f30b5f4", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "liminerity\/Blur-7B-slerp-v0.1", @@ -13979,7 +20258,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 32.0, + "Hub \u2764\ufe0f": 54.0, "Available on the hub": true, "Model sha": "d7d33a1517c57b596162a71a48bc29c87d29d9aa", "Flagged": false, @@ -14002,7 +20281,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "91a49d4c156ecb21e8477529e6b957242ba3829e", "Flagged": false, @@ -14025,7 +20304,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 23.0, "Available on the hub": true, "Model sha": "3ddae31382dd3f7e654c1fc0e9b37f2e7f4ede92", "Flagged": false, @@ -14045,7 +20324,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -14071,7 +20350,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "5dbc14842c16f1fa315e682e7e5bdb0248a2b05e", "Flagged": false, @@ -14117,7 +20396,7 @@ "Merged": false, "Hub License": "cc-by-nc-2.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 73.0, + "Hub \u2764\ufe0f": 76.0, "Available on the hub": true, "Model sha": "91e0a33fd2cb0a77401831e96536b91c5b7817e4", "Flagged": false, @@ -14164,7 +20443,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ce0d461a6de81d5b8ec4d338fb0c6e7991d0b1ff", "Flagged": false, "MoE": false @@ -14187,7 +20466,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d66c7d87fc3670c9292177e4cfc59e8a9d71322d", "Flagged": false, "MoE": false @@ -14215,6 +20494,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "grimjim\/kuno-kunoichi-v1-DPO-v2-SLERP-7B", + "Average \u2b06\ufe0f": 72.33, + "ARC": 69.11, + "HellaSwag": 87.33, + "MMLU": 64.8, + "TruthfulQA": 65.12, + "Winogrande": 80.9, + "GSM8K": 66.72, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "88d5b63f7d62baeab4704b72ed656aa8bee3a2fb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "OpenBuddy\/openbuddy-deepseek-67b-v15.2", @@ -14232,12 +20534,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 67.42, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "c3caef28f8402d52d6a646a7e1e00a971db1c507", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "mychen76\/openmixtral-6x7b-v2", + "Average \u2b06\ufe0f": 72.33, + "ARC": 68.52, + "HellaSwag": 86.75, + "MMLU": 65.11, + "TruthfulQA": 65.13, + "Winogrande": 79.87, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e38efbb07209b4e8484e4820317eb02eb95ef23f", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "mlabonne\/Beyonder-4x7B-v2", @@ -14255,7 +20580,7 @@ "Merged": true, "Hub License": "other", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 113.0, + "Hub \u2764\ufe0f": 120.0, "Available on the hub": true, "Model sha": "f44d94a8a0ccfa98e5173da9d88a5ed09efad30e", "Flagged": false, @@ -14279,7 +20604,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "83bcf51c709bcb4fcb3c8f0f91de22f458a07ee4", "Flagged": false, "MoE": false @@ -14376,6 +20701,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "R136a1\/InfinityKuno-2x7B", + "Average \u2b06\ufe0f": 72.32, + "ARC": 69.62, + "HellaSwag": 87.44, + "MMLU": 64.49, + "TruthfulQA": 63.28, + "Winogrande": 82.72, + "GSM8K": 66.34, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "382698efc4e5ff54a4155e1f2c40547ac3b2aa64", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "jan-ai\/Solar-10.7B-SLERP", @@ -14399,6 +20747,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "pabloce\/Dolphin-2.8-slerp", + "Average \u2b06\ufe0f": 72.28, + "ARC": 68.0, + "HellaSwag": 86.43, + "MMLU": 64.39, + "TruthfulQA": 65.22, + "Winogrande": 82.0, + "GSM8K": 67.63, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1da8b3280f67eeafcdf83e0bd696a1071c579aa3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cstr\/Spaetzle-v8-7b", + "Average \u2b06\ufe0f": 72.27, + "ARC": 68.69, + "HellaSwag": 86.68, + "MMLU": 64.6, + "TruthfulQA": 64.05, + "Winogrande": 81.45, + "GSM8K": 68.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "4de312664e059136d304f261755ba77baba94bb8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mncai\/yi-34B-v3", @@ -14416,12 +20810,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "f7605af56f29b42e72f9c2cbbd4ad8e443a8dae0", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/CausalLM-RP-34B", + "Average \u2b06\ufe0f": 72.26, + "ARC": 68.0, + "HellaSwag": 83.43, + "MMLU": 83.1, + "TruthfulQA": 54.51, + "Winogrande": 82.16, + "GSM8K": 62.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "e2a033646231bd947a3948d3aac198d34d04ea38", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Fimbulvetr-10.7B-v1", @@ -14439,7 +20856,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 25.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "bff7146aafe1a5b84631bd279112c8c5b95d2802", "Flagged": false, @@ -14485,7 +20902,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 41.0, "Available on the hub": true, "Model sha": "7b041695f3ac19052f8c8be1918822bba8f73f74", "Flagged": false, @@ -14508,7 +20925,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "4e21eea3c32d00b2fcfc5bcfd16d8dc9d0d8874d", "Flagged": false, @@ -14560,6 +20977,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_7-7B-slerp", + "Average \u2b06\ufe0f": 72.21, + "ARC": 69.88, + "HellaSwag": 87.66, + "MMLU": 64.85, + "TruthfulQA": 60.45, + "Winogrande": 83.19, + "GSM8K": 67.25, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fb638af990984b2d46ab4e85b1b164dec46c0f66", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "CultriX\/CultriX-MoE-Model", @@ -14667,10 +21107,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9bdce071e0f87fe047cd2446be42edf91175c3be", "Flagged": false, "MoE": false @@ -14715,12 +21155,58 @@ "Merged": true, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "17fe477d833b16aab50bef843bc8bf196a2710ac", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/Open-StarLake-Swap-7B", + "Average \u2b06\ufe0f": 72.15, + "ARC": 70.56, + "HellaSwag": 86.99, + "MMLU": 65.11, + "TruthfulQA": 57.5, + "Winogrande": 83.19, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1722dfaffa2f968ed9dd9cd70952c447cf823f72", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "cstr\/Spaetzle-v8-7b", + "Average \u2b06\ufe0f": 72.14, + "ARC": 68.69, + "HellaSwag": 86.66, + "MMLU": 64.59, + "TruthfulQA": 64.06, + "Winogrande": 81.37, + "GSM8K": 67.48, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "4de312664e059136d304f261755ba77baba94bb8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "SanjiWatsuki\/Kunoichi-7B", @@ -14738,7 +21224,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 62.0, + "Hub \u2764\ufe0f": 66.0, "Available on the hub": true, "Model sha": "cb731f23e65b8638143d88055e1db57b84fdd546", "Flagged": false, @@ -14785,7 +21271,7 @@ "Hub License": "?", "#Params (B)": 72.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "508ee8ddfd8b823fcd4b0366a72c7981c8b447d8", "Flagged": false, "MoE": false @@ -14830,12 +21316,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "b859eae30d69b065060e268b4e918601dabcc36c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "mayacinka\/chatty-djinn-14B", + "Average \u2b06\ufe0f": 72.08, + "ARC": 70.39, + "HellaSwag": 86.45, + "MMLU": 64.4, + "TruthfulQA": 67.57, + "Winogrande": 83.11, + "GSM8K": 60.58, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 13.57, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e38656d8a5110f0bf05e7cb8cec2ae8043656c4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "rwitz\/go-bruins-v2", @@ -14853,7 +21362,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": true, "Model sha": "24f8ce81d25c433bc6be147928779fb2d00ae0e7", "Flagged": true, @@ -14876,7 +21385,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 51.0, + "Hub \u2764\ufe0f": 55.0, "Available on the hub": true, "Model sha": "6011e2ef7791738f3b78fa9e122360029df7c9ed", "Flagged": false, @@ -14897,10 +21406,10 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "gpl", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5faa6fd16b30b975ec7d18dea9203c186511d910", "Flagged": false, "MoE": false @@ -14923,7 +21432,7 @@ "Hub License": "?", "#Params (B)": 72.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "508ee8ddfd8b823fcd4b0366a72c7981c8b447d8", "Flagged": false, "MoE": false @@ -14969,7 +21478,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6d083dd5e571749ad0c574897abf473600142b16", "Flagged": false, "MoE": false @@ -15034,15 +21543,38 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "75c6be75cd8eeea4bc06f0d46bfeeb803b19ff26", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "mvpmaster\/NeuralDareDMistralPro-7b-slerp", + "Average \u2b06\ufe0f": 72.04, + "ARC": 69.03, + "HellaSwag": 86.74, + "MMLU": 63.46, + "TruthfulQA": 64.12, + "Winogrande": 80.19, + "GSM8K": 68.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "21bd46abf818ff01115148f35ecac201be3de1e8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "llmixer\/BigWeave-v16-103b", @@ -15057,10 +21589,10 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "unknown", "#Params (B)": 103.2, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "a1f70cd042fc8b4c5767f597edbb0054e7cb14f9", "Flagged": false, @@ -15106,7 +21638,7 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 71.0, + "Hub \u2764\ufe0f": 73.0, "Available on the hub": true, "Model sha": "f16df07e24654858a6b04c3ecb0670dcfc42337d", "Flagged": false, @@ -15135,6 +21667,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/Bophades-BruinsMaid-7B", + "Average \u2b06\ufe0f": 71.97, + "ARC": 69.54, + "HellaSwag": 86.52, + "MMLU": 64.93, + "TruthfulQA": 60.5, + "Winogrande": 82.56, + "GSM8K": 67.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f1723c8cc48103e6e66b96699dda73e5a8f12802", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/Maidphin-Kunoichi-7B", + "Average \u2b06\ufe0f": 71.96, + "ARC": 69.37, + "HellaSwag": 87.11, + "MMLU": 64.78, + "TruthfulQA": 64.27, + "Winogrande": 80.35, + "GSM8K": 65.88, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a5fcfee8080ca5ced84f0d25a70c91368e142318", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.5", @@ -15152,7 +21730,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "fe9f9e52f1b48112d1c4349abbc0f104e56303ab", "Flagged": false, @@ -15175,7 +21753,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": true, "Model sha": "49c730c9e00299eaefeb5ada30a9ec53659729a5", "Flagged": true, @@ -15198,7 +21776,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 146.0, + "Hub \u2764\ufe0f": 150.0, "Available on the hub": true, "Model sha": "f4f3f6144dd143d6ec43ece9ab0fdd740ed610f1", "Flagged": false, @@ -15244,12 +21822,58 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "ec748dade16858ef2fb3c712c78de748d165a21c", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "databricks\/dbrx-base", + "Average \u2b06\ufe0f": 71.9, + "ARC": 66.04, + "HellaSwag": 89.0, + "MMLU": 74.7, + "TruthfulQA": 55.07, + "Winogrande": 78.06, + "GSM8K": 68.54, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 131.6, + "Hub \u2764\ufe0f": 441.0, + "Available on the hub": false, + "Model sha": "8c2724d4715132a4a6f3e520cd2b6c6189848c11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "arcee-ai\/Saul-Instruct-Clown-7b", + "Average \u2b06\ufe0f": 71.9, + "ARC": 68.09, + "HellaSwag": 86.23, + "MMLU": 64.41, + "TruthfulQA": 63.2, + "Winogrande": 81.61, + "GSM8K": 67.85, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d7954892af5c69c741493618e3830992929196a1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AA051611\/A0110", @@ -15265,7 +21889,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "gpl", + "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -15296,6 +21920,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "ozayezerceli\/BetterSaul-7B-slerp", + "Average \u2b06\ufe0f": 71.88, + "ARC": 68.09, + "HellaSwag": 86.3, + "MMLU": 64.31, + "TruthfulQA": 63.08, + "Winogrande": 82.32, + "GSM8K": 67.17, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea76a92d0d35dc6985651581ce84eafb55763672", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cloudyu\/Pluto_24B_DPO_200", @@ -15313,11 +21960,34 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "3e6ced019d4cab13bd0ca2cefbf91bc7bba31375", "Flagged": false, - "MoE": true + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Prima-LelantaclesV6.25-7b", + "Average \u2b06\ufe0f": 71.88, + "ARC": 69.11, + "HellaSwag": 87.29, + "MMLU": 64.42, + "TruthfulQA": 67.44, + "Winogrande": 82.64, + "GSM8K": 60.35, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "74cae4cc41a280382ae3930a373d158102d94d58", + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -15336,15 +22006,15 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "04a49e7c37033714a42a22c834e0c0179cfb90c6", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "jeiku\/Cookie_7B", + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Cookie_7B", "Average \u2b06\ufe0f": 71.87, "ARC": 69.71, "HellaSwag": 87.57, @@ -15352,7 +22022,7 @@ "TruthfulQA": 66.88, "Winogrande": 81.37, "GSM8K": 61.18, - "Type": "fine-tuned on domain-specific datasets", + "Type": "base merges and moerges", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", @@ -15361,13 +22031,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "026955076c0744e1257cef9b4edc25d6389fd413", + "Model sha": "bb106b2f29819c4e4a173cefaa62fa9b6a4a0d2e", "Flagged": false, "MoE": false }, { - "T": "\ud83e\udd1d", - "Model": "ChaoticNeutrals\/Cookie_7B", + "T": "\ud83d\udd36", + "Model": "jeiku\/Cookie_7B", "Average \u2b06\ufe0f": 71.87, "ARC": 69.71, "HellaSwag": 87.57, @@ -15375,16 +22045,16 @@ "TruthfulQA": 66.88, "Winogrande": 81.37, "GSM8K": 61.18, - "Type": "base merges and moerges", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": true, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, - "Model sha": "bb106b2f29819c4e4a173cefaa62fa9b6a4a0d2e", + "Model sha": "026955076c0744e1257cef9b4edc25d6389fd413", "Flagged": false, "MoE": false }, @@ -15472,7 +22142,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "gpl", + "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -15480,6 +22150,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_34-7B-slerp", + "Average \u2b06\ufe0f": 71.83, + "ARC": 70.05, + "HellaSwag": 87.46, + "MMLU": 61.82, + "TruthfulQA": 73.24, + "Winogrande": 81.29, + "GSM8K": 57.09, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dad4154a5e93eb0198d54a5347224547e7c988c5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/openchat-3.5-1210-Seraph-Slerp", @@ -15549,6 +22242,52 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/A0308-G", + "Average \u2b06\ufe0f": 71.81, + "ARC": 68.34, + "HellaSwag": 83.64, + "MMLU": 84.07, + "TruthfulQA": 54.02, + "Winogrande": 80.43, + "GSM8K": 60.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c33065e209686b67f3374fffcb11ee7b90aa7983", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/C0318-G", + "Average \u2b06\ufe0f": 71.81, + "ARC": 64.51, + "HellaSwag": 83.88, + "MMLU": 74.16, + "TruthfulQA": 58.61, + "Winogrande": 79.32, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "CohereForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1fbff466a94c2cc6ed7ec7e21b478f9528caab89", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "OpenBuddy\/openbuddy-deepseek-67b-v18.1-4k", @@ -15589,7 +22328,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 67.0, - "Hub \u2764\ufe0f": 150.0, + "Hub \u2764\ufe0f": 157.0, "Available on the hub": true, "Model sha": "79648bef7658bb824e4630740f6e1484c1b0620b", "Flagged": false, @@ -15635,12 +22374,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "72267d131001da8cdf253105c367fd913db79523", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-V4-Alpha-7B", + "Average \u2b06\ufe0f": 71.78, + "ARC": 69.28, + "HellaSwag": 87.06, + "MMLU": 64.95, + "TruthfulQA": 63.94, + "Winogrande": 81.45, + "GSM8K": 63.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8e98c2ba7f8adae6151e32cef1c607cfd40ede7a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "OpenBuddy\/openbuddy-deepseek-67b-v15.1", @@ -15687,6 +22449,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen", + "Average \u2b06\ufe0f": 71.74, + "ARC": 68.17, + "HellaSwag": 87.06, + "MMLU": 64.68, + "TruthfulQA": 63.02, + "Winogrande": 81.45, + "GSM8K": 66.03, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bf4d9b8534c5b782052512686135d4e8464e471c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Tess-M-Creative-v1.0", @@ -15710,6 +22495,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "mvpmaster\/Einstein-4D-Marcoro14-7b-full-slerp", + "Average \u2b06\ufe0f": 71.73, + "ARC": 68.86, + "HellaSwag": 85.98, + "MMLU": 64.57, + "TruthfulQA": 62.07, + "Winogrande": 80.43, + "GSM8K": 68.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "65a29ae7376affc698972b99c4802fa16baf4fcf", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "VitalContribution\/Evangelion-7B", @@ -15819,12 +22627,35 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 42.0, + "Hub \u2764\ufe0f": 48.0, "Available on the hub": true, "Model sha": "3fc12ef0089d55509552d1569f3107fd6a24b90f", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/FrankenMonarch-7B", + "Average \u2b06\ufe0f": 71.67, + "ARC": 71.59, + "HellaSwag": 88.59, + "MMLU": 63.93, + "TruthfulQA": 73.69, + "Winogrande": 83.58, + "GSM8K": 48.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5f6c842da4acef82352939453fdd6e50d716e288", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Azure99\/blossom-v4-yi-34b", @@ -15865,12 +22696,127 @@ "Merged": false, "Hub License": "unknown", "#Params (B)": 103.2, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "59004f5610548e626ad27cd4a7b92daa3ccfc9c8", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/Fett-Eris-Mix-7B", + "Average \u2b06\ufe0f": 71.66, + "ARC": 68.77, + "HellaSwag": 87.33, + "MMLU": 63.65, + "TruthfulQA": 71.91, + "Winogrande": 80.82, + "GSM8K": 57.47, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "287e1bc2ca35ba1978cfe1040d9183d530b23c0c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/MixSwap", + "Average \u2b06\ufe0f": 71.66, + "ARC": 69.45, + "HellaSwag": 86.95, + "MMLU": 65.18, + "TruthfulQA": 56.56, + "Winogrande": 83.19, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8926d6bff276af1c21f4467d48555f4d13540b95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-V3-AlphaFlavour-7B", + "Average \u2b06\ufe0f": 71.64, + "ARC": 68.86, + "HellaSwag": 86.85, + "MMLU": 61.17, + "TruthfulQA": 71.94, + "Winogrande": 81.53, + "GSM8K": 59.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "06f48a60db61e3855fcb4be17ab1c8ade40d6fee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Calme-7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 71.63, + "ARC": 67.24, + "HellaSwag": 85.57, + "MMLU": 64.97, + "TruthfulQA": 59.38, + "Winogrande": 83.35, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5f18e24665f62b8e9a3492af247978073fea54f9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "liminerity\/e.star.7b", + "Average \u2b06\ufe0f": 71.62, + "ARC": 66.81, + "HellaSwag": 87.12, + "MMLU": 63.6, + "TruthfulQA": 62.63, + "Winogrande": 82.4, + "GSM8K": 67.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e3da1a54cfdde55ae0d31db3c79512729bd8cbe8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AA051612\/B0121", @@ -15917,6 +22863,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AGI-0\/Magistral-7B-v0.1", + "Average \u2b06\ufe0f": 71.6, + "ARC": 67.15, + "HellaSwag": 86.3, + "MMLU": 64.3, + "TruthfulQA": 61.39, + "Winogrande": 83.5, + "GSM8K": 66.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "12be40c847ab6d37efce76ca3bc57686f70d45ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-14b-MoE-LaserChat", + "Average \u2b06\ufe0f": 71.6, + "ARC": 66.72, + "HellaSwag": 84.88, + "MMLU": 65.17, + "TruthfulQA": 57.64, + "Winogrande": 81.93, + "GSM8K": 73.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "e3d7c73110dd6edd9e96b1f3d9b0dea91d83ce2d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_33-7B-slerp", + "Average \u2b06\ufe0f": 71.59, + "ARC": 70.73, + "HellaSwag": 87.26, + "MMLU": 63.87, + "TruthfulQA": 68.09, + "Winogrande": 81.69, + "GSM8K": 57.92, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "745eeff3d8cf80d618a9bda256d1faf36dd871b7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "RatanRohith\/NeuralPizza-7B-V0.2", @@ -15940,6 +22955,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/flammen2", + "Average \u2b06\ufe0f": 71.57, + "ARC": 68.94, + "HellaSwag": 86.87, + "MMLU": 64.78, + "TruthfulQA": 63.12, + "Winogrande": 80.74, + "GSM8K": 64.97, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0d7f9b756f3b173a9d88ff9fe539bd5b6ea542da", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "saishf\/Top-Western-Maid-7B", @@ -16119,11 +23157,34 @@ "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "215cbefbc69d22c28181651b5b964c329ca09f59", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "R136a1\/InfinityKumon-2x7B", + "Average \u2b06\ufe0f": 71.52, + "ARC": 69.62, + "HellaSwag": 87.09, + "MMLU": 64.97, + "TruthfulQA": 61.99, + "Winogrande": 81.93, + "GSM8K": 63.53, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1cf1b3a313de0b3b22a61dd3741c1bd5a3d14c66", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "deepseek-ai\/deepseek-llm-67b-chat", @@ -16141,12 +23202,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 67.0, - "Hub \u2764\ufe0f": 150.0, + "Hub \u2764\ufe0f": 157.0, "Available on the hub": true, "Model sha": "79648bef7658bb824e4630740f6e1484c1b0620b", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "eldogbbhed\/NeuralMonarchCoderPearlBeagle", + "Average \u2b06\ufe0f": 71.5, + "ARC": 68.52, + "HellaSwag": 87.22, + "MMLU": 64.53, + "TruthfulQA": 61.19, + "Winogrande": 80.51, + "GSM8K": 67.02, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68c3d77b047118b0b06b1540f1536ae368273084", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "sethuiyer\/Nandine-7b", @@ -16170,6 +23254,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/14B-Glacier-Stack", + "Average \u2b06\ufe0f": 71.47, + "ARC": 71.67, + "HellaSwag": 88.35, + "MMLU": 66.73, + "TruthfulQA": 65.37, + "Winogrande": 84.06, + "GSM8K": 52.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "cf6f466d227c041df3b892dff394df43ecf99b8b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Azazelle\/Yuna-7b-Merge", @@ -16233,7 +23340,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "dd27a200fd3dd5500a0b5bbfc0e4a9289af486e5", "Flagged": false, @@ -16257,7 +23364,7 @@ "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "215cbefbc69d22c28181651b5b964c329ca09f59", "Flagged": false, "MoE": false @@ -16279,7 +23386,7 @@ "Merged": false, "Hub License": "wtfpl", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "2d6dcf8bf9f1a758f135929de4a6fd81e26a38da", "Flagged": false, @@ -16371,7 +23478,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.86, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "1055563879363d9ee2fba1d9fd1628eca6bcbb4e", "Flagged": false, @@ -16394,7 +23501,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.86, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "c8741ec6f4f24324a96041efaf2f627a99d946e6", "Flagged": false, @@ -16441,11 +23548,34 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "91f18df3f5c3d36f1293086113f810f662970449", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "mychen76\/mistral-7b-merged-ties", + "Average \u2b06\ufe0f": 71.37, + "ARC": 67.92, + "HellaSwag": 85.93, + "MMLU": 64.07, + "TruthfulQA": 61.31, + "Winogrande": 80.03, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36c42c61ff949d5dd0212611f77780a11e7346a9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Radu1999\/MisterUkrainianDPO", @@ -16509,7 +23639,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "5eab2c8ec1c079e53a60ebdb7811756c2faebd9b", "Flagged": false, @@ -16530,10 +23660,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 70.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "178d03ccf7e7f83019266396f326fe11382eb20a", "Flagged": false, "MoE": false @@ -16553,7 +23683,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "gpl", + "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -16578,7 +23708,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "29652406c24f9d369d6bfd1ecc4979b2ab124c08", "Flagged": false, @@ -16625,7 +23755,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "662c68ece38bcc8cb7b04dc2c0f5d6c03f8d56e0", "Flagged": false, "MoE": false @@ -16645,7 +23775,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -16739,7 +23869,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "e8bea52793d4ae58e0772918ea1727808565fc75", "Flagged": false, @@ -16829,14 +23959,37 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b75cf49b19d31ae6c4f8d2a6f3a1484d143024e0", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Nitral-AI\/Eris_PrimeV3.075-Vision-7B", + "Average \u2b06\ufe0f": 71.29, + "ARC": 68.26, + "HellaSwag": 86.44, + "MMLU": 64.9, + "TruthfulQA": 62.72, + "Winogrande": 81.06, + "GSM8K": 64.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1925727c03448e3930efe0b9491013667fcaab9d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "aqweteddy\/mistral_tv-neural-marconroni", @@ -16906,6 +24059,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-V3-BetaFlavour-7B", + "Average \u2b06\ufe0f": 71.25, + "ARC": 68.17, + "HellaSwag": 86.88, + "MMLU": 61.39, + "TruthfulQA": 72.92, + "Winogrande": 81.29, + "GSM8K": 56.86, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "606d81883116273cfc08a027cc454804e755c5d6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Q-bert\/MetaMath-Cybertron-Starling", @@ -16929,6 +24105,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Pigris-7b-v0.4", + "Average \u2b06\ufe0f": 71.23, + "ARC": 66.72, + "HellaSwag": 86.7, + "MMLU": 64.78, + "TruthfulQA": 55.8, + "Winogrande": 84.21, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3449a23360a0b8e5ccc014a667a95cd2563f9e08", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Riiid\/sheep-duck-llama-2-70b-v1.1", @@ -16946,12 +24145,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 19.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "978c3cc8d44ad37eb764a53e026ae1fa8d334eb2", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "kimou605\/shadow-clown-BioMistral-7B-DARE", + "Average \u2b06\ufe0f": 71.21, + "ARC": 67.41, + "HellaSwag": 86.78, + "MMLU": 64.07, + "TruthfulQA": 67.68, + "Winogrande": 81.61, + "GSM8K": 59.74, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "47b399337a8d0294a58ed27a343e9056af845925", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "APMIC\/caigun-lora-model-34B-v2", @@ -16989,15 +24211,38 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 15.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "cbd4f663365e40d50ed9834016bf840971b35db5", - "Flagged": true, + "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Bioxtral-4x7B-v0.1", + "Average \u2b06\ufe0f": 71.19, + "ARC": 68.34, + "HellaSwag": 87.27, + "MMLU": 63.57, + "TruthfulQA": 68.45, + "Winogrande": 82.87, + "GSM8K": 56.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "d0f47005d5b5b925e8a9de21d311ce278cf57eb7", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.4", @@ -17044,6 +24289,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-3.0-Yi-34B", + "Average \u2b06\ufe0f": 71.18, + "ARC": 64.59, + "HellaSwag": 85.61, + "MMLU": 75.98, + "TruthfulQA": 56.38, + "Winogrande": 83.5, + "GSM8K": 61.03, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "8c0a5ae12a331fe2709733331961ab433e4cec95", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "perlthoughts\/neural-chat-v3-3-8x7b-MoE", @@ -17081,11 +24349,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0c089098a27b01d577747f3071531a1a9c9d627c", "Flagged": false, "MoE": false @@ -17130,11 +24398,11 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "d5dbca5f010dd7a811e85597bcecdfd848c4ed25", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udcac", @@ -17196,7 +24464,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -17205,6 +24473,98 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/A0304", + "Average \u2b06\ufe0f": 71.13, + "ARC": 67.58, + "HellaSwag": 82.78, + "MMLU": 84.5, + "TruthfulQA": 53.35, + "Winogrande": 78.53, + "GSM8K": 60.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "48e7b56ee7e9454fed4d6729aad88cbe9c1e8a3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v18.1-32k", + "Average \u2b06\ufe0f": 71.13, + "ARC": 68.09, + "HellaSwag": 84.29, + "MMLU": 71.08, + "TruthfulQA": 56.74, + "Winogrande": 81.22, + "GSM8K": 65.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "98596b6731058cc9cca85f3b8ac9077342cb60ae", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/Experiment26-12B", + "Average \u2b06\ufe0f": 71.12, + "ARC": 68.86, + "HellaSwag": 88.59, + "MMLU": 63.75, + "TruthfulQA": 72.12, + "Winogrande": 83.43, + "GSM8K": 49.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "526040a085e68118e8ccea113c0776dcb0779f96", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/stealth-v1.3", + "Average \u2b06\ufe0f": 71.12, + "ARC": 67.49, + "HellaSwag": 86.74, + "MMLU": 64.45, + "TruthfulQA": 55.71, + "Winogrande": 80.74, + "GSM8K": 71.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f78122cb637ef0289bdb13c5d1b02a9fb6aa28da", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "NExtNewChattingAI\/shark_tank_ai_7_b", @@ -17228,6 +24588,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FredrikBL\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.09, + "ARC": 67.58, + "HellaSwag": 86.19, + "MMLU": 64.15, + "TruthfulQA": 59.84, + "Winogrande": 80.11, + "GSM8K": 68.69, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "acd7f60e7ce757dcbf0d97bd947378812b55e00b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "InnerI\/InnerILLM-7B-slerp", @@ -17251,6 +24634,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "AurelPx\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.09, + "ARC": 67.75, + "HellaSwag": 86.17, + "MMLU": 64.05, + "TruthfulQA": 59.85, + "Winogrande": 80.19, + "GSM8K": 68.54, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "71efe6e869f8983d99b0a1f525708480a73fd71c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "FredrikBL\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.09, + "ARC": 67.75, + "HellaSwag": 86.17, + "MMLU": 64.05, + "TruthfulQA": 59.85, + "Winogrande": 80.19, + "GSM8K": 68.54, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "acd7f60e7ce757dcbf0d97bd947378812b55e00b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mychen76\/mistral-7b-merged-slerp", + "Average \u2b06\ufe0f": 71.09, + "ARC": 67.75, + "HellaSwag": 86.17, + "MMLU": 64.05, + "TruthfulQA": 59.85, + "Winogrande": 80.19, + "GSM8K": 68.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f9a1661c70a8571c91023e09582c9c69f459a47c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Samee-ur\/NeuralPipe-7B-slerp", @@ -17274,6 +24726,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-2.0-Yi-34B", + "Average \u2b06\ufe0f": 71.09, + "ARC": 64.33, + "HellaSwag": 85.66, + "MMLU": 76.09, + "TruthfulQA": 55.3, + "Winogrande": 83.11, + "GSM8K": 62.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "145c52f944a1ddb7e70713ecea952b858617139f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "zhengr\/NeuralPipe-7B-slerp", @@ -17288,8 +24763,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -17383,7 +24858,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "d8d01fbb3aaefda39421850c2dabb38e73546a6e", "Flagged": false, @@ -17430,7 +24905,7 @@ "Hub License": "mit", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "fd04d89dac9f3fc8f8f43048c3fad3821b0fada6", "Flagged": false, "MoE": false @@ -17452,7 +24927,7 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "967dff56741850954a96491979995a4f686eeb05", "Flagged": false, @@ -17481,6 +24956,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/L0225", + "Average \u2b06\ufe0f": 71.04, + "ARC": 68.17, + "HellaSwag": 82.73, + "MMLU": 83.04, + "TruthfulQA": 54.19, + "Winogrande": 78.61, + "GSM8K": 59.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a9a394bdfa0ba89c60a6af94c0760dc92777c9b3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "gmonsoon\/OpenMia-Indo-Mistral-7b-v3", @@ -17519,13 +25017,13 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "gpl-3.0", "#Params (B)": 15.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "7658da56ac6e3dab2cc147b2e658c8ca892a0781", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", @@ -17552,7 +25050,7 @@ }, { "T": "\ud83d\udd36", - "Model": "mlabonne\/NeuralPipe-7B-slerp", + "Model": "DeepKarkhanis\/Mistral-Passthrough-8L-10B", "Average \u2b06\ufe0f": 71.01, "ARC": 67.58, "HellaSwag": 86.17, @@ -17567,15 +25065,15 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "16485f6a8d83061f67515bfe20ed5afe8218c993", + "Model sha": "8ebb167b4a27a9d49ec7399baf23eef6226c242d", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "DeepKarkhanis\/Mistral-Passthrough-8L-10B", + "Model": "DeepKarkhanis\/NeuralPipe-7B-slerp", "Average \u2b06\ufe0f": 71.01, "ARC": 67.58, "HellaSwag": 86.17, @@ -17592,13 +25090,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "8ebb167b4a27a9d49ec7399baf23eef6226c242d", + "Model sha": "6d45f7ca3e55658264d0b0a26b3ef98433335db0", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "DeepKarkhanis\/NeuralPipe-7B-slerp", + "Model": "mlabonne\/NeuralPipe-7B-slerp", "Average \u2b06\ufe0f": 71.01, "ARC": 67.58, "HellaSwag": 86.17, @@ -17613,9 +25111,9 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, - "Model sha": "6d45f7ca3e55658264d0b0a26b3ef98433335db0", + "Model sha": "16485f6a8d83061f67515bfe20ed5afe8218c993", "Flagged": false, "MoE": false }, @@ -17656,7 +25154,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -17682,7 +25180,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "a7c90fa652ca4b65f4e2db1126be0f884748b7ab", "Flagged": false, @@ -17705,7 +25203,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 158.0, + "Hub \u2764\ufe0f": 185.0, "Available on the hub": true, "Model sha": "1a61a6ff49be395db210a5867f02e04abb982971", "Flagged": false, @@ -17751,7 +25249,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 52.0, + "Hub \u2764\ufe0f": 54.0, "Available on the hub": true, "Model sha": "52feecf18e46dd8ed1db297345957007c3e45de1", "Flagged": false, @@ -17774,7 +25272,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.74, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "8a038d22e0d98c31619bb6b7a372b75eeba04d63", "Flagged": false, @@ -17797,7 +25295,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "d8d01fbb3aaefda39421850c2dabb38e73546a6e", "Flagged": false, @@ -17820,7 +25318,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": false, "Model sha": "f8a863749399d6a11898795bb485e721f42b6338", "Flagged": false, @@ -17844,7 +25342,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3929ff947202a530d89a2287e19873141a0136c5", "Flagged": false, "MoE": false @@ -17897,7 +25395,7 @@ }, { "T": "\ud83d\udd36", - "Model": "PulsarAI\/Draco-8x7B", + "Model": "Weyaxi\/Draco-8x7B", "Average \u2b06\ufe0f": 70.89, "ARC": 65.02, "HellaSwag": 85.24, @@ -17913,33 +25411,10 @@ "Hub License": "apache-2.0", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "c5747ec7ba9ca08eda4fd55ea32c67057db7b4d6", - "Flagged": true, - "MoE": true - }, - { - "T": "\ud83d\udd36", - "Model": "Weyaxi\/Draco-8x7B", - "Average \u2b06\ufe0f": 70.89, - "ARC": 65.02, - "HellaSwag": 85.24, - "MMLU": 64.96, - "TruthfulQA": 62.65, - "Winogrande": 80.66, - "GSM8K": 66.79, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MixtralForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", - "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "c5747ec7ba9ca08eda4fd55ea32c67057db7b4d6", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udcac", @@ -17964,6 +25439,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Nitral-AI\/Mika-Lelantacles-7b-Longtext", + "Average \u2b06\ufe0f": 70.86, + "ARC": 67.66, + "HellaSwag": 86.34, + "MMLU": 63.29, + "TruthfulQA": 70.15, + "Winogrande": 79.79, + "GSM8K": 57.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "8968ff13e35f884ef69c1239e8fecef4578c4abb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "rizla\/trrapi-16", @@ -17981,8 +25479,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, "Model sha": "fb8eee8952ec40b4165feb1a6c1dba3675ab6969", "Flagged": false, "MoE": false @@ -18050,8 +25548,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "06664239f5a4440eb71ab0892a7c03517d7da9dc", "Flagged": false, "MoE": false @@ -18079,29 +25577,6 @@ "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udfe2", - "Model": "01-ai\/Yi-34B-200K", - "Average \u2b06\ufe0f": 70.81, - "ARC": 65.36, - "HellaSwag": 85.58, - "MMLU": 76.06, - "TruthfulQA": 53.64, - "Winogrande": 82.56, - "GSM8K": 61.64, - "Type": "pretrained", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "other", - "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 226.0, - "Available on the hub": true, - "Model sha": "bb196389dbbfdf271b5564ce840027f8cd3386ef", - "Flagged": false, - "MoE": true - }, { "T": "\ud83e\udd1d", "Model": "Eric111\/MarcoHermes", @@ -18125,6 +25600,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "AbacusResearch\/Jallabi-34B", + "Average \u2b06\ufe0f": 70.73, + "ARC": 66.04, + "HellaSwag": 83.81, + "MMLU": 76.4, + "TruthfulQA": 51.46, + "Winogrande": 81.45, + "GSM8K": 65.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f3cefc6d178a7f61fc202f15dceedd041c2b6af8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Q-bert\/Terminis-7B", @@ -18165,7 +25663,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "706e71043ed40e53bfee7f25a3f2b4a8def36ae8", "Flagged": false, @@ -18188,7 +25686,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "7bab67e479c192927c4a781efdf5be27eaa315a8", "Flagged": false, @@ -18263,6 +25761,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "vishnukv\/speechless-mistral-dolphin-orca-platypus-samantha-WestSeverusJaskier-7b", + "Average \u2b06\ufe0f": 70.67, + "ARC": 68.0, + "HellaSwag": 86.56, + "MMLU": 64.92, + "TruthfulQA": 59.9, + "Winogrande": 80.66, + "GSM8K": 63.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "44a51e1f89f22c1b3962ae75e24d35a5c3c345fa", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "chargoddard\/internlm2-20b-llama", @@ -18280,7 +25801,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 19.86, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "acf3dfe237a34a1898f57787d531b86497e96777", "Flagged": false, @@ -18307,7 +25828,7 @@ "Available on the hub": false, "Model sha": "5fd0b772372a0d908279db56c5bec064e842e029", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udfe2", @@ -18326,7 +25847,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 19.86, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "acf3dfe237a34a1898f57787d531b86497e96777", "Flagged": false, @@ -18396,7 +25917,7 @@ "Hub License": "?", "#Params (B)": 70.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6a2ddfb2ddde603dae91420db019682378aa9d5e", "Flagged": false, "MoE": false @@ -18424,6 +25945,29 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "dreamgen\/opus-v1-34b", + "Average \u2b06\ufe0f": 70.57, + "ARC": 64.33, + "HellaSwag": 84.9, + "MMLU": 75.43, + "TruthfulQA": 55.92, + "Winogrande": 81.29, + "GSM8K": 61.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "4dc3e88bf59b74391c7e31e30921b7c56bdc5a40", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "DrNicefellow\/ChatAllInOne-Yi-34B-200K-V1", @@ -18441,7 +25985,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "d3fb17cdd012a7d532a49adaf798203c6524908d", "Flagged": false, @@ -18464,7 +26008,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "d3fb17cdd012a7d532a49adaf798203c6524908d", "Flagged": false, @@ -18487,7 +26031,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "7bab67e479c192927c4a781efdf5be27eaa315a8", "Flagged": false, @@ -18507,7 +26051,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, @@ -18533,7 +26077,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 68.0, + "Hub \u2764\ufe0f": 76.0, "Available on the hub": true, "Model sha": "a305e828aa2ef0f547e7037edf14bda54b78b210", "Flagged": true, @@ -18564,7 +26108,7 @@ }, { "T": "\ud83e\udd1d", - "Model": "giraffe176\/Open_Maid_Samantha_Hermes_Orca_dare_ties", + "Model": "giraffe176\/Open_Hermes_Maid_Sam_Mistral_dtv0.1", "Average \u2b06\ufe0f": 70.53, "ARC": 67.75, "HellaSwag": 86.39, @@ -18576,18 +26120,18 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "f124dfbc767e7ece3fe5f209a0768e69d8024290", + "Model sha": "a141139153dc0804e288e951fb7e777783872946", "Flagged": false, "MoE": false }, { "T": "\ud83e\udd1d", - "Model": "giraffe176\/Open_Hermes_Maid_Sam_Mistral_dtv0.1", + "Model": "giraffe176\/Open_Maid_Samantha_Hermes_Orca_dare_ties", "Average \u2b06\ufe0f": 70.53, "ARC": 67.75, "HellaSwag": 86.39, @@ -18599,12 +26143,12 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "a141139153dc0804e288e951fb7e777783872946", + "Model sha": "f124dfbc767e7ece3fe5f209a0768e69d8024290", "Flagged": false, "MoE": false }, @@ -18623,7 +26167,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -18694,7 +26238,7 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "b3767a69eb9b36aba96be586958391c45b695ff4", "Flagged": false, @@ -18717,7 +26261,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 68.0, + "Hub \u2764\ufe0f": 76.0, "Available on the hub": true, "Model sha": "a305e828aa2ef0f547e7037edf14bda54b78b210", "Flagged": true, @@ -18806,7 +26350,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -18815,6 +26359,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AetherResearch\/Cerebrum-1.0-8x7b", + "Average \u2b06\ufe0f": 70.47, + "ARC": 68.09, + "HellaSwag": 87.3, + "MMLU": 72.45, + "TruthfulQA": 50.63, + "Winogrande": 82.4, + "GSM8K": 61.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 78.0, + "Available on the hub": true, + "Model sha": "590311de11895f6f9b4d8615b473808f919bef84", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "Swisslex\/Mixtral-8x7b-DPO-v0.1", @@ -18853,10 +26420,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 10.95, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f9457027c05107889a948a6f3b99ba428e859d48", "Flagged": false, "MoE": false @@ -18875,7 +26442,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, @@ -18907,6 +26474,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/MistInst-v0.2_ochat-3.5-0106_dpo-binarized-NeuralTrix-7B", + "Average \u2b06\ufe0f": 70.42, + "ARC": 69.71, + "HellaSwag": 85.86, + "MMLU": 61.23, + "TruthfulQA": 67.93, + "Winogrande": 82.08, + "GSM8K": 55.72, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ff7df93a5285be5c58bd8e70fcff2757903ea6c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "DreadPoor\/BagelLake-7B-slerp", @@ -18921,7 +26511,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -18953,6 +26543,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "dreamgen\/opus-v1-34b", + "Average \u2b06\ufe0f": 70.39, + "ARC": 64.42, + "HellaSwag": 84.85, + "MMLU": 75.38, + "TruthfulQA": 55.88, + "Winogrande": 81.61, + "GSM8K": 60.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "4dc3e88bf59b74391c7e31e30921b7c56bdc5a40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Sinerva_7B", + "Average \u2b06\ufe0f": 70.38, + "ARC": 70.14, + "HellaSwag": 85.59, + "MMLU": 61.77, + "TruthfulQA": 59.93, + "Winogrande": 82.56, + "GSM8K": 62.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "2193384d58f41418087998167cf6ec20c76582b0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "openagi-project\/OpenAGI-7B-v0.2", @@ -18976,6 +26612,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/FrankeMerge-12.5B", + "Average \u2b06\ufe0f": 70.36, + "ARC": 68.34, + "HellaSwag": 87.74, + "MMLU": 64.01, + "TruthfulQA": 66.88, + "Winogrande": 81.53, + "GSM8K": 53.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f0df5e0045003efaf87c1cb4d7016e6641a251df", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Test157t\/Prima-Pastacles-7b-128k", @@ -18993,7 +26652,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "1be449dd843bcc1c9a1bdf4d2e3f506ddd189c10", "Flagged": false, @@ -19046,8 +26705,8 @@ "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "openagi-project\/OpenAGI-7B-v0.1", + "T": "\ud83d\udd36", + "Model": "openagi-project\/OpenAGI-7B-v0.1-test-ada", "Average \u2b06\ufe0f": 70.34, "ARC": 66.72, "HellaSwag": 86.13, @@ -19055,22 +26714,22 @@ "TruthfulQA": 69.55, "Winogrande": 79.48, "GSM8K": 56.63, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "unknown", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "36123d69a4dc871fe962337e997c5c5ccf6e739b", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "635f0d8e3bc9fe0c5fb3954614cef0a324d0bfc8", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "openagi-project\/OpenAGI-7B-v0.1-test-ada", + "T": "\ud83d\udcac", + "Model": "openagi-project\/OpenAGI-7B-v0.1", "Average \u2b06\ufe0f": 70.34, "ARC": 66.72, "HellaSwag": 86.13, @@ -19078,16 +26737,16 @@ "TruthfulQA": 69.55, "Winogrande": 79.48, "GSM8K": 56.63, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "unknown", + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, - "Model sha": "635f0d8e3bc9fe0c5fb3954614cef0a324d0bfc8", + "Model sha": "36123d69a4dc871fe962337e997c5c5ccf6e739b", "Flagged": false, "MoE": false }, @@ -19116,7 +26775,7 @@ }, { "T": "\ud83d\udd36", - "Model": "YeungNLP\/firefly-mixtral-8x7b-v0.1", + "Model": "YeungNLP\/firefly-mixtral-8x7b-v1", "Average \u2b06\ufe0f": 70.34, "ARC": 68.09, "HellaSwag": 85.76, @@ -19132,14 +26791,14 @@ "Hub License": "?", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "30abf8de36252c1e026fe758b8fde5eba960cd2a", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "YeungNLP\/firefly-mixtral-8x7b-v1", + "Model": "YeungNLP\/firefly-mixtral-8x7b-v0.1", "Average \u2b06\ufe0f": 70.34, "ARC": 68.09, "HellaSwag": 85.76, @@ -19155,7 +26814,7 @@ "Hub License": "?", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "30abf8de36252c1e026fe758b8fde5eba960cd2a", "Flagged": false, "MoE": false @@ -19177,7 +26836,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "b2e3c235196ba859b26ee14fb8c86e632bcf3e88", "Flagged": true, @@ -19201,7 +26860,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "58eb22fb92d6dfed4c0b582f1dd4573cdf7cca4a", "Flagged": false, "MoE": false @@ -19270,7 +26929,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5c19bc74d2b01b36a96e1287103bf56be3e6ad03", "Flagged": false, "MoE": false @@ -19315,7 +26974,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "9f17f1c66209dd923751a5242f33f0dfded9071f", "Flagged": false, @@ -19338,12 +26997,35 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 63.0, + "Hub \u2764\ufe0f": 75.0, "Available on the hub": true, "Model sha": "ecb260368921c5dfe16c007e871d29de9d561996", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Asherah_7B", + "Average \u2b06\ufe0f": 70.31, + "ARC": 68.17, + "HellaSwag": 86.05, + "MMLU": 63.92, + "TruthfulQA": 58.07, + "Winogrande": 78.77, + "GSM8K": 66.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "0eba35e22c2aafd69d14bf7e41c3f201eb6bcc3b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "chanwit\/flux-7b-v0.2", @@ -19384,12 +27066,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "136e3467ffdc6d44ac2d48a35f874238022b9040", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "froggeric\/WestLake-10.7B-v2", + "Average \u2b06\ufe0f": 70.28, + "ARC": 71.16, + "HellaSwag": 87.93, + "MMLU": 63.81, + "TruthfulQA": 64.91, + "Winogrande": 85.4, + "GSM8K": 48.45, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "de1f0f286ef6d5a6e10627ac05f8cfb9baaa36a5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "APMIC\/caigun-lora-model-34B-v3", @@ -19496,7 +27201,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -19551,6 +27256,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ChaoticNeutrals\/InfinityNexus_9B", + "Average \u2b06\ufe0f": 70.23, + "ARC": 68.69, + "HellaSwag": 86.28, + "MMLU": 64.49, + "TruthfulQA": 65.14, + "Winogrande": 80.82, + "GSM8K": 55.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "bf9b2d78febb994f4dd12ff870a2b2da265cc379", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Mihaiii\/Pallas-0.5", @@ -19592,7 +27320,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "dcc6fff61bfd608d8e14a040dff22cd8dae78b1e", "Flagged": false, "MoE": false @@ -19638,14 +27366,37 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "41612eecf338ae2b1cbb63a3729ce7b125c6ca3c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "grimjim\/kukulemon-7B", + "Average \u2b06\ufe0f": 70.2, + "ARC": 67.75, + "HellaSwag": 86.1, + "MMLU": 65.09, + "TruthfulQA": 61.99, + "Winogrande": 79.24, + "GSM8K": 61.03, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "80098e3132e20702cd33c049c47cfee6a26fa32c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "PulsarAI\/OpenHermes-2.5-neural-chat-v3-2-Slerp", + "Model": "Weyaxi\/OpenHermes-2.5-neural-chat-v3-2-Slerp", "Average \u2b06\ufe0f": 70.2, "ARC": 67.49, "HellaSwag": 85.42, @@ -19657,10 +27408,10 @@ "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "bf9ef6df7732dbef3cd0001d9e5cba846cb47306", "Flagged": false, @@ -19680,8 +27431,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -19706,7 +27457,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "219c9d65843f4c7356e5efffe399a7208e0dea25", "Flagged": false, @@ -19729,7 +27480,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "29751a19842fd9cae038b120dc77793b63cda663", "Flagged": false, @@ -19749,7 +27500,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -19758,6 +27509,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "invalid-coder\/Starling-LM-7B-beta-laser-dpo", + "Average \u2b06\ufe0f": 70.14, + "ARC": 67.41, + "HellaSwag": 83.38, + "MMLU": 65.29, + "TruthfulQA": 55.47, + "Winogrande": 81.37, + "GSM8K": 67.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af46d93b801339a18c70948867793e29b7b9eedb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "JaeyeonKang\/CCK_Gony_v0.2", @@ -19779,7 +27553,30 @@ "Available on the hub": false, "Model sha": "ec7ea7c16e1a8b5968cab37aab70d926c8ec341d", "Flagged": false, - "MoE": true + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Stopwolf\/Tito-7B-slerp", + "Average \u2b06\ufe0f": 70.13, + "ARC": 68.09, + "HellaSwag": 86.38, + "MMLU": 64.01, + "TruthfulQA": 57.01, + "Winogrande": 81.69, + "GSM8K": 63.61, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d19cb51fa509b97ba0e2d49bc24a9a23e2885c19", + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -19795,13 +27592,13 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "27d3bd02299580f326cc358d6d98e06a950d937e", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -19845,7 +27642,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "111ae8b3fb38d550a32f04dbd977f8cd447a3a92", "Flagged": false, "MoE": false @@ -19890,7 +27687,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 250.0, + "Hub \u2764\ufe0f": 252.0, "Available on the hub": false, "Model sha": "5f9c77b2c0397cf83d2f97740483f107c7109e8c", "Flagged": false, @@ -19919,6 +27716,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/HighdensityRPMerge-7B", + "Average \u2b06\ufe0f": 70.1, + "ARC": 67.41, + "HellaSwag": 86.58, + "MMLU": 64.73, + "TruthfulQA": 60.44, + "Winogrande": 79.4, + "GSM8K": 62.02, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68c41dda197602fa34f48f472f7e1aebf53ac609", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Prima-LelantaclesV6.5-7b", + "Average \u2b06\ufe0f": 70.09, + "ARC": 67.75, + "HellaSwag": 85.7, + "MMLU": 63.12, + "TruthfulQA": 62.12, + "Winogrande": 82.48, + "GSM8K": 59.36, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0c7a9a7b9e86a8662660e76f30a63f10a7dae4ef", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "DreadPoor\/Westuccine-7B-slerp", @@ -20028,7 +27871,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 23.0, "Available on the hub": true, "Model sha": "7f089b13e3345510281733ca1e6ff871b5b4bc76", "Flagged": false, @@ -20098,7 +27941,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cac4a2663504ccf1ca8975787a4b99df50b68bd1", "Flagged": false, "MoE": false @@ -20190,7 +28033,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "56f4a9b2f7fcc6891536de338fdb4b302a1fbcfa", "Flagged": false, "MoE": false @@ -20218,6 +28061,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/WestLake_Noromaid_OpenHermes_neural-chat", + "Average \u2b06\ufe0f": 70.0, + "ARC": 67.58, + "HellaSwag": 86.13, + "MMLU": 64.72, + "TruthfulQA": 55.47, + "Winogrande": 80.43, + "GSM8K": 65.66, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f843090d889645a22e61fbb7bbae7a92fc76812f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Inv\/MoeMoE-2x7b", + "Average \u2b06\ufe0f": 69.98, + "ARC": 66.47, + "HellaSwag": 84.31, + "MMLU": 62.7, + "TruthfulQA": 61.65, + "Winogrande": 79.87, + "GSM8K": 64.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b245e28566d675a5b2d269aa4daba80ecb9bc548", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Code-Mistral-7B", + "Average \u2b06\ufe0f": 69.97, + "ARC": 64.59, + "HellaSwag": 85.29, + "MMLU": 65.0, + "TruthfulQA": 54.64, + "Winogrande": 82.24, + "GSM8K": 68.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "ed3b9ad583910423a7b82e27274681e3865206f1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "flemmingmiguel\/Mistrality-7B", @@ -20258,7 +28170,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 11.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "cb2392b7d1913ea071c56ba4224966c70109a3c2", "Flagged": false, @@ -20310,6 +28222,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "GritLM\/GritLM-8x7B", + "Average \u2b06\ufe0f": 69.93, + "ARC": 67.75, + "HellaSwag": 86.52, + "MMLU": 71.42, + "TruthfulQA": 49.47, + "Winogrande": 82.79, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "7f089b13e3345510281733ca1e6ff871b5b4bc76", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp", @@ -20356,6 +28291,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "LeroyDyer\/Mixtral_AI_Cyber_3.m2", + "Average \u2b06\ufe0f": 69.89, + "ARC": 67.41, + "HellaSwag": 86.88, + "MMLU": 63.9, + "TruthfulQA": 64.62, + "Winogrande": 80.35, + "GSM8K": 56.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1fa9aabfcbeccf98bca82ab29e20bd584f862c8", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "Mihaiii\/Pallas-0.3", @@ -20402,6 +28360,75 @@ "Flagged": true, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Nexusflow\/Starling-LM-7B-beta", + "Average \u2b06\ufe0f": 69.88, + "ARC": 67.24, + "HellaSwag": 83.47, + "MMLU": 65.14, + "TruthfulQA": 55.47, + "Winogrande": 81.29, + "GSM8K": 66.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 212.0, + "Available on the hub": true, + "Model sha": "ee26b7c2cf9db00e1d9a92c9989d5b2a0b891dbd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Salesforce\/xLAM-v0.1-r", + "Average \u2b06\ufe0f": 69.88, + "ARC": 67.58, + "HellaSwag": 84.59, + "MMLU": 69.95, + "TruthfulQA": 57.77, + "Winogrande": 80.98, + "GSM8K": 58.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "68d5e8b311745400d926f6143e1ac3ff5c449a4d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SherlockAssistant\/Mistral-7B-Instruct-Ukrainian", + "Average \u2b06\ufe0f": 69.87, + "ARC": 67.41, + "HellaSwag": 85.81, + "MMLU": 62.87, + "TruthfulQA": 64.95, + "Winogrande": 81.85, + "GSM8K": 56.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "44524f02c0ca97e34c6610cbd7d28ef153e54437", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "kyujinpy\/PlatYi-34B-Q", @@ -20442,12 +28469,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 51.0, + "Hub \u2764\ufe0f": 58.0, "Available on the hub": true, "Model sha": "fac83ab297a1c9ecc8affd97c998d864c10b9ff4", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ResplendentAI\/Persephone_7B", + "Average \u2b06\ufe0f": 69.83, + "ARC": 66.72, + "HellaSwag": 85.59, + "MMLU": 63.23, + "TruthfulQA": 67.51, + "Winogrande": 82.32, + "GSM8K": 53.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "0a920569f922d3c900364947e381c046a8d0674d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "perlthoughts\/Chupacabra-7B-v2.02", @@ -20510,13 +28560,59 @@ "Precision": "float16", "Merged": false, "Hub License": "?", - "#Params (B)": 0.7, + "#Params (B)": 10.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9e439597e3e788e3ff8a41df54e0dae0acda14a4", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "localfultonextractor\/Erosumika-7B-v3", + "Average \u2b06\ufe0f": 69.8, + "ARC": 67.49, + "HellaSwag": 85.69, + "MMLU": 64.15, + "TruthfulQA": 62.12, + "Winogrande": 82.79, + "GSM8K": 56.56, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d80884197f744524ba44fb587944e7bde053e249", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jeiku\/Eros_Prodigadigm_7B", + "Average \u2b06\ufe0f": 69.8, + "ARC": 67.24, + "HellaSwag": 85.63, + "MMLU": 63.04, + "TruthfulQA": 68.68, + "Winogrande": 80.9, + "GSM8K": 53.3, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "50598e1c289866d0937eb789d1543414e67814f3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Tess-M-v1.1", @@ -20563,6 +28659,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "icefog72\/IceTeaRP-7b", + "Average \u2b06\ufe0f": 69.76, + "ARC": 66.98, + "HellaSwag": 86.13, + "MMLU": 63.97, + "TruthfulQA": 62.44, + "Winogrande": 78.85, + "GSM8K": 60.2, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "a6178e04aa616fcd6fc8c10ac8c2a7b5991731ae", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "internlm\/internlm2-20b", @@ -20580,12 +28699,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 30.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": true, "Model sha": "ec0e34824038c66745ba035f5c1994bd8cb99574", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "seyf1elislam\/WestKunai-Hermes-10.7b-test", + "Average \u2b06\ufe0f": 69.75, + "ARC": 68.09, + "HellaSwag": 87.1, + "MMLU": 64.43, + "TruthfulQA": 64.28, + "Winogrande": 82.72, + "GSM8K": 51.86, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "76887e42e7d48d55de29561b1306e1fe0d308466", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-l2-70b-3.1.2", @@ -20626,12 +28768,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "0c2f691bda2d1131ef87767ccf47ba7560578c48", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/ChatHercules-2.5-Mistral-7B-DPO", + "Average \u2b06\ufe0f": 69.73, + "ARC": 66.04, + "HellaSwag": 85.4, + "MMLU": 65.17, + "TruthfulQA": 52.3, + "Winogrande": 81.93, + "GSM8K": 67.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "db11ab2310f79a2f1edc4e71c64a63462e65c8e5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/MathDolphin-7B", @@ -20646,8 +28811,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -20655,6 +28820,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Nitral-AI\/Prima-LelantaclesV7-experimentalv2-7b", + "Average \u2b06\ufe0f": 69.72, + "ARC": 68.09, + "HellaSwag": 85.87, + "MMLU": 62.87, + "TruthfulQA": 68.14, + "Winogrande": 81.14, + "GSM8K": 52.24, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d420ef8df86709571c0485d3eae6d116e4dabd3d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "rishiraj\/oswald-4x7b", @@ -20669,14 +28857,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 24.15, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "1a2a1c2a7cb0d18ae4af77f99a7adbe8d9718f92", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -20741,12 +28929,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 35.0, "Available on the hub": true, "Model sha": "bc599b31f468d46d873964a58cab78380366d934", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Kool-Aid_7B", + "Average \u2b06\ufe0f": 69.69, + "ARC": 67.49, + "HellaSwag": 86.13, + "MMLU": 63.82, + "TruthfulQA": 65.12, + "Winogrande": 81.37, + "GSM8K": 54.21, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "6ab7387d794bc8f1a8da2091b6d2b46739d41bb3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "viethq188\/Rabbit-7B-DPO-Chat", @@ -20810,7 +29021,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 115.0, + "Hub \u2764\ufe0f": 117.0, "Available on the hub": true, "Model sha": "82599694771bd375c91f36dfdf30c448e4e33b3c", "Flagged": false, @@ -20923,7 +29134,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -20954,6 +29165,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "icefog72\/Kunokukulemonchini-7b", + "Average \u2b06\ufe0f": 69.61, + "ARC": 66.72, + "HellaSwag": 86.31, + "MMLU": 64.11, + "TruthfulQA": 61.89, + "Winogrande": 78.45, + "GSM8K": 60.2, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "fd534d80a67d0959c0f42be982dc937d451b86c4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Steelskull\/Lumosia-MoE-4x10.7", @@ -20998,7 +29232,7 @@ "Available on the hub": false, "Model sha": "cb62ef5613e162437a0803cddabc50e21437cd1b", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -21109,7 +29343,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "3ebea1710b555a205a04e69c743fe90162df63c9", "Flagged": false, @@ -21138,6 +29372,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/A0306", + "Average \u2b06\ufe0f": 69.57, + "ARC": 66.04, + "HellaSwag": 83.47, + "MMLU": 80.04, + "TruthfulQA": 53.05, + "Winogrande": 78.22, + "GSM8K": 56.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d869c99f5b2b456a483bca7d6cc1ec7f797cdbf1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/WizardDolphin-7B", @@ -21161,6 +29418,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FoxEngineAi\/Mega-Destroyer-8x7B", + "Average \u2b06\ufe0f": 69.54, + "ARC": 71.76, + "HellaSwag": 86.47, + "MMLU": 70.11, + "TruthfulQA": 72.12, + "Winogrande": 82.79, + "GSM8K": 33.97, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "d257c7bb089eaf791f0c1fba83a4029ccead5544", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udfe2", "Model": "Weyaxi\/Qwen-72B-Llama", @@ -21178,7 +29458,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "e94ac9684f607c71f443b7098c434b543cc62fd6", "Flagged": false, @@ -21199,7 +29479,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -21207,6 +29487,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Smaug-2-72B", + "Average \u2b06\ufe0f": 69.51, + "ARC": 67.92, + "HellaSwag": 86.37, + "MMLU": 77.73, + "TruthfulQA": 64.9, + "Winogrande": 81.61, + "GSM8K": 38.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1454e0e3e2dea0db430612b9558852e3e5793021", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_38-7B-dare_ties", + "Average \u2b06\ufe0f": 69.5, + "ARC": 71.67, + "HellaSwag": 86.35, + "MMLU": 58.3, + "TruthfulQA": 73.14, + "Winogrande": 82.0, + "GSM8K": 45.56, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f07d11120ff39e698cf808e617f01860ebaa2085", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Kquant03\/CognitiveFusion-4x7B-bf16-MoE", @@ -21313,8 +29639,8 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -21362,7 +29688,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "56805ed2f93e991f77fa6dd83502daf96aff2c9d", "Flagged": false, @@ -21391,6 +29717,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "tushar310\/MisGemma-7B", + "Average \u2b06\ufe0f": 69.45, + "ARC": 66.89, + "HellaSwag": 85.73, + "MMLU": 64.44, + "TruthfulQA": 62.22, + "Winogrande": 79.16, + "GSM8K": 58.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2f70f12276927c719b379176909f75fba4725ccd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tushar310\/MisGemma-7B", + "Average \u2b06\ufe0f": 69.44, + "ARC": 66.89, + "HellaSwag": 85.7, + "MMLU": 64.48, + "TruthfulQA": 62.22, + "Winogrande": 79.48, + "GSM8K": 57.85, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2f70f12276927c719b379176909f75fba4725ccd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "MisterRid\/saulgoodman-2x7b-alpha1", @@ -21431,12 +29803,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 1187.0, + "Hub \u2764\ufe0f": 1219.0, "Available on the hub": true, "Model sha": "cd8d59de87ea11c6453ee287ac82e5523f08c8ec", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "openchat\/openchat-3.5-0106-gemma", + "Average \u2b06\ufe0f": 69.42, + "ARC": 64.68, + "HellaSwag": 81.08, + "MMLU": 64.69, + "TruthfulQA": 54.93, + "Winogrande": 78.3, + "GSM8K": 72.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 44.0, + "Available on the hub": true, + "Model sha": "8f5401b27731fb289132eea40740fc834c9678c7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "adamo1139\/yi-34b-200k-rawrr-dpo-2", @@ -21477,7 +29872,7 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "136d8ad5d94b8ac02ac7cd4e0b32e09366a550dc", "Flagged": false, @@ -21497,14 +29892,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "50fa192492461fdfcd8ce1c84e9081891141a5ac", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -21546,7 +29941,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "c417af695d4e3370348e2ef15961884f127f7ff0", "Flagged": false, @@ -21592,7 +29987,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 67.0, - "Hub \u2764\ufe0f": 97.0, + "Hub \u2764\ufe0f": 99.0, "Available on the hub": true, "Model sha": "c3f813a1121c95488a20132d3a4da89f4a46452f", "Flagged": false, @@ -21638,7 +30033,7 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "32612e89aa87a23f6b1c5c5a9165896e599ca9ca", "Flagged": false, @@ -21659,7 +30054,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -21690,6 +30085,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cstr\/Spaetzle-v12-7b", + "Average \u2b06\ufe0f": 69.36, + "ARC": 65.96, + "HellaSwag": 86.16, + "MMLU": 63.48, + "TruthfulQA": 57.84, + "Winogrande": 80.03, + "GSM8K": 62.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f4c2a23da2edce2deb7c81ef615ec35d053b7353", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "freecs\/ThetaWave-7B", @@ -21705,7 +30123,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -21759,6 +30177,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Stopwolf\/Bumbar-7B-slerp", + "Average \u2b06\ufe0f": 69.34, + "ARC": 66.21, + "HellaSwag": 83.96, + "MMLU": 63.98, + "TruthfulQA": 57.81, + "Winogrande": 80.03, + "GSM8K": 64.06, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "40cc5f6decc0c4ada02708123d1d2a15d8cdfd7b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mayacinka\/West-Ramen-7Bx4", + "Average \u2b06\ufe0f": 69.33, + "ARC": 67.58, + "HellaSwag": 85.52, + "MMLU": 62.69, + "TruthfulQA": 61.0, + "Winogrande": 81.22, + "GSM8K": 58.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bc62dcbb054c7b6368d85eda9f2d41750e4d69f9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "gagan3012\/MetaModel_moe_multilingualv1", @@ -21799,15 +30263,15 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "533506a750975d612071ab9a56e076d65e65cef4", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "CallComply\/openchat-3.5-0106-32k", + "T": "\ud83d\udcac", + "Model": "openchat\/openchat-3.5-0106", "Average \u2b06\ufe0f": 69.3, "ARC": 66.04, "HellaSwag": 82.93, @@ -21815,16 +30279,16 @@ "TruthfulQA": 51.9, "Winogrande": 81.77, "GSM8K": 68.16, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 294.0, "Available on the hub": true, - "Model sha": "8d566086308e80e8aa01e70acfac10adcf457fe3", + "Model sha": "9619fb7d2a8e25fa6b0633c0f57f7f4aa79b45c4", "Flagged": false, "MoE": false }, @@ -21843,7 +30307,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -21852,8 +30316,8 @@ "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "openchat\/openchat-3.5-0106", + "T": "\ud83d\udd36", + "Model": "CallComply\/openchat-3.5-0106-32k", "Average \u2b06\ufe0f": 69.3, "ARC": 66.04, "HellaSwag": 82.93, @@ -21861,16 +30325,16 @@ "TruthfulQA": 51.9, "Winogrande": 81.77, "GSM8K": 68.16, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 209.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, - "Model sha": "9619fb7d2a8e25fa6b0633c0f57f7f4aa79b45c4", + "Model sha": "8d566086308e80e8aa01e70acfac10adcf457fe3", "Flagged": false, "MoE": false }, @@ -21897,6 +30361,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "saucam\/mistral-orpo-beta-NeuralBeagle14-7B-dare-ties", + "Average \u2b06\ufe0f": 69.3, + "ARC": 66.72, + "HellaSwag": 85.98, + "MMLU": 64.63, + "TruthfulQA": 53.87, + "Winogrande": 81.22, + "GSM8K": 63.38, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3fb5752c0b99378f10e5a9ad1ccdd236a4214479", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "adamo1139\/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3", @@ -21920,6 +30407,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/Open_Neural_Monarch_Maidv0.1", + "Average \u2b06\ufe0f": 69.28, + "ARC": 67.66, + "HellaSwag": 85.94, + "MMLU": 65.02, + "TruthfulQA": 56.39, + "Winogrande": 79.32, + "GSM8K": 61.33, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e0059b9618a5481808e5bec3b45b6bf572dcc629", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/Mistral-7B-Instruct_v0.2_UNA-TheBeagle-7b-v1", + "Average \u2b06\ufe0f": 69.27, + "ARC": 67.83, + "HellaSwag": 85.94, + "MMLU": 61.94, + "TruthfulQA": 65.64, + "Winogrande": 80.35, + "GSM8K": 53.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6888db1edc8185a9ba876c8ca2438d3aea28d6aa", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "andysalerno\/openchat-nectar-0.8", @@ -21966,6 +30499,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "vishnukv\/WestSeverusJaskier-OpenOrca", + "Average \u2b06\ufe0f": 69.24, + "ARC": 62.88, + "HellaSwag": 84.75, + "MMLU": 64.33, + "TruthfulQA": 53.9, + "Winogrande": 82.48, + "GSM8K": 67.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "109379e69b45018360e565fde8cced5a948d4151", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "fhai50032\/BeagleLake-7B-Toxic", @@ -22012,6 +30568,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_41-7B-dare_ties", + "Average \u2b06\ufe0f": 69.23, + "ARC": 65.61, + "HellaSwag": 85.7, + "MMLU": 64.57, + "TruthfulQA": 58.02, + "Winogrande": 81.06, + "GSM8K": 60.42, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "20109bbcd1080e4d95c450815b931bc383bd64df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "weezywitasneezy\/OxytocinErosEngineeringF1-7B-slerp", + "Average \u2b06\ufe0f": 69.22, + "ARC": 67.15, + "HellaSwag": 86.0, + "MMLU": 64.73, + "TruthfulQA": 54.54, + "Winogrande": 81.14, + "GSM8K": 61.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "18bf5bd14ddaa0484952e2972959df2bc5f7b871", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "DreadPoor\/BagelToppyLake-7B-slerp", @@ -22030,11 +30632,57 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "291f0e17b1322c7fb10e770f0febc15216beab29", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/KunoMaid-7B-slerp", + "Average \u2b06\ufe0f": 69.21, + "ARC": 68.0, + "HellaSwag": 86.34, + "MMLU": 64.82, + "TruthfulQA": 55.19, + "Winogrande": 79.24, + "GSM8K": 61.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e99b0cab99c6ab176b7a89831c9a1b8977d7eeeb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AGI-0\/ThetaWave-7B-v0.1", + "Average \u2b06\ufe0f": 69.2, + "ARC": 65.96, + "HellaSwag": 85.72, + "MMLU": 63.07, + "TruthfulQA": 63.27, + "Winogrande": 81.53, + "GSM8K": 55.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "59b71b909b172d247b3bb27ed674172dd1302c44", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "LHC88\/LaseredHermes-7B-v1", @@ -22073,7 +30721,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -22101,7 +30749,7 @@ "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "4518c1d85135efdb14ed8d3581d325ea2167d6b4", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -22257,10 +30905,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "other", "#Params (B)": 34.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3fbaa2965a16992f1e8cddbc0c9b40efd6f15698", "Flagged": false, "MoE": false @@ -22328,7 +30976,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "38da429cb28f667e8868574f32269a04dfe41280", "Flagged": false, @@ -22486,7 +31134,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -22559,7 +31207,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "daf6eee865b05b45a4ce61af906313a80de06a9d", "Flagged": false, "MoE": false @@ -22628,11 +31276,34 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "66dae63f92cac0c99b1b162383506b60ac060225", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "feeltheAGI\/Maverick-Math-7B", + "Average \u2b06\ufe0f": 69.05, + "ARC": 65.27, + "HellaSwag": 84.54, + "MMLU": 62.59, + "TruthfulQA": 55.97, + "Winogrande": 79.72, + "GSM8K": 66.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9ae5d1f286ec0148a077c75e4d201e85df305ae4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Test157t\/HerculeanSea-upd-7b-128k", @@ -22650,7 +31321,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "64c1b6cef98190b6a54d9718c18cb2dd3e9badcc", "Flagged": false, @@ -22674,7 +31345,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c1d4f997f8ed685a6efc72229523b2e56fd0774b", "Flagged": false, "MoE": false @@ -22858,11 +31529,57 @@ "Hub License": "mit", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "89b6a3be6c3b6a2fa729de466ec20153665359dd", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "uproai\/Rose-2x7B", + "Average \u2b06\ufe0f": 68.93, + "ARC": 65.27, + "HellaSwag": 85.7, + "MMLU": 64.37, + "TruthfulQA": 49.32, + "Winogrande": 79.79, + "GSM8K": 69.14, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f097d445ebb0edaeb1f2694806aa6da9b173a8a6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-PressurizedRuby-7B", + "Average \u2b06\ufe0f": 68.93, + "ARC": 66.89, + "HellaSwag": 85.4, + "MMLU": 63.33, + "TruthfulQA": 56.91, + "Winogrande": 78.77, + "GSM8K": 62.24, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6fb7d9e50848379564e66962e25fb1154c848c05", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cognitivecomputations\/MegaDolphin-120b", @@ -22880,7 +31597,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 120.32, - "Hub \u2764\ufe0f": 61.0, + "Hub \u2764\ufe0f": 65.0, "Available on the hub": true, "Model sha": "561d22376c354903641165d6691eb4df9405a4cf", "Flagged": false, @@ -22926,7 +31643,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 262.0, + "Hub \u2764\ufe0f": 270.0, "Available on the hub": true, "Model sha": "e5df841b685e5b5ca11ce142f29c6c731bf087a0", "Flagged": false, @@ -22996,7 +31713,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "87dac68765c899952d9d91ce827cda867d115c6f", "Flagged": false, "MoE": false @@ -23016,7 +31733,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -23047,6 +31764,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "giraffe176\/WestLake_Noromaid_OpenHermes_neural-chatv0.1", + "Average \u2b06\ufe0f": 68.86, + "ARC": 66.72, + "HellaSwag": 85.37, + "MMLU": 64.67, + "TruthfulQA": 51.5, + "Winogrande": 79.72, + "GSM8K": 65.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "087d5e79ae93abbc9d8c58d4bbaa61b3933761fc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Yuma42\/KangalKhan-SharpEmerald-7B", @@ -23088,7 +31828,7 @@ "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1b91227a0539deaf4dfb5b18d15c92316e0254c3", "Flagged": false, "MoE": false @@ -23116,6 +31856,29 @@ "Flagged": true, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "splm\/openchat-spin-slimorca-iter3", + "Average \u2b06\ufe0f": 68.85, + "ARC": 68.0, + "HellaSwag": 83.97, + "MMLU": 64.39, + "TruthfulQA": 59.0, + "Winogrande": 77.98, + "GSM8K": 59.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7fcc1c3ed549282789aeab73573b7ebc6262685c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "splm\/openchat-spin-slimorca-iter2", @@ -23180,7 +31943,7 @@ "Hub License": "?", "#Params (B)": 24.15, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1cc519b70e87de1c632a6dc98ac6383cf0dd994e", "Flagged": false, "MoE": true @@ -23203,11 +31966,34 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "55a30d29db194832c0b5de1392a6598a63582144", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-PolishedRuby-7B", + "Average \u2b06\ufe0f": 68.82, + "ARC": 66.72, + "HellaSwag": 85.39, + "MMLU": 63.21, + "TruthfulQA": 56.8, + "Winogrande": 78.61, + "GSM8K": 62.17, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cea9103397d28cf3d3c331adf8be43df4032f85e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Eurdem\/megatron_v1", @@ -23268,8 +32054,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "cc-by-nc-4.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -23295,7 +32081,7 @@ "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1b91227a0539deaf4dfb5b18d15c92316e0254c3", "Flagged": false, "MoE": false @@ -23317,12 +32103,58 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "aed9ff4b3edc3ed0672de35551dc750ea8fbac3b", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/correction_1", + "Average \u2b06\ufe0f": 68.8, + "ARC": 71.16, + "HellaSwag": 88.59, + "MMLU": 63.51, + "TruthfulQA": 65.92, + "Winogrande": 87.85, + "GSM8K": 35.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4d4603c9d0c91f84b15e6e62e5f2a1df4837763b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/Snorkel-Mistral-PairRM-DPO-openchat-3.5-0106-laser", + "Average \u2b06\ufe0f": 68.8, + "ARC": 67.32, + "HellaSwag": 85.11, + "MMLU": 63.23, + "TruthfulQA": 61.69, + "Winogrande": 79.87, + "GSM8K": 55.57, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2504e46e66eb320718545971bf6e4bf4eb627343", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "martyn\/solar-megamerge-dare-10.7b-v1", @@ -23360,11 +32192,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "a8bf199949b35a6037d197ffc21ae5c26fd1947b", "Flagged": false, "MoE": false @@ -23386,7 +32218,7 @@ "Merged": false, "Hub License": "agpl-3.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "53db5c3846780919b8838ed8e1415bb86c475247", "Flagged": false, @@ -23410,7 +32242,7 @@ "Hub License": "mit", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0cf54af3c084e70b6e544326d63ecffccac30b47", "Flagged": false, "MoE": false @@ -23430,7 +32262,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "gpl", + "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -23456,7 +32288,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0a14aa5fd9ae557d7dbd02e503deab50544d5a6f", "Flagged": false, "MoE": false @@ -23501,7 +32333,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 23.0, "Available on the hub": true, "Model sha": "585c2fca1dce1904491c40408f6dd5404eca3754", "Flagged": true, @@ -23567,7 +32399,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -23599,6 +32431,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "twodgirl\/Nimue-7B", + "Average \u2b06\ufe0f": 68.68, + "ARC": 63.74, + "HellaSwag": 82.74, + "MMLU": 64.64, + "TruthfulQA": 50.89, + "Winogrande": 83.27, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2d8ded1a612d3695200a6f57db70c32152afb935", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "adamo1139\/Yi-34B-AEZAKMI-v1", @@ -23639,7 +32494,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 23.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "d74ae6cb13325e0f81797ee33c07f0e234a2caa4", "Flagged": false, @@ -23668,6 +32523,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "chlee10\/T3Q-Platypus-MistralM7-7B", + "Average \u2b06\ufe0f": 68.66, + "ARC": 64.16, + "HellaSwag": 85.16, + "MMLU": 61.29, + "TruthfulQA": 59.99, + "Winogrande": 81.53, + "GSM8K": 59.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ba1c6a820ca247c079d76c3d60d2f9c302f9385", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-HardRuby-7B", + "Average \u2b06\ufe0f": 68.65, + "ARC": 66.55, + "HellaSwag": 85.41, + "MMLU": 63.46, + "TruthfulQA": 56.94, + "Winogrande": 78.3, + "GSM8K": 61.26, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af9ab4dddfcedd1b5f71cf352d78a335b21c8f94", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Walmart-the-bag\/Quintellect-10.7B", + "Average \u2b06\ufe0f": 68.65, + "ARC": 65.02, + "HellaSwag": 84.48, + "MMLU": 63.28, + "TruthfulQA": 59.57, + "Winogrande": 79.01, + "GSM8K": 60.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d264ccc4abe79251b0c6be8f65e51ead07195793", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AA051610\/A12P", @@ -23686,7 +32610,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e2eb6a36741dfc799fd13f67cba385f6e3992393", "Flagged": false, "MoE": false @@ -23760,6 +32684,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "cognitivecomputations\/dolphin-2.8-experiment26-7b", + "Average \u2b06\ufe0f": 68.6, + "ARC": 64.51, + "HellaSwag": 83.79, + "MMLU": 63.24, + "TruthfulQA": 54.87, + "Winogrande": 81.61, + "GSM8K": 63.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "b7d94074abb2a9af40c1a823e94a9ba150de5acc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.8-experiment26-7b-preview", + "Average \u2b06\ufe0f": 68.6, + "ARC": 64.51, + "HellaSwag": 83.79, + "MMLU": 63.24, + "TruthfulQA": 54.87, + "Winogrande": 81.61, + "GSM8K": 63.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "9ed28849e136e4cfbb0a9f774d5736c76b893d81", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "luqmanxyz\/Maya_Hermes-2.5-Mistral-7B", @@ -23800,7 +32770,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 23.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "94e804a4cd8e3ed54105f400118c60fa0cce764d", "Flagged": false, @@ -23826,7 +32796,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "c43b47a1d94a5daf790c506d113e5ee258871822", - "Flagged": true, + "Flagged": false, "MoE": true }, { @@ -23852,6 +32822,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "InnerI\/InnerILLM-0x00d0-7B-slerp", + "Average \u2b06\ufe0f": 68.58, + "ARC": 65.78, + "HellaSwag": 85.21, + "MMLU": 64.95, + "TruthfulQA": 53.51, + "Winogrande": 80.58, + "GSM8K": 61.41, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d8044ad07c038761f4ac72db0a2cb3770b69da0e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "InnerI\/InnerILLM-OpenPipe-Nous-Yarn-Mistral-optimized-1228-7B-slerp", + "Average \u2b06\ufe0f": 68.58, + "ARC": 65.78, + "HellaSwag": 85.21, + "MMLU": 64.95, + "TruthfulQA": 53.51, + "Winogrande": 80.58, + "GSM8K": 61.41, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bf6f6b7378e2bfc0e9f26b0cd2f0d81e0c72e350", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "brucethemoose\/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties", @@ -23893,7 +32909,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0f5d81b13718a866cb078bd8762ab80a41972663", "Flagged": false, "MoE": false @@ -23921,6 +32937,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "CohereForAI\/c4ai-command-r-v01", + "Average \u2b06\ufe0f": 68.54, + "ARC": 65.53, + "HellaSwag": 87.0, + "MMLU": 68.2, + "TruthfulQA": 52.32, + "Winogrande": 81.53, + "GSM8K": 56.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "CohereForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 34.98, + "Hub \u2764\ufe0f": 778.0, + "Available on the hub": true, + "Model sha": "2323aaa960c3c073380a0da2fc51284f5113e114", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "sequelbox\/SpellBlade", @@ -23961,7 +33000,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "142b62bd4c61639c71c15dbd7ac793bfe30a6349", "Flagged": false, @@ -23981,8 +33020,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -24008,7 +33047,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5020869e6394b1ac039bf80a0a1d2bed6be6707e", "Flagged": false, "MoE": false @@ -24099,7 +33138,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "b6eb3c3293fff1cb3d38bbfefa9adfce3e20f053", "Flagged": false, @@ -24142,11 +33181,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "c00e0ed6d1c118b377faeabde26a4620cc94930d", "Flagged": false, "MoE": false @@ -24168,7 +33207,7 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 28.0, "Available on the hub": true, "Model sha": "228e7ab8b24ebb3d459160c0b665a821d1785dc5", "Flagged": false, @@ -24214,12 +33253,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 1362.0, + "Hub \u2764\ufe0f": 1464.0, "Available on the hub": true, "Model sha": "58301445dc1378584211722b7ebf8743ec4e192b", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/SystemConfigHermes-7B", + "Average \u2b06\ufe0f": 68.47, + "ARC": 65.19, + "HellaSwag": 84.41, + "MMLU": 61.89, + "TruthfulQA": 60.11, + "Winogrande": 77.74, + "GSM8K": 61.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "73b2afa99dcfd329e5482833429cc20e88acd825", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "LoSboccacc\/orthogonal-2x7B-v2-base", @@ -24235,7 +33297,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "", + "Hub License": null, "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24261,7 +33323,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "884c53a64a3c5faf7b0706d36a587ca1532ed8f5", "Flagged": false, "MoE": false @@ -24286,7 +33348,7 @@ "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "c3c7ee002c4fdb1b8c2e2c78b7fba0c389673710", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -24312,6 +33374,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/Mixtral-8x7B-Holodeck-v1", + "Average \u2b06\ufe0f": 68.45, + "ARC": 66.55, + "HellaSwag": 86.78, + "MMLU": 71.67, + "TruthfulQA": 48.28, + "Winogrande": 81.22, + "GSM8K": 56.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6e08f700186a7ee01fa407145c1e990ec15caa71", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mistral_AI_v2", + "Average \u2b06\ufe0f": 68.44, + "ARC": 65.44, + "HellaSwag": 85.61, + "MMLU": 63.44, + "TruthfulQA": 62.63, + "Winogrande": 80.35, + "GSM8K": 53.15, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bede68f5e1f2225c281fdd97cc58bf0e9389e311", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ZoidBB\/Jovian-10.7B-v1.0", @@ -24326,8 +33434,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24350,7 +33458,7 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": "openrail", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -24375,7 +33483,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 1362.0, + "Hub \u2764\ufe0f": 1464.0, "Available on the hub": true, "Model sha": "4dd4b0f2d577d7b74152732d5543a92201481fe2", "Flagged": false, @@ -24396,7 +33504,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24427,6 +33535,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Code-Mistral-7B", + "Average \u2b06\ufe0f": 68.4, + "ARC": 63.57, + "HellaSwag": 83.71, + "MMLU": 63.38, + "TruthfulQA": 51.81, + "Winogrande": 81.22, + "GSM8K": 66.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "ed3b9ad583910423a7b82e27274681e3865206f1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mncai\/agiin-13.6B-v0.1", @@ -24467,7 +33598,7 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 55.0, + "Hub \u2764\ufe0f": 59.0, "Available on the hub": true, "Model sha": "0591b1690e5b7c800758f9f5de17a2e60cecf11e", "Flagged": false, @@ -24491,7 +33622,7 @@ "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e641a44c60ddf1f31d898ca53810ccb1e7a30972", "Flagged": false, "MoE": false @@ -24534,7 +33665,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24559,7 +33690,7 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "1bbd507bb7dd502bbca4105406a6e57abe3c1187", "Flagged": false, @@ -24579,8 +33710,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24652,7 +33783,7 @@ "Hub License": "?", "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "dab86ae57fe51dc5e993769ebb69a173637852bc", "Flagged": false, "MoE": false @@ -24720,7 +33851,7 @@ "Merged": true, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "98a4cb1db6369cda6330441ad083f4d1fa3bca29", "Flagged": false, @@ -24795,6 +33926,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/RP-Coder-SM3", + "Average \u2b06\ufe0f": 68.28, + "ARC": 65.61, + "HellaSwag": 84.22, + "MMLU": 63.34, + "TruthfulQA": 54.11, + "Winogrande": 82.56, + "GSM8K": 59.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b395abc7250f460cde49a0bdf894e20ac52e4168", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "liminerity\/e.star.7.b", + "Average \u2b06\ufe0f": 68.28, + "ARC": 63.91, + "HellaSwag": 86.02, + "MMLU": 63.44, + "TruthfulQA": 54.91, + "Winogrande": 80.19, + "GSM8K": 61.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c1af18b48367a616f673b9feff92ab73d0f40874", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "TeeZee\/Xwin-LM-70B-V0.1_Jannie", @@ -24833,7 +34010,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24841,6 +34018,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/RP-Coder-SM3", + "Average \u2b06\ufe0f": 68.25, + "ARC": 65.78, + "HellaSwag": 84.21, + "MMLU": 63.28, + "TruthfulQA": 54.12, + "Winogrande": 82.16, + "GSM8K": 59.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b395abc7250f460cde49a0bdf894e20ac52e4168", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Xenon1\/Eclipse-7B", @@ -24879,13 +34079,13 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "d398693041f482ee7ee9c91c804206e7f62ea58c", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udcac", @@ -24901,7 +34101,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, + "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 68.98, "Hub \u2764\ufe0f": 7.0, @@ -24933,6 +34133,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "hydra-project\/ChatHercules-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 68.24, + "ARC": 65.1, + "HellaSwag": 84.61, + "MMLU": 65.35, + "TruthfulQA": 47.52, + "Winogrande": 81.85, + "GSM8K": 64.97, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "a50dd22ab08cb628642dcbd62edc25230c649bc4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "decapoda-research\/Antares-11b-v1", @@ -24971,7 +34194,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -24996,7 +34219,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 138.0, + "Hub \u2764\ufe0f": 140.0, "Available on the hub": true, "Model sha": "351028e0532a084c2c1370029fcf2ef805da3929", "Flagged": false, @@ -25025,6 +34248,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "maldv\/eleusis-7b-alpha", + "Average \u2b06\ufe0f": 68.2, + "ARC": 64.93, + "HellaSwag": 84.87, + "MMLU": 64.1, + "TruthfulQA": 54.34, + "Winogrande": 79.16, + "GSM8K": 61.79, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d8b62e9eba34e430291e4649e5eb84c93bffbe65", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/C0322-reft", + "Average \u2b06\ufe0f": 68.2, + "ARC": 64.42, + "HellaSwag": 83.74, + "MMLU": 79.5, + "TruthfulQA": 59.77, + "Winogrande": 78.45, + "GSM8K": 43.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "CohereForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "153efc8ba5e9939536b2cab6d510e1762e11680d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "vistagi\/Mixtral-8x7b-v0.1-dpo", @@ -25088,7 +34357,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "333c788e0d026cdb76bb827b8dcbc14a859ae2cc", "Flagged": false, @@ -25140,6 +34409,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FredrikBL\/test-dare", + "Average \u2b06\ufe0f": 68.16, + "ARC": 64.59, + "HellaSwag": 84.87, + "MMLU": 64.43, + "TruthfulQA": 52.69, + "Winogrande": 81.29, + "GSM8K": 61.11, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c0b8022c8003f911fb73f7697bea001c8e21f6b2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Azure99\/blossom-v3_1-yi-34b", @@ -25204,7 +34496,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "36c17124ff891121c39f2d5e4d203daad5350c48", "Flagged": false, "MoE": false @@ -25224,9 +34516,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 50.0, "Available on the hub": true, "Model sha": "488b5d3a878dcbadf3f316dca9332f484ffd4e0d", "Flagged": false, @@ -25247,7 +34539,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "", + "Hub License": null, "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -25270,7 +34562,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -25318,7 +34610,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 137.0, "Available on the hub": true, "Model sha": "868f0aaeba382aa63bef6ff2bc370be5df16ce9a", "Flagged": false, @@ -25387,7 +34679,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 137.0, "Available on the hub": true, "Model sha": "868f0aaeba382aa63bef6ff2bc370be5df16ce9a", "Flagged": false, @@ -25434,11 +34726,34 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1c0e61c7da6839fe4cc34433b899c5416fadbe18", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Isaak-Carter\/JOSIE_Beta-4-7B-slerp", + "Average \u2b06\ufe0f": 68.06, + "ARC": 63.57, + "HellaSwag": 84.1, + "MMLU": 63.73, + "TruthfulQA": 55.93, + "Winogrande": 79.32, + "GSM8K": 61.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ce6ec124e2dd22c85ee71de66f574eeed1c6bdce", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Azazelle\/xDAN-SlimOrca", @@ -25462,6 +34777,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "DenisTheDev\/Blitz-AI-MOE-v0.4", + "Average \u2b06\ufe0f": 68.04, + "ARC": 66.3, + "HellaSwag": 85.59, + "MMLU": 64.24, + "TruthfulQA": 53.55, + "Winogrande": 78.45, + "GSM8K": 60.12, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7655e3973c0f0813532e82f8a239f0cb5d8fd7be", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "nlpguy\/Hermes-low-tune-2", @@ -25526,7 +34864,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7888318c72df9f668df20b2916b651b94a6ed77c", "Flagged": false, "MoE": false @@ -25556,7 +34894,7 @@ }, { "T": "\ud83d\udd36", - "Model": "indischepartij\/OpenMia-Indo-Mistral-7b-v3-refined", + "Model": "gmonsoon\/OpenMia-Indo-Mistral-7b-v3-refined", "Average \u2b06\ufe0f": 68.0, "ARC": 64.42, "HellaSwag": 84.22, @@ -25573,13 +34911,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "ce2b8e2503f9e927acbe3314c69d4a04468df55b", + "Model sha": "c2c84867adc3160d6c39acf3e8cb56413a9000ac", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "gmonsoon\/OpenMia-Indo-Mistral-7b-v3-refined", + "Model": "indischepartij\/OpenMia-Indo-Mistral-7b-v3-refined", "Average \u2b06\ufe0f": 68.0, "ARC": 64.42, "HellaSwag": 84.22, @@ -25596,7 +34934,7 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "c2c84867adc3160d6c39acf3e8cb56413a9000ac", + "Model sha": "ce2b8e2503f9e927acbe3314c69d4a04468df55b", "Flagged": false, "MoE": false }, @@ -25618,11 +34956,34 @@ "Hub License": "cc-by-4.0", "#Params (B)": 10.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "04b63652663be2d6c7178577781efdd737b3c37a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "HIT-SCIR\/huozi3", + "Average \u2b06\ufe0f": 67.97, + "ARC": 65.02, + "HellaSwag": 86.0, + "MMLU": 70.61, + "TruthfulQA": 49.45, + "Winogrande": 82.16, + "GSM8K": 54.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.91, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "fa66db9e2971b84bc084bac74d97d04149a65a05", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "Walmart-the-bag\/openchat-3.5-Infinity", @@ -25638,7 +34999,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -25669,6 +35030,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/SystemHermes-2-7B", + "Average \u2b06\ufe0f": 67.92, + "ARC": 65.02, + "HellaSwag": 84.05, + "MMLU": 63.16, + "TruthfulQA": 56.42, + "Winogrande": 77.35, + "GSM8K": 61.56, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "56ae3b1d75dcf4b435272aff0db7eb73a752e6dc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Mihaiii\/Pallas-0.5-LASER-exp2-0.1", @@ -25752,11 +35136,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "0375c801fc511b3c63ece6e9c6e05bc926d1cfb4", "Flagged": false, "MoE": false @@ -25801,7 +35185,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "9bbbcdae306c8e5a8a7c695411274321abcea485", "Flagged": false, @@ -25893,8 +35277,8 @@ "Merged": false, "Hub License": null, "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 755.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 788.0, + "Available on the hub": true, "Model sha": "ed7b07231238f836b99bf45701b9a0063576b194", "Flagged": false, "MoE": false @@ -25940,7 +35324,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8f6bcbc440db8044af878f4a60e7fd000741daa5", "Flagged": false, "MoE": false @@ -25962,7 +35346,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "e6ad0daaeb0e2d1f4b01fb8f409b146a4b752317", "Flagged": false, @@ -25985,7 +35369,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "92a96144f94c24341cb6a40259be28627bc76298", "Flagged": false, @@ -26031,12 +35415,58 @@ "Merged": false, "Hub License": "unknown", "#Params (B)": 179.52, - "Hub \u2764\ufe0f": 1044.0, + "Hub \u2764\ufe0f": 1073.0, "Available on the hub": true, "Model sha": "71a1a70b629e9963f7b4601e82f3f9079d48011e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Shiki-m7", + "Average \u2b06\ufe0f": 67.85, + "ARC": 65.53, + "HellaSwag": 85.3, + "MMLU": 63.57, + "TruthfulQA": 65.45, + "Winogrande": 77.74, + "GSM8K": 49.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f98d82c7b01b5ac1bf6ee62871a27011cf57cbf9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/A0305a", + "Average \u2b06\ufe0f": 67.85, + "ARC": 61.35, + "HellaSwag": 80.4, + "MMLU": 75.66, + "TruthfulQA": 51.74, + "Winogrande": 77.66, + "GSM8K": 60.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f9770a953c3daa35590323746b1dd01620c6edd8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "beberik\/Nyxene-v2-11B", @@ -26054,7 +35484,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "07d017d24117fabce2e7b67819f6689e3187404f", "Flagged": false, @@ -26106,6 +35536,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "ldahee\/SLAL-0.1", + "Average \u2b06\ufe0f": 67.83, + "ARC": 57.94, + "HellaSwag": 80.14, + "MMLU": 65.99, + "TruthfulQA": 54.22, + "Winogrande": 85.56, + "GSM8K": 63.15, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 26.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "315b4b492c861e9445712d8bc0d7b9245d7cdeac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-Gemma-7b", + "Average \u2b06\ufe0f": 67.83, + "ARC": 59.98, + "HellaSwag": 81.91, + "MMLU": 63.76, + "TruthfulQA": 61.0, + "Winogrande": 76.64, + "GSM8K": 63.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "87cf83507c53dc0a41f8ecd0c961235b42c20ade", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Swisslex\/Mixtral-Orca-v0.1", @@ -26131,7 +35607,7 @@ }, { "T": "\ud83d\udd36", - "Model": "FelixChao\/NarutoDolphin-7B", + "Model": "FelixChao\/NarutoDolphin-10B", "Average \u2b06\ufe0f": 67.82, "ARC": 63.82, "HellaSwag": 84.17, @@ -26143,18 +35619,18 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, + "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "fcf546ffbfdee6e9bd288eec27316cac533d1ffe", + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "20c3e2a3d13afb7340d1261e76528b1cbe6cd7ce", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "FelixChao\/NarutoDolphin-10B", + "Model": "FelixChao\/NarutoDolphin-7B", "Average \u2b06\ufe0f": 67.82, "ARC": 63.82, "HellaSwag": 84.17, @@ -26166,12 +35642,35 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fcf546ffbfdee6e9bd288eec27316cac533d1ffe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_BioMedical", + "Average \u2b06\ufe0f": 67.81, + "ARC": 65.44, + "HellaSwag": 85.2, + "MMLU": 63.17, + "TruthfulQA": 62.24, + "Winogrande": 79.72, + "GSM8K": 51.1, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "20c3e2a3d13afb7340d1261e76528b1cbe6cd7ce", + "Available on the hub": false, + "Model sha": "565e44539eeb5db84fda3d030e16b4bc09373de6", "Flagged": false, "MoE": false }, @@ -26192,7 +35691,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "82dc0ab70090085b4271f0f317f667f180db9872", "Flagged": false, @@ -26267,6 +35766,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "kimou605\/shadow-clown-BioMistral-7B-SLERP", + "Average \u2b06\ufe0f": 67.78, + "ARC": 64.76, + "HellaSwag": 84.55, + "MMLU": 61.93, + "TruthfulQA": 62.4, + "Winogrande": 80.66, + "GSM8K": 52.39, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5d0a327a3f37668c90e649b8bcf05c9db5961a40", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "eren23\/DistilHermes-2.5-Mistral-7B", @@ -26284,7 +35806,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "b75259311e80e39117c7c31e5f93ebd8e33ffc75", "Flagged": false, @@ -26327,8 +35849,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -26428,6 +35950,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "eldogbbhed\/NeuralKrishnaMathWizard-7B", + "Average \u2b06\ufe0f": 67.7, + "ARC": 63.05, + "HellaSwag": 85.12, + "MMLU": 61.78, + "TruthfulQA": 49.06, + "Winogrande": 78.06, + "GSM8K": 69.14, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "01af35d4f26b45d8ae0e042303a4995194e54c68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cognitivecomputations\/dolphin-2.8-experiment26-7b", + "Average \u2b06\ufe0f": 67.69, + "ARC": 63.65, + "HellaSwag": 83.7, + "MMLU": 62.31, + "TruthfulQA": 55.1, + "Winogrande": 78.77, + "GSM8K": 62.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "0c90dbad22d980ece39ae8256086b9f9142c63cb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "PetroGPT\/Voldemort-10B-DPO", @@ -26491,10 +36059,10 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 38.0, + "Hub \u2764\ufe0f": 39.0, "Available on the hub": true, "Model sha": "6e3ce78eb5346bf3a5ee88cd60c25dc0d73de639", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -26511,13 +36079,36 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "0e82c4271fa9de78e829c717af871ab7067243c4", "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SeaLLMs\/SeaLLM-7B-v2", + "Average \u2b06\ufe0f": 67.65, + "ARC": 61.86, + "HellaSwag": 82.34, + "MMLU": 62.15, + "TruthfulQA": 51.15, + "Winogrande": 79.72, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.38, + "Hub \u2764\ufe0f": 49.0, + "Available on the hub": true, + "Model sha": "9fddeaa79d3862ac4c2e3eab647f11e8d88f2920", + "Flagged": false, "MoE": true }, { @@ -26537,12 +36128,35 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 37.0, + "Hub \u2764\ufe0f": 40.0, "Available on the hub": true, "Model sha": "df11f29693b1cd4da9967f1c1832c4f4e0eb3303", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "localfultonextractor\/Erosumika-7B-v2", + "Average \u2b06\ufe0f": 67.64, + "ARC": 65.61, + "HellaSwag": 86.29, + "MMLU": 62.51, + "TruthfulQA": 69.0, + "Winogrande": 77.27, + "GSM8K": 45.19, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "d391a01d8277f80b159ca4c06a4316b771241be6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "freeCS-dot-org\/OpenAGI-testing-truthyDPO-1", @@ -26612,6 +36226,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/Mistral-7B-Instruct-v0.2_openchat-3.5-0106", + "Average \u2b06\ufe0f": 67.63, + "ARC": 65.7, + "HellaSwag": 84.58, + "MMLU": 63.23, + "TruthfulQA": 58.89, + "Winogrande": 79.32, + "GSM8K": 54.06, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce648c03c3d5b47ee86252177a665d84617bb790", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "JaeyeonKang\/CCK-v2.0-DPO", @@ -26630,7 +36267,7 @@ "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.86, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "84ceccea3e3cde7348a07f3e2bfb1f58b07b38ee", "Flagged": false, "MoE": false @@ -26727,6 +36364,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nonetrix\/sillyrp-7b", + "Average \u2b06\ufe0f": 67.58, + "ARC": 64.93, + "HellaSwag": 85.26, + "MMLU": 64.2, + "TruthfulQA": 54.28, + "Winogrande": 77.66, + "GSM8K": 59.14, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9ab1c660c1ae1887e5e647a6ba40e04c49cbfe3f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "r2rss\/Malachite-7b-v0", @@ -26751,7 +36411,30 @@ "MoE": false }, { - "T": "\ud83d\udcac", + "T": "\ud83e\udd1d", + "Model": "dozzke\/hermorca", + "Average \u2b06\ufe0f": 67.57, + "ARC": 63.74, + "HellaSwag": 84.4, + "MMLU": 64.28, + "TruthfulQA": 57.69, + "Winogrande": 76.87, + "GSM8K": 58.45, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5102ad0c27d60a2c6381b8ec97fcc59450ea5640", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", "Model": "SeaLLMs\/SeaLLM-7B-v2", "Average \u2b06\ufe0f": 67.57, "ARC": 62.03, @@ -26760,19 +36443,42 @@ "TruthfulQA": 51.11, "Winogrande": 79.08, "GSM8K": 68.99, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 49.0, "Available on the hub": true, "Model sha": "8bb693e108dc92efdd608767144bc0232721b18a", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v5-14b", + "Average \u2b06\ufe0f": 67.57, + "ARC": 58.45, + "HellaSwag": 80.72, + "MMLU": 68.45, + "TruthfulQA": 54.89, + "Winogrande": 75.14, + "GSM8K": 67.78, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c7bcffc0500cff73fdee957c3428c2ade1135dfc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "fangloveskari\/Platypus_QLoRA_LLaMA_70b", @@ -26813,12 +36519,35 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 37.0, + "Hub \u2764\ufe0f": 40.0, "Available on the hub": true, "Model sha": "df11f29693b1cd4da9967f1c1832c4f4e0eb3303", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_Chat_X_128k", + "Average \u2b06\ufe0f": 67.54, + "ARC": 65.27, + "HellaSwag": 85.27, + "MMLU": 63.98, + "TruthfulQA": 57.23, + "Winogrande": 80.58, + "GSM8K": 52.92, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "47c31317be30328c7c4309a6b3af702a0068e0f9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/MetaMath-neural-chat-7b-v3-2-Ties", @@ -26857,14 +36586,37 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 70.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ade069976a810b6b7caf3173a1aa4bfb30534ec9", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "dozzke\/hermorca", + "Average \u2b06\ufe0f": 67.53, + "ARC": 63.57, + "HellaSwag": 84.41, + "MMLU": 64.29, + "TruthfulQA": 57.63, + "Winogrande": 77.03, + "GSM8K": 58.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5102ad0c27d60a2c6381b8ec97fcc59450ea5640", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "argilla\/DistilabelBeagle14-7B", @@ -26949,7 +36701,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -26957,6 +36709,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "grimjim\/Mistral-Starling-merge-trial1-7B", + "Average \u2b06\ufe0f": 67.49, + "ARC": 66.13, + "HellaSwag": 84.67, + "MMLU": 64.12, + "TruthfulQA": 53.18, + "Winogrande": 80.43, + "GSM8K": 56.41, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8781341908ff63afe7a31e8692ae964cfb75cf38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "InferenceIllusionist\/Magic-Dolphin-7b", + "Average \u2b06\ufe0f": 67.48, + "ARC": 65.78, + "HellaSwag": 85.61, + "MMLU": 64.64, + "TruthfulQA": 58.01, + "Winogrande": 79.64, + "GSM8K": 51.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "4cd26c63dd5cb6e26af5e7815bb1ab62b7dfd4b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "llmixer\/BigWeave-v6-90b", @@ -27086,7 +36884,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -27095,6 +36893,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ValiantLabs\/Fireplace-34b", + "Average \u2b06\ufe0f": 67.44, + "ARC": 71.25, + "HellaSwag": 82.72, + "MMLU": 47.01, + "TruthfulQA": 65.11, + "Winogrande": 79.56, + "GSM8K": 58.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "58c8df51a5963cd206301461edb68fa86ba059ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Hermes-2-Pro-Mistral-7B", + "Average \u2b06\ufe0f": 67.43, + "ARC": 63.99, + "HellaSwag": 82.75, + "MMLU": 62.12, + "TruthfulQA": 59.01, + "Winogrande": 75.45, + "GSM8K": 61.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 365.0, + "Available on the hub": true, + "Model sha": "8dd571ec94aa1709b4b02a07e1201678b939ef44", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "ehartford\/Samantha-1.1-70b", @@ -27113,7 +36957,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a3819d186f5b4d52ced7ddeb7fa16bf66e8a2ea7", "Flagged": false, "MoE": false @@ -27135,12 +36979,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "3e2cd605dde0bd7443172c722a1f34a498a36901", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "DenisTheDev\/Blitz-AI-MOE-v0.7", + "Average \u2b06\ufe0f": 67.42, + "ARC": 67.15, + "HellaSwag": 85.59, + "MMLU": 64.04, + "TruthfulQA": 55.56, + "Winogrande": 79.08, + "GSM8K": 53.07, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ed520aac996a1e3f0f261f207572739579adff1c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_ThoughtsProcess_1", + "Average \u2b06\ufe0f": 67.42, + "ARC": 65.27, + "HellaSwag": 85.69, + "MMLU": 61.9, + "TruthfulQA": 67.34, + "Winogrande": 77.66, + "GSM8K": 46.63, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b2c56ac7f94c61538cf1ba44bee37e689259bd3f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AI-B\/UTENA-7B-V3", @@ -27204,7 +37094,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 873.0, + "Hub \u2764\ufe0f": 880.0, "Available on the hub": false, "Model sha": "e4944caa6ece819413b140b8dcecea79fe7e22cf", "Flagged": false, @@ -27250,7 +37140,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 92.0, + "Hub \u2764\ufe0f": 99.0, "Available on the hub": true, "Model sha": "9934c04c767e6ae0f792712a060f02915391d4ec", "Flagged": false, @@ -27274,7 +37164,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ca3789cd6b683e97dcd6a5f0367f90a63d7a4e7b", "Flagged": false, "MoE": false @@ -27319,7 +37209,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "337fe3de7874d3a09aa1cfe9e78f5efd81c00f43", "Flagged": false, @@ -27342,7 +37232,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 62.0, + "Hub \u2764\ufe0f": 63.0, "Available on the hub": false, "Model sha": "8469429924dc2e1a9394b8095753985668a4052e", "Flagged": false, @@ -27371,6 +37261,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "NousResearch\/Hermes-2-Pro-Mistral-7B", + "Average \u2b06\ufe0f": 67.35, + "ARC": 64.16, + "HellaSwag": 82.73, + "MMLU": 62.21, + "TruthfulQA": 58.99, + "Winogrande": 75.61, + "GSM8K": 60.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 365.0, + "Available on the hub": true, + "Model sha": "8dd571ec94aa1709b4b02a07e1201678b939ef44", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Synthia-v3.0-11B", @@ -27394,6 +37307,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Isotonic\/Hermes-2-Pro-Mixtral-4x7B", + "Average \u2b06\ufe0f": 67.35, + "ARC": 64.25, + "HellaSwag": 82.7, + "MMLU": 62.26, + "TruthfulQA": 59.02, + "Winogrande": 75.45, + "GSM8K": 60.42, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "787647b887303d98363ce1b352d7034f4f0d1b6e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/openchat_3.5-gpt-4-80k", + "Average \u2b06\ufe0f": 67.35, + "ARC": 63.31, + "HellaSwag": 81.21, + "MMLU": 64.33, + "TruthfulQA": 54.34, + "Winogrande": 76.48, + "GSM8K": 64.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f54231e6c3e3a3c8164a10a5bbe9cd055a57ff50", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Mihaiii\/Bucharest-0.1", @@ -27409,7 +37368,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -27417,6 +37376,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Hertz\/Mistral-Hermes-2x7b", + "Average \u2b06\ufe0f": 67.33, + "ARC": 65.19, + "HellaSwag": 85.27, + "MMLU": 63.71, + "TruthfulQA": 51.2, + "Winogrande": 79.32, + "GSM8K": 59.29, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f050aed1a47eb58712ad4e47b92c09e188371472", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "abacusai\/Fewshot-Metamath-OrcaVicuna-Mistral", @@ -27480,12 +37462,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "76efb2db34ee99b591431a3055eca785ffed44f7", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/WestSenzu-Swap-7B", + "Average \u2b06\ufe0f": 67.28, + "ARC": 68.34, + "HellaSwag": 85.7, + "MMLU": 64.14, + "TruthfulQA": 50.43, + "Winogrande": 82.48, + "GSM8K": 52.62, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "620fb61f0f963dab1ef2255ba2ffa1590ac5daf5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "diffnamehard\/Mistral-CatMacaroni-slerp-uncensored", @@ -27504,7 +37509,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "18a3b2e5a34765daafb8e36318a4baf33e272c83", "Flagged": false, "MoE": false @@ -27526,7 +37531,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 94.0, + "Hub \u2764\ufe0f": 112.0, "Available on the hub": true, "Model sha": "05cc9e559e87e7e269401a3843a0e63a6084a85e", "Flagged": false, @@ -27550,7 +37555,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "49e5b5ee0bed2864f0b38ba8bf9e01ccc5e0ba5f", "Flagged": false, "MoE": false @@ -27572,7 +37577,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "c4f668605515745bb097e3bbbfec808550324704", "Flagged": false, @@ -27601,6 +37606,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "LeroyDyer\/Mixtral_AI_Cyber_4.0", + "Average \u2b06\ufe0f": 67.25, + "ARC": 64.93, + "HellaSwag": 84.04, + "MMLU": 62.82, + "TruthfulQA": 60.4, + "Winogrande": 80.27, + "GSM8K": 51.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "27862ae88891b2948f25ceec2023945e0911f449", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "mahiatlinux\/ShadowDolph-7B-v1", + "Average \u2b06\ufe0f": 67.25, + "ARC": 69.2, + "HellaSwag": 85.0, + "MMLU": 58.95, + "TruthfulQA": 64.56, + "Winogrande": 80.43, + "GSM8K": 45.34, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "357bc5342080b4de9b1926873d0aa46670280b17", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Ana-v1-m7", @@ -27624,6 +37675,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-Beta-Sapphire-7B", + "Average \u2b06\ufe0f": 67.24, + "ARC": 65.78, + "HellaSwag": 85.76, + "MMLU": 64.28, + "TruthfulQA": 51.28, + "Winogrande": 79.64, + "GSM8K": 56.71, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e656fa8001d126ce775b10092f4d44f2c26bbd2c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Test157t\/Kunocchini-7b-128k-test", @@ -27641,7 +37715,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "c3a102205219be392f9fdb12468a394525fc73b4", "Flagged": false, @@ -27661,14 +37735,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 18.52, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "63499a3e77b66d0709c15208720d48e89b4c1786", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", @@ -27687,7 +37761,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.7, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "c6659f344448dc66044df9b5b3e223419b0bcfbd", "Flagged": false, @@ -27756,7 +37830,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 51.0, + "Hub \u2764\ufe0f": 55.0, "Available on the hub": true, "Model sha": "5c32e515f3d79beefc110e8a07c3671269a0f5ab", "Flagged": false, @@ -27848,7 +37922,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "f60f1f62c9e7e7440b24cdd7a1333dac739cc359", "Flagged": false, @@ -27871,7 +37945,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 33.0, + "Hub \u2764\ufe0f": 46.0, "Available on the hub": true, "Model sha": "0ece1807074c4f1b9461e271a8931e4947902fbb", "Flagged": true, @@ -27892,9 +37966,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 476.0, + "Hub \u2764\ufe0f": 526.0, "Available on the hub": true, "Model sha": "f721e85293598f2ef774e483ae95343e39811577", "Flagged": false, @@ -27917,7 +37991,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "1407000b20cf38cf59d7a2d1143cb0883abe5ab3", "Flagged": false, @@ -27940,7 +38014,7 @@ "Merged": false, "Hub License": "cc-by-nc-2.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 56.0, + "Hub \u2764\ufe0f": 62.0, "Available on the hub": true, "Model sha": "b366c0bb318ae592023cca894cc6b4421a607a0d", "Flagged": false, @@ -27964,7 +38038,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3d95e0f3598f7a76ab97cb2cc0e4aae957d77479", "Flagged": false, "MoE": false @@ -28032,12 +38106,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "d3e24684f38e0332cf4a6c70a37ee894e7a27fdc", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "sophosympatheia\/Midnight-Rose-70B-v2.0.3", + "Average \u2b06\ufe0f": 67.11, + "ARC": 70.65, + "HellaSwag": 87.5, + "MMLU": 69.64, + "TruthfulQA": 65.27, + "Winogrande": 81.22, + "GSM8K": 28.35, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "fcfcf5539655820679ce0f952cfb07466f3b1ec1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "decem\/Dionysus-Mistral-m3-v6", @@ -28055,12 +38152,58 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "417618a86cd04bfcc48bd987043a4ef096e866cd", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Nitral-AI\/Eris_PrimeV4.20-Vision-32k-7B", + "Average \u2b06\ufe0f": 67.1, + "ARC": 64.93, + "HellaSwag": 84.8, + "MMLU": 63.71, + "TruthfulQA": 52.53, + "Winogrande": 79.48, + "GSM8K": 57.16, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e204d3ee2b54aa32cbf0c39d36552fe5cb256b31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ontocord\/Felix-8B", + "Average \u2b06\ufe0f": 67.1, + "ARC": 65.02, + "HellaSwag": 84.61, + "MMLU": 61.05, + "TruthfulQA": 64.23, + "Winogrande": 75.93, + "GSM8K": 51.78, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "599b440074588eee5bada30cf17dc545915f9e55", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO", @@ -28084,6 +38227,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Starling-LM-7B-alpha-gpt-4-80k", + "Average \u2b06\ufe0f": 67.1, + "ARC": 62.97, + "HellaSwag": 81.28, + "MMLU": 64.22, + "TruthfulQA": 54.35, + "Winogrande": 76.72, + "GSM8K": 63.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e38bac0fb1d74c5abc65715c2b60c7b1509b64fb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-corrupted", @@ -28107,6 +38273,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "maldv\/winter-garden-7b-beta", + "Average \u2b06\ufe0f": 67.09, + "ARC": 64.93, + "HellaSwag": 85.02, + "MMLU": 64.54, + "TruthfulQA": 50.82, + "Winogrande": 80.51, + "GSM8K": 56.71, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43825c3842ba34557993a8028c5591a614369027", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "freecs\/ThetaWave-7B-v1", @@ -28130,6 +38319,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_Instruct", + "Average \u2b06\ufe0f": 67.07, + "ARC": 64.51, + "HellaSwag": 84.77, + "MMLU": 63.41, + "TruthfulQA": 61.9, + "Winogrande": 79.48, + "GSM8K": 48.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "89e9d160c870cdeec454f78da62d5a6f81cb9e94", + "Flagged": false, + "MoE": true + }, { "T": "\ud83e\udd1d", "Model": "paulilioaica\/Hugo-7B-slerp", @@ -28214,9 +38426,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 476.0, + "Hub \u2764\ufe0f": 526.0, "Available on the hub": true, "Model sha": "76e60ca9807f55acd8eff3ec7ae022c5fbdf1e0e", "Flagged": false, @@ -28236,7 +38448,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -28265,7 +38477,7 @@ "Hub \u2764\ufe0f": 33.0, "Available on the hub": true, "Model sha": "0c7f7c85359f15d3e6c361e8192738bdfb14ea6c", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -28337,6 +38549,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "LeroyDyer\/Mixtral_AI_Cyber_3.1_SFT", + "Average \u2b06\ufe0f": 67.01, + "ARC": 61.86, + "HellaSwag": 81.32, + "MMLU": 64.51, + "TruthfulQA": 52.75, + "Winogrande": 80.19, + "GSM8K": 61.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f5c5468cc9c8191e4ed89a30b6d7b98d2a0dfadc", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Synthia-70B-v1.2b", @@ -28354,7 +38589,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 26.0, "Available on the hub": true, "Model sha": "7b687d6e4101b8bb8cc4062f8a318d639098a55d", "Flagged": false, @@ -28384,7 +38619,7 @@ "MoE": true }, { - "T": "\ud83d\udfe2", + "T": "\ud83d\udfe9", "Model": "chargoddard\/internlm2-7b-llama", "Average \u2b06\ufe0f": 66.94, "ARC": 60.49, @@ -28393,14 +38628,14 @@ "TruthfulQA": 54.25, "Winogrande": 79.87, "GSM8K": 62.85, - "Type": "pretrained", - "Architecture": "L;l;a;m;a;F;o;r;C;a;u;s;a;l;L;M", + "Type": "continuously pretrained", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, "Hub License": "other", "#Params (B)": 7.74, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "67517f8c49907cf4c1e515b356ce6907189dbdd4", "Flagged": false, @@ -28452,6 +38687,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "maldv\/winter-garden-7b-alpha", + "Average \u2b06\ufe0f": 66.91, + "ARC": 65.19, + "HellaSwag": 85.36, + "MMLU": 65.2, + "TruthfulQA": 50.94, + "Winogrande": 80.35, + "GSM8K": 54.44, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0a289b3d6fbb286fb7c7897bdc84df0b4d950572", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wolfeidau\/NeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.91, + "ARC": 68.26, + "HellaSwag": 85.46, + "MMLU": 63.31, + "TruthfulQA": 55.02, + "Winogrande": 78.37, + "GSM8K": 51.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0b9321aa6d6c51329f0589976c0820e961d0a3cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "grimjim\/Mistral-Starling-merge-trial3-7B", + "Average \u2b06\ufe0f": 66.9, + "ARC": 66.55, + "HellaSwag": 84.81, + "MMLU": 64.18, + "TruthfulQA": 52.85, + "Winogrande": 80.03, + "GSM8K": 52.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "95cc5aafb8b12ae31b5fd5e68a0e9e3e16c7546a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Synthia-70B-v1.2", @@ -28521,6 +38825,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Liberated-Qwen1.5-14B", + "Average \u2b06\ufe0f": 66.86, + "ARC": 57.94, + "HellaSwag": 80.65, + "MMLU": 68.83, + "TruthfulQA": 52.48, + "Winogrande": 74.74, + "GSM8K": 66.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "cc0fa5102bfee821bb5e49f082731ccb9d1fedf1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/SystemHermes-7B", + "Average \u2b06\ufe0f": 66.86, + "ARC": 64.76, + "HellaSwag": 83.68, + "MMLU": 63.23, + "TruthfulQA": 52.81, + "Winogrande": 77.82, + "GSM8K": 58.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f6882245b6a84d44b0ffe1fe2026ef97863e129c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Cartinoe5930\/MoE-Merging", @@ -28584,7 +38934,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "6b78354a0789d3e9d0bfa6dd3d0b52c5e4594c39", "Flagged": false, @@ -28653,7 +39003,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "8cbf07c769e920054948dada4d4a1d4f914d32fa", "Flagged": false, @@ -28682,6 +39032,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/SpydazWeb_AI_BASE_128k", + "Average \u2b06\ufe0f": 66.79, + "ARC": 65.19, + "HellaSwag": 84.62, + "MMLU": 63.81, + "TruthfulQA": 57.82, + "Winogrande": 79.24, + "GSM8K": 50.04, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c210d19ce0b57f13217ea70c14ecfca5bf0c5737", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "dillfrescott\/sonya-medium-x8-MoE", @@ -28745,7 +39118,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 14.17, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "b505d4e2311a709de56a214a33820f5a4ee0d3e5", "Flagged": false, @@ -28791,7 +39164,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "472637ca2bf2bfb08aa4b5ebcdc5f89f48c7b257", "Flagged": false, @@ -28814,7 +39187,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 18.52, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "9127c38cad1a2b9dd3d3fa7ab71706585b46225d", "Flagged": false, @@ -28843,6 +39216,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-14B", + "Average \u2b06\ufe0f": 66.7, + "ARC": 56.57, + "HellaSwag": 81.08, + "MMLU": 69.36, + "TruthfulQA": 52.06, + "Winogrande": 73.48, + "GSM8K": 67.63, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "39b74a78357df4d2296e838d87565967d663a67a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chlee10\/T3Q-Platypus-Mistral7B", + "Average \u2b06\ufe0f": 66.69, + "ARC": 63.14, + "HellaSwag": 84.41, + "MMLU": 60.71, + "TruthfulQA": 51.85, + "Winogrande": 81.29, + "GSM8K": 58.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "266e15172e2c985fe4b1bf3c3a3030fef3b40cac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Liberated-Qwen1.5-14B", + "Average \u2b06\ufe0f": 66.69, + "ARC": 57.94, + "HellaSwag": 80.56, + "MMLU": 68.81, + "TruthfulQA": 52.37, + "Winogrande": 74.59, + "GSM8K": 65.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "cc0fa5102bfee821bb5e49f082731ccb9d1fedf1", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udfe2", "Model": "HIT-SCIR\/Chinese-Mixtral-8x7B", @@ -28860,14 +39302,37 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.91, - "Hub \u2764\ufe0f": 40.0, + "Hub \u2764\ufe0f": 42.0, "Available on the hub": true, "Model sha": "58d799575d809c0e80ee6964a546aaa3a8569963", "Flagged": false, "MoE": true }, { - "T": "\ud83d\udfe2", + "T": "\ud83e\udd1d", + "Model": "rombodawg\/EveryoneLLM-7b-Gemma-Base", + "Average \u2b06\ufe0f": 66.69, + "ARC": 64.33, + "HellaSwag": 81.98, + "MMLU": 62.95, + "TruthfulQA": 50.38, + "Winogrande": 76.87, + "GSM8K": 63.61, + "Type": "base merges and moerges", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "89441e1aec14b21bf39ad51994310ad67f48ae97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe9", "Model": "internlm\/internlm2-7b", "Average \u2b06\ufe0f": 66.68, "ARC": 58.02, @@ -28876,14 +39341,14 @@ "TruthfulQA": 48.73, "Winogrande": 83.82, "GSM8K": 63.0, - "Type": "pretrained", + "Type": "continuously pretrained", "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 28.0, "Available on the hub": true, "Model sha": "aac482e5fbfd5a85daa2a8e3aa3a1c5c97331d58", "Flagged": false, @@ -28906,12 +39371,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.8, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "5807ef01a569e3ecda619af66f98271d6bf872f7", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Isaak-Carter\/JOSIE_Beta-3-7B-slerp", + "Average \u2b06\ufe0f": 66.66, + "ARC": 63.4, + "HellaSwag": 84.56, + "MMLU": 64.17, + "TruthfulQA": 48.8, + "Winogrande": 80.43, + "GSM8K": 58.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3754562d668ac4a9903df03628b9dfa52443e501", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Test157t\/Hex-Macaroniac-7b", @@ -28926,11 +39414,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "ae590a93adc146935da5fae38c3cdc7d5d86e16e", "Flagged": false, "MoE": false @@ -28958,6 +39446,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Badgids\/Gonzo-Chat-7B", + "Average \u2b06\ufe0f": 66.63, + "ARC": 65.02, + "HellaSwag": 85.4, + "MMLU": 63.75, + "TruthfulQA": 60.23, + "Winogrande": 77.74, + "GSM8K": 47.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "533fc41b9ff87bc8ba1e1d84a23bb453a3aff966", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Mihaiii\/Pallas-0.5-LASER-0.6", @@ -28981,6 +39492,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Einstein-v4-7B", + "Average \u2b06\ufe0f": 66.62, + "ARC": 64.68, + "HellaSwag": 83.75, + "MMLU": 62.31, + "TruthfulQA": 55.15, + "Winogrande": 76.24, + "GSM8K": 57.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 44.0, + "Available on the hub": true, + "Model sha": "8c831e8878fe7f2f83320c3acfc4de7135bf8fa7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ArianAskari\/NeuralHermes-2.5-Mistral-7B", @@ -29044,7 +39578,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 61.0, + "Hub \u2764\ufe0f": 67.0, "Available on the hub": false, "Model sha": "366a19a3a8e64aea2fc77d648bec5738fb1f89ce", "Flagged": false, @@ -29067,7 +39601,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.8, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "5807ef01a569e3ecda619af66f98271d6bf872f7", "Flagged": false, @@ -29093,7 +39627,7 @@ "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "61aefa2ac956ce0e8ce40aa2521bdb5634452766", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -29142,6 +39676,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nlpguy\/StockFuseChat", + "Average \u2b06\ufe0f": 66.58, + "ARC": 63.14, + "HellaSwag": 84.26, + "MMLU": 63.95, + "TruthfulQA": 45.57, + "Winogrande": 79.48, + "GSM8K": 63.08, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4c9556c99e5e9df6696186d9e741a0765710c436", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_AI_128k_bioMedical", + "Average \u2b06\ufe0f": 66.58, + "ARC": 64.51, + "HellaSwag": 84.99, + "MMLU": 63.66, + "TruthfulQA": 58.69, + "Winogrande": 79.56, + "GSM8K": 48.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "24d2766780b4460654703eb2978c03d575ac289e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NovoCode\/NeuralPaca-7b", @@ -29160,7 +39740,7 @@ "Hub License": "other", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "4e02c1c08c3ce16db8df2a07db559eaab46a3ac4", "Flagged": false, "MoE": false @@ -29188,6 +39768,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "922CA\/Silicon-Monika-7b", + "Average \u2b06\ufe0f": 66.55, + "ARC": 63.14, + "HellaSwag": 82.64, + "MMLU": 62.67, + "TruthfulQA": 52.14, + "Winogrande": 78.22, + "GSM8K": 60.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6cc958abfbbd5f9d3f4221158e729663166d819c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "migtissera\/Tess-10.7B-v1.5", @@ -29211,6 +39814,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "mahiatlinux\/MasherAI-v6-7B", + "Average \u2b06\ufe0f": 66.55, + "ARC": 62.88, + "HellaSwag": 83.94, + "MMLU": 60.56, + "TruthfulQA": 62.56, + "Winogrande": 77.43, + "GSM8K": 51.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "4c1c504c7a9d37720f71722f14856677dd5827ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Locutusque\/OpenHercules-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.55, + "ARC": 64.25, + "HellaSwag": 84.84, + "MMLU": 64.21, + "TruthfulQA": 47.84, + "Winogrande": 78.93, + "GSM8K": 59.21, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2f08ffbda0f39413f34934a526118fb3fbdd6c03", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NExtNewChattingAI\/shark_tank_ai_7b_v2", @@ -29249,7 +39898,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -29257,6 +39906,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Azazelle\/Mocha-Sample-7b-ex", + "Average \u2b06\ufe0f": 66.53, + "ARC": 64.76, + "HellaSwag": 84.35, + "MMLU": 62.2, + "TruthfulQA": 54.18, + "Winogrande": 77.11, + "GSM8K": 56.56, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0da3176b36871025e15c3dac3787cdc4f352e63f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "FuseAI\/FuseChat-7B-VaRM", + "Average \u2b06\ufe0f": 66.52, + "ARC": 62.88, + "HellaSwag": 84.25, + "MMLU": 63.71, + "TruthfulQA": 45.67, + "Winogrande": 79.16, + "GSM8K": 63.46, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 64.0, + "Available on the hub": true, + "Model sha": "5d1e28bac6efc675549060b3babb64945b27d25c", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "openaccess-ai-collective\/dpopenhermes-alpha-v0", @@ -29294,7 +39989,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, @@ -29344,11 +40039,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "0de1702faa89250ae329b3989c487fb0feb9e3f6", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "yanolja\/EEVE-Korean-Instruct-10.8B-v1.0", + "Average \u2b06\ufe0f": 66.48, + "ARC": 64.85, + "HellaSwag": 83.04, + "MMLU": 64.23, + "TruthfulQA": 54.09, + "Winogrande": 81.93, + "GSM8K": 50.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "fb3f5e88e28b6f063f9f3a36c5ae475a31413517", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-original-v2", @@ -29386,8 +40104,8 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 24.15, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -29395,6 +40113,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "Undi95\/C-Based-2x7B", + "Average \u2b06\ufe0f": 66.47, + "ARC": 65.53, + "HellaSwag": 85.0, + "MMLU": 64.59, + "TruthfulQA": 50.16, + "Winogrande": 81.06, + "GSM8K": 52.46, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae2914cb1fc547a441526e1eecd0ea139ec1adc5", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "v2ray\/LLaMA-2-Wizard-70B-QLoRA", @@ -29410,14 +40151,37 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, "Model sha": "4bff676fe29f56d31961794c062aebc36312446e", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FuseAI\/OpenChat-3.5-7B-Solar", + "Average \u2b06\ufe0f": 66.46, + "ARC": 62.97, + "HellaSwag": 84.19, + "MMLU": 63.94, + "TruthfulQA": 45.65, + "Winogrande": 79.48, + "GSM8K": 62.55, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "dc892da6642efb20ea88c3804bf75c0e8759139f", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "rishiraj\/uncensored", @@ -29459,7 +40223,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c9b20b6f34269c27e56759888c5d42bd045e6da7", "Flagged": false, "MoE": false @@ -29482,11 +40246,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "db052d375f389aa264bacac47aeb07538698122d", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-Beta-Ruby-7B", + "Average \u2b06\ufe0f": 66.42, + "ARC": 64.51, + "HellaSwag": 85.57, + "MMLU": 64.2, + "TruthfulQA": 51.04, + "Winogrande": 79.16, + "GSM8K": 54.06, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67d757765597e4b8ee879e9d6a4c2e2a780d6bac", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Brillibits\/Instruct_Llama70B_Dolly15k", @@ -29602,6 +40389,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FuseAI\/OpenChat-3.5-7B-Mixtral", + "Average \u2b06\ufe0f": 66.4, + "ARC": 62.8, + "HellaSwag": 84.24, + "MMLU": 63.95, + "TruthfulQA": 45.68, + "Winogrande": 79.64, + "GSM8K": 62.09, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "566e2d1a010864875443e9b91d4b1c78b216b9d8", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "openaccess-ai-collective\/openhermes-2_5-dpo-no-robots", @@ -29625,6 +40435,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FuseAI\/FuseChat-7B-Slerp", + "Average \u2b06\ufe0f": 66.39, + "ARC": 62.63, + "HellaSwag": 84.17, + "MMLU": 63.9, + "TruthfulQA": 45.62, + "Winogrande": 79.48, + "GSM8K": 62.55, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "19be316337d21c8ba0fb8a15e19257fc814e6a3c", + "Flagged": false, + "MoE": true + }, { "T": "\ud83e\udd1d", "Model": "cris177\/Orca-Hermes-7B-slerp", @@ -29685,7 +40518,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, "Hub \u2764\ufe0f": 0.0, @@ -29734,12 +40567,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, "Model sha": "5252c3d68fcd69d14cc76488d689e0adb76d881f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "cstr\/Spaetzle-v44-7b", + "Average \u2b06\ufe0f": 66.34, + "ARC": 64.59, + "HellaSwag": 84.76, + "MMLU": 61.76, + "TruthfulQA": 54.45, + "Winogrande": 78.77, + "GSM8K": 53.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5f6becfdbc97b1caf280714e5755c00c5ad61cbf", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "sethuiyer\/CodeCalc-Mistral-7B", @@ -29757,12 +40613,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "e03e7b8e6ea737f565848caaf3467b75b646c878", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "hydra-project\/OpenHyperion-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.32, + "ARC": 64.25, + "HellaSwag": 84.86, + "MMLU": 63.86, + "TruthfulQA": 49.92, + "Winogrande": 79.32, + "GSM8K": 55.72, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "85a94bc7584beb08e8df09bad85f06b786f184c4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "snorkelai\/Snorkel-Mistral-PairRM-DPO", @@ -29780,7 +40659,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 95.0, "Available on the hub": true, "Model sha": "e4110a5689e146bc07296218f84ae09129168868", "Flagged": false, @@ -29788,7 +40667,7 @@ }, { "T": "\ud83d\udd36", - "Model": "augtoma\/qCammel-70-x", + "Model": "augtoma\/qCammel70", "Average \u2b06\ufe0f": 66.31, "ARC": 68.34, "HellaSwag": 87.87, @@ -29797,21 +40676,21 @@ "Winogrande": 84.29, "GSM8K": 29.72, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", - "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 23.0, - "Available on the hub": true, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "augtoma\/qCammel-70v1", + "Model": "augtoma\/qCammel-70-x", "Average \u2b06\ufe0f": 66.31, "ARC": 68.34, "HellaSwag": 87.87, @@ -29820,13 +40699,13 @@ "Winogrande": 84.29, "GSM8K": 29.72, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 68.72, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", "Flagged": false, @@ -29850,14 +40729,14 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "augtoma\/qCammel-70", + "Model": "augtoma\/qCammel-70v1", "Average \u2b06\ufe0f": 66.31, "ARC": 68.34, "HellaSwag": 87.87, @@ -29873,14 +40752,14 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "augtoma\/qCammel70", + "Model": "augtoma\/qCammel-70", "Average \u2b06\ufe0f": 66.31, "ARC": 68.34, "HellaSwag": 87.87, @@ -29896,11 +40775,34 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FuseAI\/FuseChat-7B-TA", + "Average \u2b06\ufe0f": 66.31, + "ARC": 62.54, + "HellaSwag": 84.22, + "MMLU": 63.96, + "TruthfulQA": 45.74, + "Winogrande": 79.4, + "GSM8K": 62.02, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "9862833e1c59df274ff426fb09638faa2e0bc9f0", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "garage-bAInd\/Platypus2-70B", @@ -29944,7 +40846,53 @@ "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "ff29fed2a33fc050fd20d0e25b5b23c4a101b074", - "Flagged": true, + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/Worldsim-Hermes-7B", + "Average \u2b06\ufe0f": 66.26, + "ARC": 64.08, + "HellaSwag": 83.45, + "MMLU": 63.12, + "TruthfulQA": 51.52, + "Winogrande": 78.77, + "GSM8K": 56.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a08a049d7b0ada1a9422f1502d103233ba9a9854", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/megamarcoroni-120b", + "Average \u2b06\ufe0f": 66.25, + "ARC": 72.01, + "HellaSwag": 88.94, + "MMLU": 69.88, + "TruthfulQA": 64.24, + "Winogrande": 80.9, + "GSM8K": 21.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 120.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db2d5376b1a1c36efaca83668e1ce6bfcc43356a", + "Flagged": false, "MoE": false }, { @@ -29965,11 +40913,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "d1a30161bd58ed7506ad0ad22fea7f186e065776", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "M4-ai\/Hercules-Qwen1.5-14B", + "Average \u2b06\ufe0f": 66.24, + "ARC": 56.23, + "HellaSwag": 80.6, + "MMLU": 68.73, + "TruthfulQA": 52.03, + "Winogrande": 73.88, + "GSM8K": 65.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1467881f0621f2b3906461c7e656a7fbeddbfd45", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Xwin-LM\/Xwin-LM-70B-V0.1", @@ -30033,7 +41004,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 95.0, "Available on the hub": true, "Model sha": "e4110a5689e146bc07296218f84ae09129168868", "Flagged": false, @@ -30056,7 +41027,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": false, "Model sha": "b00992c26604c9cd496bc41472a05e4c01cd2008", "Flagged": false, @@ -30079,7 +41050,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "a74a9fa5797b75262187fffa173948f1c03e2af4", "Flagged": false, @@ -30125,8 +41096,8 @@ "Merged": false, "Hub License": "other", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, "Model sha": "73491b7bda948e0755f5a6cd655238e0ba73fad6", "Flagged": false, "MoE": false @@ -30177,6 +41148,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_AI_base_128k", + "Average \u2b06\ufe0f": 66.08, + "ARC": 65.1, + "HellaSwag": 84.05, + "MMLU": 63.36, + "TruthfulQA": 58.11, + "Winogrande": 79.24, + "GSM8K": 46.63, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "205a2099382a99c581e822e77ca425fc1dbc269c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Eurdem\/megatron_v4_4x7B", + "Average \u2b06\ufe0f": 66.08, + "ARC": 65.61, + "HellaSwag": 84.1, + "MMLU": 61.64, + "TruthfulQA": 60.51, + "Winogrande": 76.56, + "GSM8K": 48.07, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d5703cd346b1f82c3ed8e7f8083d4c4bfee81242", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "amazingvince\/where-llambo-7b", @@ -30292,6 +41309,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_Uncensored", + "Average \u2b06\ufe0f": 66.04, + "ARC": 63.82, + "HellaSwag": 84.07, + "MMLU": 61.96, + "TruthfulQA": 65.86, + "Winogrande": 78.69, + "GSM8K": 41.85, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3167f5d9a3f0fc7e96f1317ff8f29b4eee106c55", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "seungduk\/KoSOLAR-10.7B-v0.1", @@ -30310,7 +41350,7 @@ "Hub License": "?", "#Params (B)": 10.86, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a4ddde9b0d06f340ff9c29777b4bfd883700c6cd", "Flagged": false, "MoE": false @@ -30332,12 +41372,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 194.0, + "Hub \u2764\ufe0f": 216.0, "Available on the hub": true, "Model sha": "6e2783822f35c376ea96852fe479faa6a8bf09cb", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "KatyTheCutie\/LemonadeRP-4.5.3", + "Average \u2b06\ufe0f": 66.02, + "ARC": 65.1, + "HellaSwag": 84.72, + "MMLU": 64.39, + "TruthfulQA": 57.87, + "Winogrande": 77.74, + "GSM8K": 46.32, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "d84bd91c114a8ae689c3d10c2fcdb8e83300a115", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Paradigm_Shift_7B", + "Average \u2b06\ufe0f": 66.02, + "ARC": 67.92, + "HellaSwag": 83.69, + "MMLU": 59.49, + "TruthfulQA": 66.07, + "Winogrande": 78.69, + "GSM8K": 40.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "c39cf7ba63acf8eaafc7b08d67fac494e64df98e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TokenBender\/pic_7B_mistral_Full_v0.1", @@ -30356,7 +41442,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "64f7a800327466b76697c1f81d88b008274c8861", "Flagged": false, "MoE": false @@ -30376,14 +41462,37 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, "Model sha": "d55e05e9d67418c639933c85a5b9d17c6f531a92", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "0-hero\/Matter-0.1-7B-boost-DPO", + "Average \u2b06\ufe0f": 65.99, + "ARC": 65.02, + "HellaSwag": 83.08, + "MMLU": 61.87, + "TruthfulQA": 60.29, + "Winogrande": 75.61, + "GSM8K": 50.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5bee9978fcf2188f1070b67f6d94be344fdd99c0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-dpo-e1", @@ -30424,7 +41533,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "c79c121d00a7edce5decc7189c32a4411ab26311", "Flagged": false, @@ -30445,14 +41554,37 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "other", "#Params (B)": 72.29, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 172.0, "Available on the hub": true, "Model sha": "bc11a298a0c6a5cd737064db62c6ad20ec6331be", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nbeerbower\/Flammen-Trismegistus-7B", + "Average \u2b06\ufe0f": 65.98, + "ARC": 63.99, + "HellaSwag": 84.79, + "MMLU": 62.45, + "TruthfulQA": 57.12, + "Winogrande": 76.48, + "GSM8K": 51.02, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ef80a33ffebbe3f28f1178f324cf99d12b5f0f0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "DreadPoor\/Bageluccine-7B-slerp", @@ -30467,7 +41599,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -30563,11 +41695,34 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9542702011bf4d282f4b0f0bd79229f5822b6313", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Qwen\/Qwen1.5-72B-Chat", + "Average \u2b06\ufe0f": 65.96, + "ARC": 68.52, + "HellaSwag": 86.42, + "MMLU": 77.44, + "TruthfulQA": 63.9, + "Winogrande": 79.08, + "GSM8K": 20.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 172.0, + "Available on the hub": true, + "Model sha": "1a6ccc1215278f962c794b1848c710c29ef4053d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "dddsaty\/SOLAR_Merge_Adapter_DPO_Orca", @@ -30588,7 +41743,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "0d1d423bab515ce5aee7e7029f86cfabfc26b4d9", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -30608,7 +41763,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": false, "Model sha": "803a3e7f24f61e8cd53ef4133ae22c3ce2568a78", "Flagged": false, @@ -30637,6 +41792,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Zephyr_beta_32k_7B", + "Average \u2b06\ufe0f": 65.93, + "ARC": 63.48, + "HellaSwag": 84.79, + "MMLU": 60.5, + "TruthfulQA": 68.99, + "Winogrande": 77.11, + "GSM8K": 40.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5860071cd3ccbc086e133ae4ba30583b3338a34d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "liminerity\/Blured-Ties-7B", @@ -30677,7 +41855,7 @@ "Merged": false, "Hub License": "wtfpl", "#Params (B)": 14.0, - "Hub \u2764\ufe0f": 98.0, + "Hub \u2764\ufe0f": 105.0, "Available on the hub": true, "Model sha": "34bc2dd73ae5f8738e5bcaaa5591427675f7801f", "Flagged": false, @@ -30723,12 +41901,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "406aeb5ce848dfefbca65d69022ce1de36f9fde4", "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Kazbek-7B", + "Average \u2b06\ufe0f": 65.88, + "ARC": 65.1, + "HellaSwag": 85.2, + "MMLU": 63.41, + "TruthfulQA": 49.43, + "Winogrande": 80.9, + "GSM8K": 51.25, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "890d48a457b7cd7f9aadb23b615afec741792590", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "RaduGabriel\/SirUkrainian2.0DPO", @@ -30747,7 +41948,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cc7f95d454989d6b7c96efb1ba7f89826bb56f3b", "Flagged": false, "MoE": false @@ -30769,7 +41970,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 14.17, - "Hub \u2764\ufe0f": 194.0, + "Hub \u2764\ufe0f": 195.0, "Available on the hub": false, "Model sha": "5eda9482e32a8ea7ed2dc47178f3b491eb207939", "Flagged": false, @@ -30798,6 +41999,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "harshitv804\/MetaMath-Mistral-2x7B", + "Average \u2b06\ufe0f": 65.84, + "ARC": 60.58, + "HellaSwag": 82.59, + "MMLU": 61.87, + "TruthfulQA": 44.8, + "Winogrande": 76.01, + "GSM8K": 69.22, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "193485a4016e12c1a3d3347801648fa4913dbd7c", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "perlthoughts\/Chupacabra-7B-v2.03-128k", @@ -30812,13 +42036,13 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "22bb3c15b2770dfe91e239573b6c35b475a43cbe", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -30844,6 +42068,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "Replete-AI\/Mistral-11b-v0.1", + "Average \u2b06\ufe0f": 65.8, + "ARC": 62.2, + "HellaSwag": 84.65, + "MMLU": 63.11, + "TruthfulQA": 59.23, + "Winogrande": 75.77, + "GSM8K": 49.81, + "Type": "continuously pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 11.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "57eb00a9bf191d5a338c11098fa6e82d5f121d9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Replete-AI\/Mistral-Evolved-11b-v0.1", + "Average \u2b06\ufe0f": 65.8, + "ARC": 62.2, + "HellaSwag": 84.65, + "MMLU": 63.11, + "TruthfulQA": 59.23, + "Winogrande": 75.77, + "GSM8K": 49.81, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 11.17, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "57eb00a9bf191d5a338c11098fa6e82d5f121d9b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "macadeliccc\/laser-polyglot-4x7b", @@ -30907,12 +42177,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 67.0, + "Hub \u2764\ufe0f": 73.0, "Available on the hub": true, "Model sha": "016a7bb03bfcd953860357e1a16d5b333b887d26", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "0-hero\/Matter-0.1-7B-boost-DPO-preview", + "Average \u2b06\ufe0f": 65.77, + "ARC": 64.59, + "HellaSwag": 82.87, + "MMLU": 62.02, + "TruthfulQA": 58.86, + "Winogrande": 75.85, + "GSM8K": 50.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d390fb35a781129efd26d53f7ecdb513c0c3da27", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "kaitchup\/Maixtchup-4x7b", @@ -31000,7 +42293,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "13c7b5f403c0f2af9bf7fce2d4a32deb9054c083", "Flagged": false, "MoE": false @@ -31045,7 +42338,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 69.16, - "Hub \u2764\ufe0f": 33.0, + "Hub \u2764\ufe0f": 35.0, "Available on the hub": true, "Model sha": "feba815b847806df03f23a375f3d4d07fa251134", "Flagged": false, @@ -31097,6 +42390,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_AI_128k_b", + "Average \u2b06\ufe0f": 65.73, + "ARC": 64.08, + "HellaSwag": 84.68, + "MMLU": 63.76, + "TruthfulQA": 57.09, + "Winogrande": 79.16, + "GSM8K": 45.64, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "edf358adffe215b34acf695a4c1243a7e5d47417", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "nextai-team\/Moe-4x7b-reason-code-qa", @@ -31114,7 +42430,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "6a88e94af88e8ab9386cd9f3d3694a68b2428952", "Flagged": false, @@ -31137,7 +42453,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 24.15, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "630daafebf8b8fd6f3959b2e924b49598e8ee2d3", "Flagged": false, @@ -31184,11 +42500,57 @@ "Hub License": "?", "#Params (B)": 70.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a1190dee60b5854e80d340958dc3cc956bc56f68", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral-v2-7b-selfplay-v0", + "Average \u2b06\ufe0f": 65.72, + "ARC": 63.05, + "HellaSwag": 84.88, + "MMLU": 60.78, + "TruthfulQA": 68.14, + "Winogrande": 77.19, + "GSM8K": 40.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "60b1e543f54cc5b803bc4e4f22f8716c472370d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "grimjim\/Mistral-7B-Instruct-demi-merge-v0.2-7B", + "Average \u2b06\ufe0f": 65.71, + "ARC": 63.91, + "HellaSwag": 84.89, + "MMLU": 63.69, + "TruthfulQA": 55.26, + "Winogrande": 78.53, + "GSM8K": 47.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db786274df9d55902a7c5e98a134e63deee1f558", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mistralai\/Mistral-7B-Instruct-v0.2", @@ -31206,7 +42568,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 979.0, + "Hub \u2764\ufe0f": 1591.0, "Available on the hub": true, "Model sha": "c72e5d1908b1e2929ec8fc4c8820e9706af1f80f", "Flagged": false, @@ -31281,6 +42643,144 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ziniuli\/Mistral-7B-ReMax-v0.1", + "Average \u2b06\ufe0f": 65.69, + "ARC": 63.31, + "HellaSwag": 84.98, + "MMLU": 60.76, + "TruthfulQA": 68.16, + "Winogrande": 77.35, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c99152ef7fab26a55a8b9ac7766c394acc54fcad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Corianas\/Neural-Mistral-7B", + "Average \u2b06\ufe0f": 65.69, + "ARC": 63.4, + "HellaSwag": 85.59, + "MMLU": 60.92, + "TruthfulQA": 69.26, + "Winogrande": 77.43, + "GSM8K": 37.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0744af8f77f61b0e182f6d5204354c71534f3992", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/Mistral-7B-Instruct-v2-sp-v0.1", + "Average \u2b06\ufe0f": 65.68, + "ARC": 63.05, + "HellaSwag": 84.84, + "MMLU": 60.75, + "TruthfulQA": 68.22, + "Winogrande": 77.11, + "GSM8K": 40.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8dfe19f4bda45edfab91f895e28ca41b251117cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/Mistral-7B-Instruct-v0.2-sp-v0", + "Average \u2b06\ufe0f": 65.68, + "ARC": 63.05, + "HellaSwag": 84.84, + "MMLU": 60.75, + "TruthfulQA": 68.22, + "Winogrande": 77.11, + "GSM8K": 40.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3df848493713aafe17011d7dfbe2c8b11c1b364f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "localfultonextractor\/Erosumika-7B-v3-0.2", + "Average \u2b06\ufe0f": 65.65, + "ARC": 67.75, + "HellaSwag": 84.95, + "MMLU": 60.0, + "TruthfulQA": 55.77, + "Winogrande": 81.53, + "GSM8K": 43.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "a634a34eb846fb891c58e45b82997c56abdac4c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Einstein-v5-v0.2-7B", + "Average \u2b06\ufe0f": 65.65, + "ARC": 60.92, + "HellaSwag": 80.99, + "MMLU": 61.02, + "TruthfulQA": 52.59, + "Winogrande": 78.69, + "GSM8K": 59.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "1b5e6e0bbefff2b7bbc15d11c15fa1ac3696fabd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "SC44\/Mistral-7B-private-spef", @@ -31322,11 +42822,80 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "420f54afd10959bb1c86b485245349cd437960b5", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral-v2-7b-selfplay-low-tmp", + "Average \u2b06\ufe0f": 65.63, + "ARC": 63.05, + "HellaSwag": 84.91, + "MMLU": 60.76, + "TruthfulQA": 68.13, + "Winogrande": 77.35, + "GSM8K": 39.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "78caf2641e8b84495d5199b81e51920c7b10285e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ziniuli\/Mistral-7B-ReMax-v0.1", + "Average \u2b06\ufe0f": 65.63, + "ARC": 63.31, + "HellaSwag": 84.98, + "MMLU": 60.89, + "TruthfulQA": 68.11, + "Winogrande": 77.03, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c99152ef7fab26a55a8b9ac7766c394acc54fcad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral-v2-7b-selfplay-v0-test", + "Average \u2b06\ufe0f": 65.61, + "ARC": 62.97, + "HellaSwag": 84.86, + "MMLU": 60.64, + "TruthfulQA": 67.91, + "Winogrande": 77.58, + "GSM8K": 39.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e34f3b09c03a9a96e1a76dfbd57a88a99c82a595", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "perlthoughts\/Mistral-7B-Instruct-v0.2-2x7B-MoE", @@ -31344,7 +42913,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "46a2d11c1025e6ddec0fe35093d39e2e16170ca2", "Flagged": false, @@ -31365,10 +42934,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": false, "Model sha": "e552ddca841a2b86e36bbe5f99840afedfdbcd14", "Flagged": false, "MoE": false @@ -31442,6 +43011,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "nonetrix\/pippafeet-11B-0.1", + "Average \u2b06\ufe0f": 65.56, + "ARC": 63.65, + "HellaSwag": 82.25, + "MMLU": 65.03, + "TruthfulQA": 65.12, + "Winogrande": 81.53, + "GSM8K": 35.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.6, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ff8da0fb475e20f68bce8b8141d172df3c4f0ffb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/Mistral-7B-Instruct-v0.2-Selfplay-v0", + "Average \u2b06\ufe0f": 65.56, + "ARC": 62.8, + "HellaSwag": 84.74, + "MMLU": 60.6, + "TruthfulQA": 67.35, + "Winogrande": 77.58, + "GSM8K": 40.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "636a1aede230bc57c951994992ec0c01c1d927af", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "JosephusCheung\/Yee-34B-200K-Chat", @@ -31460,11 +43075,34 @@ "Hub License": "?", "#Params (B)": 34.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "94bc30449e41628f59dd965cb7d9a8eb53ce9a45", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ConvexAI\/Julianne-2x7B-bf16", + "Average \u2b06\ufe0f": 65.55, + "ARC": 63.74, + "HellaSwag": 82.81, + "MMLU": 61.57, + "TruthfulQA": 55.91, + "Winogrande": 77.74, + "GSM8K": 51.55, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f2a976852944787c5e2d4014d8d1220ef417e8e7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Delcos\/Velara-11B-V2", @@ -31534,6 +43172,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Badgids\/Gonzo-Code-7B", + "Average \u2b06\ufe0f": 65.51, + "ARC": 61.26, + "HellaSwag": 83.67, + "MMLU": 62.77, + "TruthfulQA": 56.7, + "Winogrande": 77.27, + "GSM8K": 51.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8318630caf9e174e1ac39c3f1b71bd3cbffd423c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "pankajmathur\/Lima_Unchained_70b", @@ -31575,7 +43236,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ca3789cd6b683e97dcd6a5f0367f90a63d7a4e7b", "Flagged": false, "MoE": false @@ -31640,15 +43301,38 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "952c34cfb588ac4fe955b324ce263b91982f2ce9", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "invalid-coder\/dolphin-2.1-mistral-7b-snr-laser", + "Average \u2b06\ufe0f": 65.5, + "ARC": 63.82, + "HellaSwag": 84.78, + "MMLU": 63.63, + "TruthfulQA": 55.24, + "Winogrande": 78.3, + "GSM8K": 47.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7c83d0e9f7af82ee97bccf1ef6554561c358d43", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/bagel-7b-v0.1", @@ -31666,7 +43350,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "10ac045905d13da0e2be8e647cfe3e5ac8444894", "Flagged": false, @@ -31689,7 +43373,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 10.7, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "ae32ccb01cc971cfb36370876bf8981db243b2a3", "Flagged": false, @@ -31804,12 +43488,35 @@ "Merged": false, "Hub License": "unknown", "#Params (B)": 179.52, - "Hub \u2764\ufe0f": 1044.0, + "Hub \u2764\ufe0f": 1073.0, "Available on the hub": true, "Model sha": "71a1a70b629e9963f7b4601e82f3f9079d48011e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "LeroyDyer\/Mixtral_AI_Cyber_3.0", + "Average \u2b06\ufe0f": 65.46, + "ARC": 62.46, + "HellaSwag": 84.02, + "MMLU": 61.91, + "TruthfulQA": 58.21, + "Winogrande": 80.19, + "GSM8K": 45.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b869a301cb7dab92b9693366c42423b49a2f5fe0", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "Mihaiii\/Metis-0.3", @@ -31925,6 +43632,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Eurdem\/megatron_v3_2x7B", + "Average \u2b06\ufe0f": 65.4, + "ARC": 66.38, + "HellaSwag": 83.71, + "MMLU": 61.53, + "TruthfulQA": 55.5, + "Winogrande": 79.08, + "GSM8K": 46.17, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "7556a4cd977e687916d943db245fcf6c03c57a18", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "garage-bAInd\/Camel-Platypus2-70B", @@ -31965,7 +43695,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 68.0, + "Hub \u2764\ufe0f": 69.0, "Available on the hub": true, "Model sha": "33da87ba6d90662c6a00535bd628e5b39b3afd3b", "Flagged": false, @@ -32010,7 +43740,7 @@ "Precision": "4bit", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 3.86, + "#Params (B)": 7.0, "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "4d104982c9759ae57fa482280c50b1950e51fd48", @@ -32031,13 +43761,13 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "73641ebe6ba450a83f6e80ed919fba48cc5f2837", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -32057,12 +43787,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 274.0, + "Hub \u2764\ufe0f": 303.0, "Available on the hub": true, "Model sha": "a99ec35331cbfc9da596af7d4538fe2efecff03c", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "BarraHome\/Lucie-7B-v0.2-16bit", + "Average \u2b06\ufe0f": 65.3, + "ARC": 62.12, + "HellaSwag": 84.83, + "MMLU": 60.45, + "TruthfulQA": 67.65, + "Winogrande": 76.87, + "GSM8K": 39.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "38b6ff5f24f4069dedad1025b2b09c156af9c310", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BarraHome\/Mistroll-7B-v0.3-16bit", @@ -32224,6 +43977,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "ContextualAI\/Contextual_KTO_Mistral_PairRM", + "Average \u2b06\ufe0f": 65.26, + "ARC": 64.76, + "HellaSwag": 85.52, + "MMLU": 60.28, + "TruthfulQA": 71.67, + "Winogrande": 75.53, + "GSM8K": 33.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "bdf7fe0202e81a9409ae92eada6804efa205d061", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Fredithefish\/MadMix-v0.1", @@ -32261,14 +44037,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "93b3807b8fa38b9c95267117d25055bbd3eab29b", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udcac", @@ -32295,7 +44071,7 @@ }, { "T": "\ud83d\udd36", - "Model": "BarraHome\/Mistroll-7B-v0.1-16bit", + "Model": "BarraHome\/Lucie-7b-3e-5", "Average \u2b06\ufe0f": 65.23, "ARC": 62.2, "HellaSwag": 84.81, @@ -32312,13 +44088,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "db9f03ed4f6d5e8c8ccdcb7ad1e66d527dfcf5fc", + "Model sha": "38901d0e7baa164636a8ab30a0b54eafcecc7b93", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "BarraHome\/Wistral-7B-Instruct-v0.3", + "Model": "BarraHome\/Mistroll-7B-v0.1-16bit", "Average \u2b06\ufe0f": 65.23, "ARC": 62.2, "HellaSwag": 84.81, @@ -32335,13 +44111,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "541d36b0dcaf8e0e9c791c0b54e5358fafd1aebb", + "Model sha": "db9f03ed4f6d5e8c8ccdcb7ad1e66d527dfcf5fc", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "BarraHome\/Lucie-7b-3e-5", + "Model": "BarraHome\/Lucie-7b", "Average \u2b06\ufe0f": 65.23, "ARC": 62.2, "HellaSwag": 84.81, @@ -32358,13 +44134,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "38901d0e7baa164636a8ab30a0b54eafcecc7b93", + "Model sha": "ffbb35e5ad00d0c51a626d122ce07a5fbf7759ad", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "BarraHome\/Wistral-7B-Instruct-v0.4", + "Model": "BarraHome\/Wistral-7B-Instruct-v0.3", "Average \u2b06\ufe0f": 65.23, "ARC": 62.2, "HellaSwag": 84.81, @@ -32381,13 +44157,13 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "6f75a5559ef6008886b9abbcf5df998db43edc00", + "Model sha": "541d36b0dcaf8e0e9c791c0b54e5358fafd1aebb", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "BarraHome\/Lucie-7b", + "Model": "BarraHome\/Wistral-7B-Instruct-v0.4", "Average \u2b06\ufe0f": 65.23, "ARC": 62.2, "HellaSwag": 84.81, @@ -32404,7 +44180,7 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "ffbb35e5ad00d0c51a626d122ce07a5fbf7759ad", + "Model sha": "6f75a5559ef6008886b9abbcf5df998db43edc00", "Flagged": false, "MoE": false }, @@ -32517,12 +44293,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "bd19912eb652fd76165938179abd3b54cacb85fa", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "csujeong\/Gemma-7B-Finetuning-JCS-Ko-Ins", + "Average \u2b06\ufe0f": 65.18, + "ARC": 62.46, + "HellaSwag": 82.78, + "MMLU": 66.23, + "TruthfulQA": 48.6, + "Winogrande": 79.08, + "GSM8K": 51.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "54ded4775e2db352629004939236918da8abc9a4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "DreadPoor\/ToppyEvil-7B-slerp", @@ -32537,7 +44336,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -32561,9 +44360,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 12.88, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "5ea651448fbeb313665d66187416233b865db7f1", "Flagged": false, @@ -32592,6 +44391,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Mistral-7B-Instruct-KhanAcademy-v0.2", + "Average \u2b06\ufe0f": 65.11, + "ARC": 62.03, + "HellaSwag": 82.98, + "MMLU": 61.68, + "TruthfulQA": 64.22, + "Winogrande": 77.58, + "GSM8K": 42.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "dafd4df37ea9817de0b18af1ea8d0ad124c4095a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "KnutJaegersberg\/internlm-20b-llama", @@ -32655,12 +44477,58 @@ "Merged": false, "Hub License": "agpl-3.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "823e103126393a0ba4a9cc6d082ab4cda54413ec", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/fc-dolphin-2.6-mistral-7b-dpo-laser", + "Average \u2b06\ufe0f": 65.04, + "ARC": 62.97, + "HellaSwag": 84.18, + "MMLU": 63.65, + "TruthfulQA": 57.75, + "Winogrande": 78.37, + "GSM8K": 43.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "a5cb1123f93521d1febc9c73dd110e1ca0016bf6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "invalid-coder\/dolphin-2.1-mistral-7b-snr-math-laser", + "Average \u2b06\ufe0f": 65.03, + "ARC": 63.31, + "HellaSwag": 84.29, + "MMLU": 63.02, + "TruthfulQA": 54.75, + "Winogrande": 77.58, + "GSM8K": 47.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8bab5ff5eeff2bdd8b591059b7079edd5da4b351", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Azazelle\/Sina-Loki-7b-Merge", @@ -32698,7 +44566,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -32724,12 +44592,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 165.0, + "Hub \u2764\ufe0f": 177.0, "Available on the hub": true, "Model sha": "2022924c0bb13588308d429e0b7f51568c07629c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/DarkSapling-7B-v2.0", + "Average \u2b06\ufe0f": 64.98, + "ARC": 64.16, + "HellaSwag": 85.1, + "MMLU": 64.37, + "TruthfulQA": 52.21, + "Winogrande": 78.61, + "GSM8K": 45.41, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "b62ede72cb044efe88017d7d5eb178d9d807ef1e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/OpenOrca-Zephyr-7B", @@ -32816,7 +44707,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "0dd712293d5b914d53f1e1f35922cd023ba98047", "Flagged": false, @@ -32839,12 +44730,81 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "8f3198a3e235d7c1ae56befbe8fb14a974acdf69", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_Chat_X", + "Average \u2b06\ufe0f": 64.94, + "ARC": 65.53, + "HellaSwag": 84.93, + "MMLU": 61.5, + "TruthfulQA": 56.15, + "Winogrande": 77.03, + "GSM8K": 44.5, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8c4fda57602b78d3a3608e1cc3853bd64f663b04", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "LeroyDyer\/Mixtral_AI_128k", + "Average \u2b06\ufe0f": 64.94, + "ARC": 63.23, + "HellaSwag": 84.62, + "MMLU": 64.24, + "TruthfulQA": 52.43, + "Winogrande": 79.56, + "GSM8K": 45.56, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "75fc3545fc6671a519a81cbbc5efb7f1b95c8d14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "maldv\/winter-garden-7b-delta", + "Average \u2b06\ufe0f": 64.93, + "ARC": 64.16, + "HellaSwag": 84.37, + "MMLU": 60.38, + "TruthfulQA": 67.95, + "Winogrande": 76.72, + "GSM8K": 36.01, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d541081d69248a76260278f4bbc89d8811c6a4a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ehartford\/dolphin-2.2.1-mistral-7b", @@ -32863,7 +44823,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "001b48e9aebffb395c698af47b6b48364cc3cbe8", "Flagged": false, "MoE": false @@ -32886,11 +44846,34 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d366f84cef3a084c6c3dc87b304f0937080c2a6d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "localfultonextractor\/Erosumika-7B", + "Average \u2b06\ufe0f": 64.92, + "ARC": 62.88, + "HellaSwag": 85.9, + "MMLU": 60.64, + "TruthfulQA": 67.59, + "Winogrande": 75.3, + "GSM8K": 37.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "fe495970cdaf66b16b2dc77567adb7bf3fe7fe90", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cognitivecomputations\/dolphin-2.6-mistral-7b", @@ -32908,7 +44891,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 94.0, + "Hub \u2764\ufe0f": 97.0, "Available on the hub": true, "Model sha": "61981ccfb93bad331c8d3da97aafeb13596afc9d", "Flagged": false, @@ -32956,7 +44939,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 94.0, + "Hub \u2764\ufe0f": 97.0, "Available on the hub": true, "Model sha": "61981ccfb93bad331c8d3da97aafeb13596afc9d", "Flagged": false, @@ -32979,12 +44962,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "7d8702ad9d9da7871492ce8843fdb7308a42b3f4", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Joseph717171\/Genstruct-10.7B", + "Average \u2b06\ufe0f": 64.89, + "ARC": 60.84, + "HellaSwag": 82.81, + "MMLU": 60.27, + "TruthfulQA": 46.66, + "Winogrande": 76.8, + "GSM8K": 61.94, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "619648c528f000c38a6de60c69b689caa210bbc5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jarradh\/llama2_70b_chat_uncensored", @@ -33002,12 +45008,58 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 56.0, + "Hub \u2764\ufe0f": 64.0, "Available on the hub": true, "Model sha": "34b23982a9a996adc8f45c4c2eac7245c4e251b3", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "prhegde\/merge-aanaphi-phi2-orage-3b", + "Average \u2b06\ufe0f": 64.87, + "ARC": 63.57, + "HellaSwag": 77.42, + "MMLU": 58.21, + "TruthfulQA": 53.47, + "Winogrande": 74.98, + "GSM8K": 61.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6396a99299f440c7d7ec93786d7874a49accce7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "0-hero\/Matter-0.1-7B-DPO-preview", + "Average \u2b06\ufe0f": 64.87, + "ARC": 62.71, + "HellaSwag": 82.99, + "MMLU": 62.7, + "TruthfulQA": 45.79, + "Winogrande": 78.85, + "GSM8K": 56.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "78040e4754051df49dd907cf1fd46a6b8a6cc30f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TeeZee\/Kyllene-v1.0", @@ -33022,7 +45074,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 56.7, "Hub \u2764\ufe0f": 0.0, @@ -33031,6 +45083,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "krevas\/SOLAR-10.7B", + "Average \u2b06\ufe0f": 64.86, + "ARC": 74.32, + "HellaSwag": 89.05, + "MMLU": 62.94, + "TruthfulQA": 80.33, + "Winogrande": 82.56, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "9c85e654ecc292f4491e332f7f25e6870f166f1e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "jondurbin\/bagel-7b-v0.4", @@ -33071,7 +45146,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.29, - "Hub \u2764\ufe0f": 32.0, + "Hub \u2764\ufe0f": 42.0, "Available on the hub": true, "Model sha": "9c96e8cefc1079ef566cc46fc9b60b52dc36f583", "Flagged": false, @@ -33100,6 +45175,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "runkai\/PascalHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 64.81, + "ARC": 63.82, + "HellaSwag": 83.75, + "MMLU": 62.22, + "TruthfulQA": 53.72, + "Winogrande": 77.11, + "GSM8K": 48.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17a4070a6e2515ef3e2dfb690d171e0a047aa3b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "TeeZee\/DarkSapling-7B-v1.1", @@ -33117,12 +45215,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "0064fc89ee6ce11c01d9061845e1d6498a91ab1a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "NeuralNovel\/Ignis-7B-DPO", + "Average \u2b06\ufe0f": 64.77, + "ARC": 66.3, + "HellaSwag": 84.85, + "MMLU": 58.99, + "TruthfulQA": 65.46, + "Winogrande": 79.95, + "GSM8K": 33.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "4794b5e366ff56097a1136715415748822fba9d4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "yanolja\/KoSOLAR-10.7B-v0.3", @@ -33146,6 +45267,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Dykh-Tau-7B", + "Average \u2b06\ufe0f": 64.76, + "ARC": 63.74, + "HellaSwag": 84.67, + "MMLU": 63.79, + "TruthfulQA": 47.25, + "Winogrande": 80.03, + "GSM8K": 49.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f2036b05109e411e358253449b5a66f967d27ba4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NeuralNovel\/Tanuki-7B-v0.1", @@ -33163,12 +45307,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "699ab2535487aee7cfd8d55ad928805b310c4b17", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/mistral-7b-v0.1-layla-v3", + "Average \u2b06\ufe0f": 64.73, + "ARC": 61.77, + "HellaSwag": 83.41, + "MMLU": 64.26, + "TruthfulQA": 43.2, + "Winogrande": 79.72, + "GSM8K": 56.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3fd903c921129317a5002b67df39995040acaebc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v17.1-32k", @@ -33207,10 +45374,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4cded6e49d74571408be7acf13a8e0ad7f5bf79e", "Flagged": false, "MoE": false @@ -33261,6 +45428,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/Open_Neural_Monarch_Maidv0.2", + "Average \u2b06\ufe0f": 64.72, + "ARC": 63.31, + "HellaSwag": 82.6, + "MMLU": 64.21, + "TruthfulQA": 43.04, + "Winogrande": 79.08, + "GSM8K": 56.1, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "608e14c72451900c353ad4cde064485c4b5d2490", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "MaziyarPanahi\/WizardLM-Math-70B-TIES-v0.1", @@ -33307,6 +45497,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "l3utterfly\/mistral-7b-v0.1-layla-v4", + "Average \u2b06\ufe0f": 64.69, + "ARC": 62.29, + "HellaSwag": 83.36, + "MMLU": 64.32, + "TruthfulQA": 43.14, + "Winogrande": 79.56, + "GSM8K": 55.5, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 34.0, + "Available on the hub": true, + "Model sha": "c98e0493e7651e6acb90cf58b5f06d0b15486bbf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v5-9b", + "Average \u2b06\ufe0f": 64.69, + "ARC": 62.46, + "HellaSwag": 78.41, + "MMLU": 69.81, + "TruthfulQA": 52.78, + "Winogrande": 76.32, + "GSM8K": 48.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.83, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "aa2232946290c89581c39172fe048fd70c5b6e92", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-mistral-7b-dare-0.85", @@ -33344,7 +45580,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, + "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 55.59, "Hub \u2764\ufe0f": 9.0, @@ -33399,6 +45635,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Hermetic-Platypus-B-2x7B", + "Average \u2b06\ufe0f": 64.65, + "ARC": 59.47, + "HellaSwag": 82.95, + "MMLU": 62.15, + "TruthfulQA": 61.49, + "Winogrande": 77.43, + "GSM8K": 44.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1972aa1c2ad8f1b808efa9bce98ec154cd361264", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "smelborp\/MixtralOrochi8x7B", @@ -33416,10 +45675,10 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "e88684d163fd3e789c40261c5b68244bb72bd706", - "Flagged": true, + "Flagged": false, "MoE": true }, { @@ -33514,6 +45773,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "vishnukv\/WestSeverusJaskier-dare-ties-7b-32k", + "Average \u2b06\ufe0f": 64.57, + "ARC": 67.75, + "HellaSwag": 87.02, + "MMLU": 61.18, + "TruthfulQA": 73.05, + "Winogrande": 82.4, + "GSM8K": 16.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "480c92aacda73c75bd1d4503c76e040952bed15f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Hermetic-Platypus-C-2x7B", + "Average \u2b06\ufe0f": 64.56, + "ARC": 59.3, + "HellaSwag": 82.75, + "MMLU": 62.24, + "TruthfulQA": 60.81, + "Winogrande": 78.14, + "GSM8K": 44.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "777b95105f6e8e5a493cb3b38a21a6534a24d784", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "proto-llm\/uniwiz-7B-v0.2", @@ -33606,6 +45911,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/mistral-7b-zephyr-dpo", + "Average \u2b06\ufe0f": 64.53, + "ARC": 63.74, + "HellaSwag": 85.79, + "MMLU": 61.98, + "TruthfulQA": 56.61, + "Winogrande": 78.22, + "GSM8K": 40.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "ac80a1ae40341ea97a5381e4ce509ebd86f4ae72", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "genaicore3434\/Mistral-7b-instruct-v0.2-summ-sft-bf16-e2", @@ -33738,7 +46066,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "08daa40fbe05366466f96c92deb775d1b9b04669", "Flagged": false, @@ -33761,7 +46089,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 55.59, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "dc4ed42fc886c3d912fc0aa3b19cf5c92bfb55d7", "Flagged": false, @@ -33830,7 +46158,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": true, "Model sha": "0aeb810af28e2910a92b929c21b931a5c06073de", "Flagged": false, @@ -33859,6 +46187,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-0-2", + "Average \u2b06\ufe0f": 64.47, + "ARC": 62.2, + "HellaSwag": 82.19, + "MMLU": 65.57, + "TruthfulQA": 47.63, + "Winogrande": 78.22, + "GSM8K": 51.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f1701204d496edcec40e97377dcf46da3060b100", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "OpenBuddy\/openbuddy-llama-65b-v8-bf16", @@ -33974,6 +46325,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-Mistral-7b-v1.0", + "Average \u2b06\ufe0f": 64.44, + "ARC": 60.75, + "HellaSwag": 81.87, + "MMLU": 63.13, + "TruthfulQA": 51.49, + "Winogrande": 76.32, + "GSM8K": 53.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.37, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6a11ae478588e7633b8d45fbcbf31a542e259c81", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NurtureAI\/Starling-LM-11B-alpha-v1", @@ -33992,14 +46366,14 @@ "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b2b3b9fc069a8b5d8be82f68f0f578a6f23e9e5f", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "hedronstone\/OpenHermes-7B-Symbolic", + "Model": "hedronstone\/OpenHermes-7B-Reasoner", "Average \u2b06\ufe0f": 64.44, "ARC": 63.14, "HellaSwag": 82.73, @@ -34008,21 +46382,21 @@ "Winogrande": 75.85, "GSM8K": 53.45, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "23eb76553aa37cd48c1f2d8a314d78fd3ead53f6", + "Available on the hub": false, + "Model sha": "d26f2defbf9f40a65dbb2ead08c79cd61096ed08", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "hedronstone\/OpenHermes-7B-Reasoner", + "Model": "hedronstone\/OpenHermes-7B-Symbolic", "Average \u2b06\ufe0f": 64.44, "ARC": 63.14, "HellaSwag": 82.73, @@ -34031,15 +46405,15 @@ "Winogrande": 75.85, "GSM8K": 53.45, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "d26f2defbf9f40a65dbb2ead08c79cd61096ed08", + "Model sha": "23eb76553aa37cd48c1f2d8a314d78fd3ead53f6", "Flagged": false, "MoE": false }, @@ -34061,11 +46435,34 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b6512d2a2202e685da461ff876a1ffb707034c97", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "NeuralNovel\/Ignis-7B-DPO-Laser", + "Average \u2b06\ufe0f": 64.41, + "ARC": 65.19, + "HellaSwag": 84.57, + "MMLU": 58.56, + "TruthfulQA": 66.24, + "Winogrande": 80.43, + "GSM8K": 31.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "2094cd52a4f7835b2d38983e889b693f841c6eb8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "elinas\/chronos-70b-v2", @@ -34107,11 +46504,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "49c083289b20fbe14e7002fa71eed01127b2fbf5", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/Yi-34B-200K-AEZAKMI-XLCTX-v3", + "Average \u2b06\ufe0f": 64.39, + "ARC": 64.85, + "HellaSwag": 84.76, + "MMLU": 74.48, + "TruthfulQA": 37.14, + "Winogrande": 81.06, + "GSM8K": 44.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "93d5dc04ee4a3c62a6dae9c5c6d62ed999cd6d7b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "xxyyy123\/Mistral-dpo-v1", @@ -34130,11 +46550,149 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3c677a659bffbccbd8cf5ea75d198541ea2ec990", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Hermetic-Platypus-C-2x7B", + "Average \u2b06\ufe0f": 64.39, + "ARC": 58.96, + "HellaSwag": 82.77, + "MMLU": 62.08, + "TruthfulQA": 60.87, + "Winogrande": 77.74, + "GSM8K": 43.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "778903b24f320ce4e46d9e43ff296a64a6b835b6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/gemma-orchid-7b-dpo", + "Average \u2b06\ufe0f": 64.37, + "ARC": 62.88, + "HellaSwag": 80.95, + "MMLU": 61.41, + "TruthfulQA": 53.27, + "Winogrande": 77.51, + "GSM8K": 50.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "de936b0952f5c78ba6817b3ff91d3ab85e2e90fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mahiatlinux\/MasherAI-7B-v3", + "Average \u2b06\ufe0f": 64.36, + "ARC": 63.99, + "HellaSwag": 82.19, + "MMLU": 64.04, + "TruthfulQA": 47.63, + "Winogrande": 81.14, + "GSM8K": 47.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d1395cb02d5de6ed10f8ed3dbc4a570fe426e651", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/mistral_9B_instruct_v0.2", + "Average \u2b06\ufe0f": 64.32, + "ARC": 61.01, + "HellaSwag": 82.77, + "MMLU": 60.54, + "TruthfulQA": 63.9, + "Winogrande": 78.14, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "9a8e0e208cefc52f8e33c765720bf3c95cca38b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "liminerity\/m.star.7b", + "Average \u2b06\ufe0f": 64.32, + "ARC": 60.15, + "HellaSwag": 80.96, + "MMLU": 58.28, + "TruthfulQA": 53.93, + "Winogrande": 78.53, + "GSM8K": 54.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1de2c02db0939bd92748b207d8f56dc06105712a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/Phigments12", + "Average \u2b06\ufe0f": 64.31, + "ARC": 62.63, + "HellaSwag": 77.1, + "MMLU": 58.43, + "TruthfulQA": 51.71, + "Winogrande": 74.66, + "GSM8K": 61.33, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "387d840de390441faa8bdab7b44b0c65ec0abfa8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "v1olet\/v1olet_merged_dpo_7B_v4", @@ -34153,7 +46711,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aa1b6363990ed2f180b2a22986cecc3afa4d12c8", "Flagged": false, "MoE": false @@ -34181,6 +46739,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Elly_7B", + "Average \u2b06\ufe0f": 64.29, + "ARC": 63.57, + "HellaSwag": 83.48, + "MMLU": 62.8, + "TruthfulQA": 56.27, + "Winogrande": 78.77, + "GSM8K": 40.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "eb149860bd442475828fe2ce71069ec7dbcea3b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "google\/gemma-7b", @@ -34198,12 +46779,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 8.54, - "Hub \u2764\ufe0f": 1509.0, + "Hub \u2764\ufe0f": 2698.0, "Available on the hub": true, "Model sha": "7646584ed746494da9e1058b1be53d1be8b2ee73", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/gemma-7b-experiment", + "Average \u2b06\ufe0f": 64.29, + "ARC": 61.09, + "HellaSwag": 82.47, + "MMLU": 66.03, + "TruthfulQA": 44.91, + "Winogrande": 78.45, + "GSM8K": 52.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "299334f1358f38b40480b232f94a637c5636e77b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "maywell\/PiVoT-10.7B-Mistral-v0.2", @@ -34219,13 +46823,59 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-sa-4.0", - "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 5.0, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a496457d0743b6030ffbb96dad2dc6a62d143943", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Hermetic-Platypus-D-2x7B", + "Average \u2b06\ufe0f": 64.24, + "ARC": 58.87, + "HellaSwag": 82.89, + "MMLU": 61.96, + "TruthfulQA": 61.02, + "Winogrande": 77.43, + "GSM8K": 43.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d64cb44e12b446b1e532ecd6a8f6f8c60e1ee095", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Hermetic-Platypus-A-2x7B", + "Average \u2b06\ufe0f": 64.23, + "ARC": 59.3, + "HellaSwag": 82.89, + "MMLU": 62.0, + "TruthfulQA": 61.08, + "Winogrande": 77.66, + "GSM8K": 42.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "a496457d0743b6030ffbb96dad2dc6a62d143943", + "Model sha": "6e102b60cde5dc38374bf4906a8cdeb0411321f0", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", @@ -34244,12 +46894,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "b396464b51acb625c8bf1875fb8fb0ebe973e9a3", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/mistral-7b-v0.1-layla-v4-chatml", + "Average \u2b06\ufe0f": 64.22, + "ARC": 62.03, + "HellaSwag": 83.4, + "MMLU": 63.74, + "TruthfulQA": 43.03, + "Winogrande": 79.32, + "GSM8K": 53.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "5642d735943dd13df17a89dfe52839a2f10ee607", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "genaicore3434\/Mistral-7b-instruct-v0.2-summ-sft-bf16-e1", @@ -34291,7 +46964,7 @@ "Hub License": "?", "#Params (B)": 68.72, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5095384f1b7bb6e23a987f95589e66e21ae854ef", "Flagged": false, "MoE": false @@ -34314,7 +46987,7 @@ "Hub License": "cc-by-4.0", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "dc2dcdfe71a5f9a059d98c8e573df3254ff5bdd0", "Flagged": false, "MoE": false @@ -34336,7 +47009,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.7, - "Hub \u2764\ufe0f": 25.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "ca6148593cca082392faa5d1b0b72995b672eddb", "Flagged": false, @@ -34365,6 +47038,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "222limin\/Liph-36-imatwarwithmyself", + "Average \u2b06\ufe0f": 64.19, + "ARC": 62.37, + "HellaSwag": 77.16, + "MMLU": 58.14, + "TruthfulQA": 52.28, + "Winogrande": 75.3, + "GSM8K": 59.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0ba0be5ca330c67a3a248372b7513b3b94441352", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "lodrick-the-lafted\/Platyboros-Instruct-7B", @@ -34405,12 +47101,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "f16526d9bb814dc10adc911f94e8c7a520beb5b6", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "abhishekchohan\/Yi-9B-Forest-DPO-v1.0", + "Average \u2b06\ufe0f": 64.11, + "ARC": 59.81, + "HellaSwag": 78.6, + "MMLU": 70.02, + "TruthfulQA": 50.98, + "Winogrande": 76.87, + "GSM8K": 48.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 9.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af6d3cc25c901619d118ebf616f7a5902413a4ea", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/Einstein-v3-7B", @@ -34426,9 +47145,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "632d22a529a04a16f0297320ba221ef4091a797c", "Flagged": false, @@ -34436,24 +47155,24 @@ }, { "T": "\ud83d\udd36", - "Model": "PulsarAI\/Einstein-v3-7B", - "Average \u2b06\ufe0f": 64.09, + "Model": "liminerity\/Liph.42", + "Average \u2b06\ufe0f": 64.08, "ARC": 62.29, - "HellaSwag": 83.01, - "MMLU": 63.32, - "TruthfulQA": 51.18, - "Winogrande": 79.95, - "GSM8K": 44.81, + "HellaSwag": 77.12, + "MMLU": 58.2, + "TruthfulQA": 52.08, + "Winogrande": 74.98, + "GSM8K": 59.82, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", + "Architecture": "PhiForCausalLM", "Weight type": "Original", - "Precision": "bfloat16", + "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "632d22a529a04a16f0297320ba221ef4091a797c", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b63ea4fb0fda33ac633f972094a5e23b05c92021", "Flagged": false, "MoE": false }, @@ -34480,6 +47199,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83e\udd1d", + "Model": "Azazelle\/Mocha-Dare-7b-ex", + "Average \u2b06\ufe0f": 64.08, + "ARC": 61.26, + "HellaSwag": 81.6, + "MMLU": 60.77, + "TruthfulQA": 53.44, + "Winogrande": 73.8, + "GSM8K": 53.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4cedadeb455e4507b4fc1a4ac14b0340ed43cd05", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "sethuiyer\/Herculoid-2.0", @@ -34494,7 +47236,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -34503,6 +47245,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "zelus82\/Obelix-Phi2", + "Average \u2b06\ufe0f": 64.07, + "ARC": 61.77, + "HellaSwag": 76.76, + "MMLU": 58.19, + "TruthfulQA": 51.29, + "Winogrande": 74.9, + "GSM8K": 61.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a9e4d388944139cf342c6118202e4b3440794770", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MSL7\/Liph.42-slerp", + "Average \u2b06\ufe0f": 64.05, + "ARC": 62.54, + "HellaSwag": 77.12, + "MMLU": 58.2, + "TruthfulQA": 52.05, + "Winogrande": 74.9, + "GSM8K": 59.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ad4e7f913c15183cdcd7ea9e89b96a662e1eb55e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e1", @@ -34544,11 +47332,80 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "32122f2efc944e3b88e502c6c310ce4c70fe1419", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "altomek\/CodeRosa-70B-AB1", + "Average \u2b06\ufe0f": 64.04, + "ARC": 65.53, + "HellaSwag": 83.16, + "MMLU": 59.87, + "TruthfulQA": 49.85, + "Winogrande": 81.29, + "GSM8K": 44.5, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ca29018ad4b6c7f92453b0a6a97ca9053e6415a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ibm\/merlinite-7b", + "Average \u2b06\ufe0f": 64.0, + "ARC": 63.65, + "HellaSwag": 84.52, + "MMLU": 64.91, + "TruthfulQA": 50.15, + "Winogrande": 79.72, + "GSM8K": 41.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 88.0, + "Available on the hub": true, + "Model sha": "ba52e4164e649c48b7b5d724fc8bc4020049fe28", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "NeuralNovel\/Mini-Mixtral-v0.2", + "Average \u2b06\ufe0f": 64.0, + "ARC": 61.26, + "HellaSwag": 84.12, + "MMLU": 63.83, + "TruthfulQA": 50.36, + "Winogrande": 78.85, + "GSM8K": 45.56, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "326146db4ced10445991d84ec144765daf99b154", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "Enoch\/llama-65b-hf", @@ -34586,7 +47443,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, @@ -34641,6 +47498,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Gemma-10.2B-Coder", + "Average \u2b06\ufe0f": 63.94, + "ARC": 58.7, + "HellaSwag": 82.04, + "MMLU": 61.96, + "TruthfulQA": 52.44, + "Winogrande": 78.37, + "GSM8K": 50.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.2, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "540d930fa1ea5b20e7cad85f309a0822f4bb05ed", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CorticalStack\/gemma-7b-ultrachat-sft", @@ -34658,7 +47538,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 8.54, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "c4cd06ead3275d15e021423af0b69e59b0e3ec00", "Flagged": false, @@ -34710,6 +47590,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cgato\/TheSpice-7b-FT-ExperimentalOrca", + "Average \u2b06\ufe0f": 63.86, + "ARC": 62.63, + "HellaSwag": 84.26, + "MMLU": 63.33, + "TruthfulQA": 54.87, + "Winogrande": 79.87, + "GSM8K": 38.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "89feebddbb3b836f898d5f40287f3d4e8cb27b39", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Novocoders\/Mistral-NeuralDPO-v0.4", @@ -34727,7 +47630,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "76a02dd47c11f8c225d922eb12aa1b4a3c3a74a7", "Flagged": false, @@ -34750,12 +47653,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 55.59, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "dcab4ed7680a3e5c2f4e3ef36e880cb3b9149dd0", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "zelus82\/Obelix-Phi2", + "Average \u2b06\ufe0f": 63.83, + "ARC": 61.6, + "HellaSwag": 76.68, + "MMLU": 58.14, + "TruthfulQA": 50.79, + "Winogrande": 74.59, + "GSM8K": 61.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a9e4d388944139cf342c6118202e4b3440794770", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "openbmb\/UltraLM-65b", @@ -34773,7 +47699,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 65.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": false, "Model sha": "", "Flagged": false, @@ -34819,7 +47745,7 @@ "Merged": false, "Hub License": "wtfpl", "#Params (B)": 14.0, - "Hub \u2764\ufe0f": 258.0, + "Hub \u2764\ufe0f": 279.0, "Available on the hub": true, "Model sha": "2576a37434e2e03804c841d36c669c8a34c729de", "Flagged": false, @@ -34843,7 +47769,7 @@ "Hub License": "?", "#Params (B)": 14.17, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0649cf49b7a879fe837567a346a3ebbbac77614a", "Flagged": false, "MoE": false @@ -34889,7 +47815,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "600c429a86dcd6e18f0285d7cd9189540ccbdc50", "Flagged": false, "MoE": false @@ -34917,6 +47843,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/mistral-7b-zephyr-sft", + "Average \u2b06\ufe0f": 63.79, + "ARC": 62.29, + "HellaSwag": 84.88, + "MMLU": 62.29, + "TruthfulQA": 53.07, + "Winogrande": 77.98, + "GSM8K": 42.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7c09dbc23ce9d5e5281494cc8d62b9104f9cef05", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "jae24\/openhermes_dpo_norobot_0201", @@ -34940,6 +47889,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Mewthree_7B", + "Average \u2b06\ufe0f": 63.78, + "ARC": 65.78, + "HellaSwag": 85.74, + "MMLU": 62.56, + "TruthfulQA": 65.85, + "Winogrande": 78.85, + "GSM8K": 23.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7b81ea3d4782dc2ea5ae21039aed4c561b0397f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mobidic\/solar-10b-platypus-lora", + "Average \u2b06\ufe0f": 63.77, + "ARC": 62.2, + "HellaSwag": 84.16, + "MMLU": 63.23, + "TruthfulQA": 52.7, + "Winogrande": 82.56, + "GSM8K": 37.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c71c66d8e751b39f0105a123144cc8ebfd4871b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheSkullery\/Aurora_19e_Test", + "Average \u2b06\ufe0f": 63.76, + "ARC": 59.3, + "HellaSwag": 83.74, + "MMLU": 61.45, + "TruthfulQA": 47.46, + "Winogrande": 75.93, + "GSM8K": 54.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 10.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b85cfdd8abb892807059e2df97912abf3b7ee978", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "abhishekchohan\/mistral-7B-med-merge", @@ -34954,7 +47972,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -34980,12 +47998,58 @@ "Merged": false, "Hub License": "other", "#Params (B)": 8.54, - "Hub \u2764\ufe0f": 1509.0, + "Hub \u2764\ufe0f": 2698.0, "Available on the hub": true, "Model sha": "1685d3c30e63630be55aa9a8730531732b3bd93c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "avinash31d\/phi-2-slerp", + "Average \u2b06\ufe0f": 63.74, + "ARC": 62.54, + "HellaSwag": 76.04, + "MMLU": 57.6, + "TruthfulQA": 49.15, + "Winogrande": 75.85, + "GSM8K": 61.26, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "38ff8f0e47a438ea4eb5bc1f3abb592690a503fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "N8Programs\/Thestral-v0.2", + "Average \u2b06\ufe0f": 63.74, + "ARC": 62.71, + "HellaSwag": 82.49, + "MMLU": 62.73, + "TruthfulQA": 52.77, + "Winogrande": 75.77, + "GSM8K": 45.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "766194ad6cb1e9e991afd1477d2112706cb19453", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "fhai50032\/xLakeChat", @@ -35027,7 +48091,7 @@ "Hub License": "?", "#Params (B)": 68.95, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8af85526293eb8625375f3f7a1bab69825176e48", "Flagged": false, "MoE": false @@ -35070,7 +48134,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -35078,6 +48142,98 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-SOLAR-11b-v3.0", + "Average \u2b06\ufe0f": 63.69, + "ARC": 62.29, + "HellaSwag": 84.93, + "MMLU": 65.48, + "TruthfulQA": 52.9, + "Winogrande": 82.87, + "GSM8K": 33.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b47d5115a5e4a1fbee8bf94ce732890deb710432", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Azazelle\/Mocha-SR-7b-ex", + "Average \u2b06\ufe0f": 63.69, + "ARC": 59.81, + "HellaSwag": 81.24, + "MMLU": 60.87, + "TruthfulQA": 54.72, + "Winogrande": 73.09, + "GSM8K": 52.39, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "18919ffe9ea22d5cd29cb582043bbc806098b9d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheSkullery\/Aurora_25e_Test", + "Average \u2b06\ufe0f": 63.68, + "ARC": 59.64, + "HellaSwag": 84.29, + "MMLU": 61.7, + "TruthfulQA": 47.26, + "Winogrande": 76.64, + "GSM8K": 52.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 11.6, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "12145811d11dd6e7cd493cbe9a4add1e951bbc3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rhysjones\/phi-2-orange-v2", + "Average \u2b06\ufe0f": 63.67, + "ARC": 61.86, + "HellaSwag": 76.32, + "MMLU": 55.72, + "TruthfulQA": 54.84, + "Winogrande": 75.69, + "GSM8K": 57.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "c18e2743c806a9730659e7c3c627b9b01d1ff8ce", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Delcos\/Starling-LM-11B-alpha", @@ -35216,6 +48372,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Epiculous\/Mika-7B", + "Average \u2b06\ufe0f": 63.63, + "ARC": 63.48, + "HellaSwag": 85.44, + "MMLU": 59.85, + "TruthfulQA": 69.57, + "Winogrande": 74.9, + "GSM8K": 28.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "agpl-3.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "364d896f55fb409701e2fea947ebda21908f8ecd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Azure99\/blossom-v4-mistral-7b", @@ -35256,7 +48435,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "43dea8e97d05f2e4358415b9a95a1b327c1f5804", "Flagged": false, @@ -35302,12 +48481,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "ff62c26031544deeffd9f06250e71fd05fb1169a", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/phigment6-slerp", + "Average \u2b06\ufe0f": 63.58, + "ARC": 62.63, + "HellaSwag": 77.25, + "MMLU": 58.65, + "TruthfulQA": 50.49, + "Winogrande": 73.88, + "GSM8K": 58.61, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "976d97de8cb3a7af72aa6ef9583d186f6911f919", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NovoCode\/Mistral-NeuralDPO-v0.2", @@ -35325,12 +48527,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "8c6e6989261d5223ca613a22660f4ba7df70995a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v5-7b", + "Average \u2b06\ufe0f": 63.57, + "ARC": 56.06, + "HellaSwag": 77.36, + "MMLU": 61.29, + "TruthfulQA": 54.29, + "Winogrande": 72.38, + "GSM8K": 60.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "adac4d4172343ca5fa56c788615cb1a98f03794d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dreamgen\/opus-v1.2-7b", + "Average \u2b06\ufe0f": 63.56, + "ARC": 58.45, + "HellaSwag": 82.58, + "MMLU": 61.76, + "TruthfulQA": 60.34, + "Winogrande": 77.27, + "GSM8K": 40.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "2caa564170ab98b40247e2812de1ab053115d3a7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "UCLA-AGI\/test-test", @@ -35349,7 +48597,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "83731d11da3f0878effd3a32e5aea52249de7c81", "Flagged": false, "MoE": false @@ -35418,7 +48666,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "83731d11da3f0878effd3a32e5aea52249de7c81", "Flagged": false, "MoE": false @@ -35441,7 +48689,7 @@ "Hub License": "?", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2365c7af9eb60bfa946b566dadd6802befa122e8", "Flagged": false, "MoE": false @@ -35486,12 +48734,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, "Model sha": "b991e934e478e9b406d07840940e9a785a62f0ba", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/mistral_18B_instruct_v0.1", + "Average \u2b06\ufe0f": 63.5, + "ARC": 56.91, + "HellaSwag": 81.36, + "MMLU": 60.52, + "TruthfulQA": 64.85, + "Winogrande": 77.03, + "GSM8K": 40.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 17.71, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1ebb0c9b000e460b78736afd2e40a5c875d241b0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "argilla\/notus-7b-v1", @@ -35509,35 +48780,12 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 106.0, + "Hub \u2764\ufe0f": 108.0, "Available on the hub": true, "Model sha": "f23f4cf6cb76402c76e932ead01109191af72a60", "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udd36", - "Model": "Weyaxi\/einstein-v2-test-model", - "Average \u2b06\ufe0f": 63.48, - "ARC": 62.37, - "HellaSwag": 83.46, - "MMLU": 62.08, - "TruthfulQA": 50.52, - "Winogrande": 79.32, - "GSM8K": 43.14, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "2e31cc426945278f93a91b3a93dc5bf524fe0972", - "Flagged": false, - "MoE": false - }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/Einstein-v2-7B", @@ -35553,9 +48801,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "2e31cc426945278f93a91b3a93dc5bf524fe0972", "Flagged": false, @@ -35563,7 +48811,7 @@ }, { "T": "\ud83d\udd36", - "Model": "tuantran1632001\/Psyfighter2-Orca2-ties", + "Model": "tuantran1632001\/Psyfighter2-Orca2-13B-ties", "Average \u2b06\ufe0f": 63.48, "ARC": 62.46, "HellaSwag": 81.74, @@ -35578,15 +48826,15 @@ "Merged": true, "Hub License": "other", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "e4ab7df425cfa2b2687194837c3b7fba4be7fc74", + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b858fbc15734cc797f1c9e4acb239bfb6c390f08", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "tuantran1632001\/Psyfighter2-Orca2-13B-ties", + "Model": "tuantran1632001\/Psyfighter2-Orca2-ties", "Average \u2b06\ufe0f": 63.48, "ARC": 62.46, "HellaSwag": 81.74, @@ -35598,12 +48846,12 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "other", + "Merged": false, + "Hub License": "?", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "b858fbc15734cc797f1c9e4acb239bfb6c390f08", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e4ab7df425cfa2b2687194837c3b7fba4be7fc74", "Flagged": false, "MoE": false }, @@ -35653,6 +48901,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "delayedkarma\/NeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 63.47, + "ARC": 66.55, + "HellaSwag": 85.0, + "MMLU": 63.41, + "TruthfulQA": 53.83, + "Winogrande": 77.98, + "GSM8K": 34.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "44177ada255b456e97fd9ab246c7dda3869950c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zelus82\/Obelix-Phi2-v0", + "Average \u2b06\ufe0f": 63.46, + "ARC": 63.4, + "HellaSwag": 76.66, + "MMLU": 58.21, + "TruthfulQA": 48.78, + "Winogrande": 75.06, + "GSM8K": 58.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c647172f62c099d1d599da4d99fdb54e7febc77a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dreamgen\/opus-v1.2-7b", + "Average \u2b06\ufe0f": 63.46, + "ARC": 58.45, + "HellaSwag": 82.55, + "MMLU": 61.79, + "TruthfulQA": 60.27, + "Winogrande": 77.11, + "GSM8K": 40.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "a8740f45ee9f633479f1079bfb1ad8ad65231a80", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Stopwolf\/Cerberus-7B-slerp", @@ -35693,12 +49010,81 @@ "Merged": true, "Hub License": "unlicense", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "2da9543e68e222ca627a22a131772155d5ef9078", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "0-hero\/Matter-0.1-Slim-7B-C-DPO", + "Average \u2b06\ufe0f": 63.44, + "ARC": 63.48, + "HellaSwag": 83.12, + "MMLU": 60.63, + "TruthfulQA": 46.53, + "Winogrande": 78.45, + "GSM8K": 48.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "129e2aecb1f5033821c0fbe148bb8aa994565112", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cgato\/Thespis-Krangled-7b-v2", + "Average \u2b06\ufe0f": 63.44, + "ARC": 62.88, + "HellaSwag": 83.04, + "MMLU": 62.44, + "TruthfulQA": 53.02, + "Winogrande": 77.9, + "GSM8K": 41.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc8cbcfe36ae94b19cd7e4c4c5afdf55b825865f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LeroyDyer\/Mixtral_AI_Cyber_2.0", + "Average \u2b06\ufe0f": 63.43, + "ARC": 60.75, + "HellaSwag": 82.5, + "MMLU": 60.03, + "TruthfulQA": 57.58, + "Winogrande": 77.74, + "GSM8K": 42.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "79e60738a576cfb9669ef673d00dbd35f016bdd2", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "xxyyy123\/Mistral7B_adaptor_v1", @@ -35717,7 +49103,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "23e800094570c22fbaa4279ef7e7f27315ac61af", "Flagged": false, "MoE": false @@ -35740,11 +49126,34 @@ "Hub License": "?", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3b723559b550a34e489cc41ec5414e00531ec2ae", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "0-hero\/Matter-0.1-7B", + "Average \u2b06\ufe0f": 63.39, + "ARC": 61.77, + "HellaSwag": 82.14, + "MMLU": 62.42, + "TruthfulQA": 42.44, + "Winogrande": 77.82, + "GSM8K": 53.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "035c8193ce71be90be7d90098669afb9164ec6cb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "llm-agents\/tora-70b-v1.0", @@ -35791,6 +49200,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ozayezerceli\/Threnystril-2x7B-moe", + "Average \u2b06\ufe0f": 63.37, + "ARC": 52.82, + "HellaSwag": 73.36, + "MMLU": 63.83, + "TruthfulQA": 52.71, + "Winogrande": 78.85, + "GSM8K": 58.68, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fe2f1b6f3e3153ae1e3628644b8be77f17d3903e", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "xxyyy123\/1701221123_Ads_Mistral7B-slimorca_all-Lqv-r4b128", @@ -35806,7 +49238,7 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -35814,6 +49246,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/GALAXY-XB-v.03", + "Average \u2b06\ufe0f": 63.37, + "ARC": 61.77, + "HellaSwag": 83.59, + "MMLU": 64.55, + "TruthfulQA": 44.19, + "Winogrande": 81.06, + "GSM8K": 45.03, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 15.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9ffedaa035687282793e54395e141e8e5e47d068", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "xDAN-AI\/xDAN-L1Mix-DeepThinking-v2", @@ -35877,12 +49332,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "906025770a885b26f762b13bb0bc726438e525de", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "itsliupeng\/llama_9b_long", + "Average \u2b06\ufe0f": 63.33, + "ARC": 60.07, + "HellaSwag": 78.67, + "MMLU": 70.53, + "TruthfulQA": 45.95, + "Winogrande": 76.64, + "GSM8K": 48.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 9.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e927d0cf1a8ce240c2d4dd023c869a7c18bf9b1c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/OpenHermes-2.5-Code-290k-13B", + "Average \u2b06\ufe0f": 63.33, + "ARC": 57.34, + "HellaSwag": 80.48, + "MMLU": 56.53, + "TruthfulQA": 52.5, + "Winogrande": 74.82, + "GSM8K": 58.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "5fe89b1eb555644dd8a658c74ea118620ba3fdc1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "liminerity\/Blur-7b-v1.22", @@ -35906,6 +49407,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "itsliupeng\/llama_9b_long", + "Average \u2b06\ufe0f": 63.3, + "ARC": 60.32, + "HellaSwag": 78.62, + "MMLU": 70.5, + "TruthfulQA": 45.91, + "Winogrande": 76.48, + "GSM8K": 47.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 9.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e927d0cf1a8ce240c2d4dd023c869a7c18bf9b1c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mobiuslabsgmbh\/aanaphi2-v0.1", @@ -35921,9 +49445,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "3ccc97066e70b9aa5f686083b7d406c312c490e2", "Flagged": false, @@ -36021,6 +49545,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "0-hero\/Matter-0.1-7B-boost", + "Average \u2b06\ufe0f": 63.22, + "ARC": 62.63, + "HellaSwag": 81.51, + "MMLU": 61.97, + "TruthfulQA": 54.7, + "Winogrande": 75.93, + "GSM8K": 42.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ba56089eed1211f02e8d0ff47901e77b0cd48f83", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "chanwit\/flux-base-optimized", @@ -36061,8 +49608,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 9.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "b7befcbc2e609356efc76c64cee1b1727727d815", "Flagged": false, "MoE": false @@ -36153,12 +49700,58 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.39, - "Hub \u2764\ufe0f": 274.0, + "Hub \u2764\ufe0f": 303.0, "Available on the hub": true, "Model sha": "a99ec35331cbfc9da596af7d4538fe2efecff03c", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udfe9", + "Model": "01-ai\/Yi-9B", + "Average \u2b06\ufe0f": 63.17, + "ARC": 61.18, + "HellaSwag": 78.82, + "MMLU": 70.06, + "TruthfulQA": 42.45, + "Winogrande": 77.51, + "GSM8K": 48.98, + "Type": "continuously pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.83, + "Hub \u2764\ufe0f": 170.0, + "Available on the hub": true, + "Model sha": "6868e9775d48a9b6a1ae0653ff8865a438691a9c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Soulful_Bepis_7B", + "Average \u2b06\ufe0f": 63.15, + "ARC": 63.82, + "HellaSwag": 80.69, + "MMLU": 62.53, + "TruthfulQA": 56.65, + "Winogrande": 76.16, + "GSM8K": 39.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "182bf0a4e15570da44678d589b2b703cd21b024d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e3", @@ -36321,8 +49914,31 @@ "MoE": false }, { - "T": "\ud83d\udfe2", - "Model": "tourist800\/Marcoro14-7B-slerp", + "T": "\ud83e\udd1d", + "Model": "saishf\/Fett-uccine-11B-Experiment", + "Average \u2b06\ufe0f": 63.09, + "ARC": 63.14, + "HellaSwag": 85.39, + "MMLU": 59.72, + "TruthfulQA": 69.92, + "Winogrande": 74.59, + "GSM8K": 25.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "agpl-3.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b0673c461432527942cf2e82ffdca34360098712", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tourist800\/mistral_2X7b", "Average \u2b06\ufe0f": 63.08, "ARC": 63.4, "HellaSwag": 83.77, @@ -36330,7 +49946,7 @@ "TruthfulQA": 52.08, "Winogrande": 77.9, "GSM8K": 40.18, - "Type": "pretrained", + "Type": "base merges and moerges", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", @@ -36338,14 +49954,14 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "8722dce4c447d974545f55623788c351a15bc36c", "Flagged": false, "MoE": false }, { - "T": "\ud83e\udd1d", - "Model": "tourist800\/mistral_2X7b", + "T": "\ud83d\udfe2", + "Model": "tourist800\/Marcoro14-7B-slerp", "Average \u2b06\ufe0f": 63.08, "ARC": 63.4, "HellaSwag": 83.77, @@ -36353,19 +49969,42 @@ "TruthfulQA": 52.08, "Winogrande": 77.9, "GSM8K": 40.18, - "Type": "base merges and moerges", + "Type": "pretrained", "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8722dce4c447d974545f55623788c351a15bc36c", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "INSAIT-Institute\/BgGPT-7B-Instruct-v0.2", + "Average \u2b06\ufe0f": 63.08, + "ARC": 60.58, + "HellaSwag": 82.18, + "MMLU": 60.5, + "TruthfulQA": 54.63, + "Winogrande": 76.48, + "GSM8K": 44.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.29, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "e1aa1a3ff1bde9ed33fbfc83eb9a0391afc19424", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e2", @@ -36381,34 +50020,103 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "cc-by-nc-4.0", - "#Params (B)": 7.0, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "01a73ccd10a275738304c695d0728a29e8586f47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-falcon-180b-v12-preview0", + "Average \u2b06\ufe0f": 63.06, + "ARC": 62.29, + "HellaSwag": 83.8, + "MMLU": 55.92, + "TruthfulQA": 53.05, + "Winogrande": 82.08, + "GSM8K": 41.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 180.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4f1aeb136860ee3216f23faec0c598014e5c40a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maldv\/SHRDFU-7b-overbaked-lora", + "Average \u2b06\ufe0f": 63.05, + "ARC": 64.33, + "HellaSwag": 83.46, + "MMLU": 62.42, + "TruthfulQA": 50.98, + "Winogrande": 78.69, + "GSM8K": 38.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "48d8e195edab6945f4eecead0e65f3aa9de4c1f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalleorg\/OpenHermes-Yi-9B", + "Average \u2b06\ufe0f": 63.05, + "ARC": 60.67, + "HellaSwag": 78.73, + "MMLU": 69.67, + "TruthfulQA": 42.25, + "Winogrande": 77.19, + "GSM8K": 49.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.83, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "01a73ccd10a275738304c695d0728a29e8586f47", + "Model sha": "1e757a2c2c0f32983e6d360ee2ca62581a121ea7", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "OpenBuddy\/openbuddy-falcon-180b-v12-preview0", - "Average \u2b06\ufe0f": 63.06, - "ARC": 62.29, - "HellaSwag": 83.8, - "MMLU": 55.92, - "TruthfulQA": 53.05, - "Winogrande": 82.08, - "GSM8K": 41.24, + "Model": "cloudyu\/mistral_15B_instruct_v0.1", + "Average \u2b06\ufe0f": 63.04, + "ARC": 58.45, + "HellaSwag": 81.71, + "MMLU": 59.82, + "TruthfulQA": 63.43, + "Winogrande": 76.24, + "GSM8K": 38.59, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "FalconForCausalLM", + "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "4bit", + "Precision": "bfloat16", "Merged": false, - "Hub License": "", - "#Params (B)": 180.0, + "Hub License": "cc-by-4.0", + "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "4f1aeb136860ee3216f23faec0c598014e5c40a6", + "Available on the hub": true, + "Model sha": "5871f452765a0fd097fbb186c3a6328832ddcfa0", "Flagged": false, "MoE": false }, @@ -36452,7 +50160,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 36.1, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "5d1159dd60ec2cc92dbc52508430e620b6adbdaa", "Flagged": false, @@ -36481,6 +50189,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/Blitz-v0.1", + "Average \u2b06\ufe0f": 63.03, + "ARC": 55.2, + "HellaSwag": 82.5, + "MMLU": 61.33, + "TruthfulQA": 60.77, + "Winogrande": 77.43, + "GSM8K": 40.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8617ca42117e462cbe856f23807cb9e8c3fbae8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-3.0-Mistral-7B-DPO", + "Average \u2b06\ufe0f": 63.03, + "ARC": 60.67, + "HellaSwag": 83.95, + "MMLU": 62.71, + "TruthfulQA": 46.17, + "Winogrande": 79.32, + "GSM8K": 45.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "31b3358c9ec5e4dd7b159241a622ea68c60b0500", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Azure99\/blossom-v3-mistral-7b", @@ -36544,7 +50298,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "4ba64c10fb56ade9ce2e0c5a097819b888c0a272", "Flagged": false, @@ -36573,6 +50327,75 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-gemma-7b", + "Average \u2b06\ufe0f": 62.93, + "ARC": 62.12, + "HellaSwag": 79.77, + "MMLU": 61.57, + "TruthfulQA": 49.41, + "Winogrande": 75.45, + "GSM8K": 49.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0366d26aaef3342cf11691fbe97f7266fc30644d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Inv\/Elbrus-7B", + "Average \u2b06\ufe0f": 62.93, + "ARC": 63.99, + "HellaSwag": 83.96, + "MMLU": 63.06, + "TruthfulQA": 44.34, + "Winogrande": 79.72, + "GSM8K": 42.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fbd9336495f86592d1c8532abd04be5da8895c57", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mervinpraison\/tamil-large-language-model-7b-v1.0", + "Average \u2b06\ufe0f": 62.92, + "ARC": 60.15, + "HellaSwag": 82.21, + "MMLU": 63.9, + "TruthfulQA": 45.09, + "Winogrande": 77.51, + "GSM8K": 48.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b07baafc06099b5835118213e79768a60f4a8973", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jefferylovely\/AthenaImaniMaven", @@ -36587,8 +50410,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -36613,15 +50436,84 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 73.0, + "Hub \u2764\ufe0f": 75.0, "Available on the hub": true, "Model sha": "5f57f70ec99450c70da2540e94dd7fd67be4b23c", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "nasiruddin15\/Mistral-grok-instract-2-7B-slerp", + "Average \u2b06\ufe0f": 62.87, + "ARC": 62.8, + "HellaSwag": 83.03, + "MMLU": 61.04, + "TruthfulQA": 53.51, + "Winogrande": 76.95, + "GSM8K": 39.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7ce8d94268c52ed2c7046624d5052fee5bc1e247", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/GALAXY-XB-v.01", + "Average \u2b06\ufe0f": 62.87, + "ARC": 60.92, + "HellaSwag": 82.92, + "MMLU": 65.11, + "TruthfulQA": 43.67, + "Winogrande": 81.14, + "GSM8K": 43.44, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 17.71, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "65626e3a0f529ae6466984f947cf38b4ecf2f584", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "UCLA-AGI\/test", + "Model": "cloudyu\/mistral_18B_v0.1", + "Average \u2b06\ufe0f": 62.86, + "ARC": 62.54, + "HellaSwag": 79.93, + "MMLU": 61.98, + "TruthfulQA": 57.32, + "Winogrande": 77.27, + "GSM8K": 38.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 17.71, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d2b6e259165661001696a8d2198d559b0e448685", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter1", "Average \u2b06\ufe0f": 62.86, "ARC": 65.87, "HellaSwag": 85.44, @@ -36630,21 +50522,21 @@ "Winogrande": 76.64, "GSM8K": 30.86, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, - "Model sha": "437d2f9c55aec50ebaedce22df8aaa7fcc0f9ff8", + "Model sha": "d8569aea49f28131ca3d319da343da0777ed4161", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "UCLA-AGI\/zephyr-7b-sft-full-spin-iter1", + "Model": "UCLA-AGI\/test", "Average \u2b06\ufe0f": 62.86, "ARC": 65.87, "HellaSwag": 85.44, @@ -36660,14 +50552,14 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "9257b6484010acf5eed7e77ff787264b49c1a923", + "Available on the hub": false, + "Model sha": "437d2f9c55aec50ebaedce22df8aaa7fcc0f9ff8", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter1", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-spin-iter1", "Average \u2b06\ufe0f": 62.86, "ARC": 65.87, "HellaSwag": 85.44, @@ -36676,15 +50568,15 @@ "Winogrande": 76.64, "GSM8K": 30.86, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, - "Model sha": "d8569aea49f28131ca3d319da343da0777ed4161", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9257b6484010acf5eed7e77ff787264b49c1a923", "Flagged": false, "MoE": false }, @@ -36702,8 +50594,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -36728,7 +50620,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "b7577f83a0af27e1a380efce4f993c25c33d8b33", "Flagged": false, @@ -36749,9 +50641,9 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "6623e1ec77f20f7c152e86e99b49e501d0133b13", "Flagged": false, @@ -36826,6 +50718,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/mistral_28B_instruct_v0.2", + "Average \u2b06\ufe0f": 62.81, + "ARC": 58.19, + "HellaSwag": 80.52, + "MMLU": 60.53, + "TruthfulQA": 64.25, + "Winogrande": 74.9, + "GSM8K": 38.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 28.18, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc872860320a3fee6c64c88c42c92341a38d25e1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "vince62s\/phi-2-psy", @@ -36843,7 +50758,7 @@ "Merged": true, "Hub License": "mit", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "9a9a31679e597e92dd02af20e94e4cd7fb211112", "Flagged": false, @@ -36889,12 +50804,127 @@ "Merged": false, "Hub License": "other", "#Params (B)": 65.29, - "Hub \u2764\ufe0f": 68.0, + "Hub \u2764\ufe0f": 70.0, "Available on the hub": true, "Model sha": "49707c5313d34d1c5a846e29cf2a2a650c22c8ee", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Minami-su\/IA_14B", + "Average \u2b06\ufe0f": 62.78, + "ARC": 62.37, + "HellaSwag": 80.7, + "MMLU": 68.08, + "TruthfulQA": 62.22, + "Winogrande": 74.35, + "GSM8K": 28.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e38a53dd782115b75968be205efd8b4da31b3b93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/OpenCerebrum-1.0-7b-DPO", + "Average \u2b06\ufe0f": 62.78, + "ARC": 62.71, + "HellaSwag": 84.33, + "MMLU": 62.59, + "TruthfulQA": 44.91, + "Winogrande": 80.11, + "GSM8K": 42.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "c62cf904fb834bf99cd281cc32fb58048be411fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/lr-experiment1-7B", + "Average \u2b06\ufe0f": 62.77, + "ARC": 60.75, + "HellaSwag": 83.73, + "MMLU": 63.25, + "TruthfulQA": 44.07, + "Winogrande": 79.48, + "GSM8K": 45.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "184813a8265802dccbbc1f8bb0fe72ae32a3475e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/mistral_28B_instruct_v0.1", + "Average \u2b06\ufe0f": 62.77, + "ARC": 58.36, + "HellaSwag": 80.53, + "MMLU": 60.73, + "TruthfulQA": 64.17, + "Winogrande": 74.82, + "GSM8K": 37.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 28.18, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d87f393ea232749bf48131107131778c79ab3a74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chlee10\/T3Q-Platypus-SOLAR", + "Average \u2b06\ufe0f": 62.76, + "ARC": 61.86, + "HellaSwag": 84.18, + "MMLU": 53.72, + "TruthfulQA": 50.67, + "Winogrande": 82.4, + "GSM8K": 43.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c86f8fbea101541d5e93f055cd0ee5e9a897bf58", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/neural-chat-7b-v3-1-dare-0.85", @@ -36918,6 +50948,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Ba2han\/Cucumber-7b-10k", + "Average \u2b06\ufe0f": 62.74, + "ARC": 60.41, + "HellaSwag": 83.75, + "MMLU": 63.1, + "TruthfulQA": 50.97, + "Winogrande": 78.93, + "GSM8K": 39.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "137a42ed37aa261f95b99ccd0f91952bc7656e1e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Faradaylab\/ARIA-70B-V3", @@ -36941,6 +50994,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/experiment2-cause", + "Average \u2b06\ufe0f": 62.73, + "ARC": 61.26, + "HellaSwag": 83.4, + "MMLU": 63.91, + "TruthfulQA": 48.16, + "Winogrande": 79.79, + "GSM8K": 39.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4d6f888de5ba44d5ca8ef766c54e92103a0afe16", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cgato\/Thespis-CurtainCall-7b-v0.3", + "Average \u2b06\ufe0f": 62.73, + "ARC": 64.25, + "HellaSwag": 82.93, + "MMLU": 62.24, + "TruthfulQA": 50.95, + "Winogrande": 78.61, + "GSM8K": 37.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "cc6a7116ab0b3651bbd03a15eb90f8fb5330e340", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "mlinmg\/SG-Raccoon-Yi-200k-2.0", @@ -36959,11 +51058,34 @@ "Hub License": "?", "#Params (B)": 55.59, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "986706415fcb2118f35626dbc12e054457ec9ad3", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-Mistral-7b-v1.1", + "Average \u2b06\ufe0f": 62.72, + "ARC": 59.47, + "HellaSwag": 80.75, + "MMLU": 60.56, + "TruthfulQA": 45.54, + "Winogrande": 76.48, + "GSM8K": 53.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.37, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0f7e1ed84843f50791fa74315dfa0f975f300344", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "Fredithefish\/MadMix-v0.2", @@ -36987,6 +51109,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Joseph717171\/BigOrca-2-XB", + "Average \u2b06\ufe0f": 62.72, + "ARC": 61.6, + "HellaSwag": 83.64, + "MMLU": 60.85, + "TruthfulQA": 58.0, + "Winogrande": 77.27, + "GSM8K": 34.95, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 22.53, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9345eada460ca54e22d1bee64f2680fde814c7a9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NovoCode\/Mistral-NeuralDPO", @@ -37004,12 +51149,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "1b8ecfe53f090c6c7dffcb46a3fade8087ab0767", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "grayhacker91\/gemma-7b-open-platypus-commercial", + "Average \u2b06\ufe0f": 62.71, + "ARC": 62.8, + "HellaSwag": 81.65, + "MMLU": 58.94, + "TruthfulQA": 53.54, + "Winogrande": 79.01, + "GSM8K": 40.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "50a1fda9a90009f9de508f08bf1b192ef195667a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/experiment2-non-cause-v1", + "Average \u2b06\ufe0f": 62.71, + "ARC": 61.52, + "HellaSwag": 83.71, + "MMLU": 63.79, + "TruthfulQA": 48.12, + "Winogrande": 79.32, + "GSM8K": 39.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c911ffa558630d04c97f5d39e1d2e5412cd4346f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "amu\/r-zephyr-7b-beta-qlora", @@ -37021,15 +51212,38 @@ "Winogrande": 79.32, "GSM8K": 39.04, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", - "Weight type": "Original", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3948f437f08ebb9f0bc7da37cdead0cc3dd7a562", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/experiment2-cause-non", + "Average \u2b06\ufe0f": 62.69, + "ARC": 61.09, + "HellaSwag": 83.72, + "MMLU": 64.13, + "TruthfulQA": 47.34, + "Winogrande": 79.48, + "GSM8K": 40.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 7.0, + "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "3948f437f08ebb9f0bc7da37cdead0cc3dd7a562", + "Model sha": "3236726d4a5c4a3e18a8eedf35593bf4b1c14b8b", "Flagged": false, "MoE": false }, @@ -37050,7 +51264,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "3463e3123ea32116e5aca1a4498c1f8fb5109244", "Flagged": false, @@ -37073,7 +51287,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 19.86, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "ab228139d9da36acb908b8ff7732b456dfdd57e7", "Flagged": false, @@ -37117,7 +51331,7 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 10.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -37163,7 +51377,7 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -37188,7 +51402,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "0f5977a5d2fa791359dc92eb1574b6112e709cad", "Flagged": false, @@ -37217,6 +51431,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AetherResearch\/Cerebrum-1.0-7b", + "Average \u2b06\ufe0f": 62.63, + "ARC": 61.6, + "HellaSwag": 84.56, + "MMLU": 63.56, + "TruthfulQA": 46.49, + "Winogrande": 79.4, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "da3d8699055cd5f49626613af771473ae447e082", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "yeontaek\/llama-2-70b-IA3-guanaco", @@ -37255,9 +51492,9 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "6623e1ec77f20f7c152e86e99b49e501d0133b13", "Flagged": false, @@ -37280,12 +51517,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "f16526d9bb814dc10adc911f94e8c7a520beb5b6", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-v0.1-gpt-4-40k", + "Average \u2b06\ufe0f": 62.59, + "ARC": 63.31, + "HellaSwag": 81.5, + "MMLU": 62.9, + "TruthfulQA": 54.89, + "Winogrande": 73.8, + "GSM8K": 39.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c96652218ba869551915f5f6a502cfb91091ba20", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/VicUnlocked-alpaca-65B-QLoRA-fp16", @@ -37349,9 +51609,101 @@ "Merged": false, "Hub License": "other", "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "af7d5521bf657a2323ad437feaa060969244afab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/gemma-7b-alpaca-52k-v0.1", + "Average \u2b06\ufe0f": 62.56, + "ARC": 60.15, + "HellaSwag": 81.97, + "MMLU": 64.14, + "TruthfulQA": 46.7, + "Winogrande": 77.82, + "GSM8K": 44.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, - "Model sha": "af7d5521bf657a2323ad437feaa060969244afab", + "Model sha": "05bc24728baa4a680dd7aff3f15053e28671e801", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-Instruct-v0.2-gpt-4-80k", + "Average \u2b06\ufe0f": 62.55, + "ARC": 58.02, + "HellaSwag": 78.89, + "MMLU": 60.96, + "TruthfulQA": 63.95, + "Winogrande": 74.66, + "GSM8K": 38.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b5b0442077e2bdbfe29943a82db8a306fdf75af5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "XuanXuanXuanXuan\/Mistral-7B-Instruct-v0.2-gpt-4-80k", + "Average \u2b06\ufe0f": 62.55, + "ARC": 58.02, + "HellaSwag": 78.89, + "MMLU": 60.96, + "TruthfulQA": 63.95, + "Winogrande": 74.66, + "GSM8K": 38.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "45c1256737a33c5a35a2e87f5b7fd0b5a149d5e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kaist-ai\/mistral-orpo-beta", + "Average \u2b06\ufe0f": 62.53, + "ARC": 61.18, + "HellaSwag": 84.03, + "MMLU": 63.26, + "TruthfulQA": 47.69, + "Winogrande": 79.24, + "GSM8K": 39.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "0b457487cd34991f5de81a941a1b56f9673bf38b", "Flagged": false, "MoE": false }, @@ -37393,7 +51745,7 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 10.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -37418,12 +51770,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "72d393d13f1bd26442e59993c57840b91ff6f6fc", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/GALAXY-XB-v.02", + "Average \u2b06\ufe0f": 62.48, + "ARC": 60.67, + "HellaSwag": 83.27, + "MMLU": 64.99, + "TruthfulQA": 43.6, + "Winogrande": 80.27, + "GSM8K": 42.08, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 16.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "66beef010dea755eacf6e9316be7169df361ca99", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mistral2-7b-v20.2-32k", + "Average \u2b06\ufe0f": 62.46, + "ARC": 56.91, + "HellaSwag": 79.45, + "MMLU": 60.73, + "TruthfulQA": 53.18, + "Winogrande": 75.06, + "GSM8K": 49.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bc0207c5bc5b6838c50ec8db77225f4f18cd7871", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jikaixuan\/test_merged_model", @@ -37470,6 +51868,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/zephyr-7b-gemma-v0.1", + "Average \u2b06\ufe0f": 62.41, + "ARC": 58.45, + "HellaSwag": 83.48, + "MMLU": 60.68, + "TruthfulQA": 52.07, + "Winogrande": 74.19, + "GSM8K": 45.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 106.0, + "Available on the hub": true, + "Model sha": "19186e70e5679c47aaef473ae2fd56e20765088d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Bepis_9B", + "Average \u2b06\ufe0f": 62.4, + "ARC": 62.54, + "HellaSwag": 80.12, + "MMLU": 62.84, + "TruthfulQA": 53.3, + "Winogrande": 76.48, + "GSM8K": 39.12, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "68e796a8e1612119821f3187d62779ca472991a0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "meta-llama\/Llama-2-70b-chat-hf", @@ -37487,8 +51931,8 @@ "Merged": false, "Hub License": null, "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 1988.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 2058.0, + "Available on the hub": true, "Model sha": "7f54101c0fbb67a8143ca23eb8bd09b71f269c74", "Flagged": false, "MoE": false @@ -37518,7 +51962,7 @@ }, { "T": "\ud83d\udd36", - "Model": "UCLA-AGI\/test0", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter0", "Average \u2b06\ufe0f": 62.37, "ARC": 63.65, "HellaSwag": 84.44, @@ -37527,21 +51971,21 @@ "Winogrande": 77.98, "GSM8K": 36.69, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, - "Model sha": "e90506303f046ebe6da9d8b41489a7365b455a06", + "Model sha": "d457f58ca73bd5540dc4e12b70315e4464ea138c", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter0", + "Model": "UCLA-AGI\/test0", "Average \u2b06\ufe0f": 62.37, "ARC": 63.65, "HellaSwag": 84.44, @@ -37550,15 +51994,15 @@ "Winogrande": 77.98, "GSM8K": 36.69, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "MistralForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 6.0, - "Available on the hub": true, - "Model sha": "d457f58ca73bd5540dc4e12b70315e4464ea138c", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e90506303f046ebe6da9d8b41489a7365b455a06", "Flagged": false, "MoE": false }, @@ -37608,6 +52052,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "Qwen\/Qwen1.5-14B-Chat", + "Average \u2b06\ufe0f": 62.37, + "ARC": 58.79, + "HellaSwag": 82.33, + "MMLU": 68.52, + "TruthfulQA": 60.38, + "Winogrande": 73.32, + "GSM8K": 30.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 67.0, + "Available on the hub": true, + "Model sha": "17e11c306ed235e970c9bb8e5f7233527140cdcf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-qwen1.5-en-7b-dpo-v0.1", + "Average \u2b06\ufe0f": 62.36, + "ARC": 54.35, + "HellaSwag": 76.04, + "MMLU": 61.21, + "TruthfulQA": 56.4, + "Winogrande": 72.06, + "GSM8K": 54.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f4f3ed15b4d59f3e22a290085a51aa5f1ac39455", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Locutusque\/Hercules-3.0-Mistral-7B", @@ -37648,7 +52138,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 69.2, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "2646170ac2788259d258de8d16c563e36efce299", "Flagged": false, @@ -37700,6 +52190,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Azazelle\/Moko-SAMPLE", + "Average \u2b06\ufe0f": 62.34, + "ARC": 61.09, + "HellaSwag": 83.85, + "MMLU": 64.57, + "TruthfulQA": 43.45, + "Winogrande": 79.16, + "GSM8K": 41.93, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ed942b34411970e688adb0ec6fe39c2b56e5e0e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "huseyinatahaninan\/phi-2-dpo", @@ -37718,7 +52231,7 @@ "Hub License": "mit", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "e23c721e850052435d5b0c1c664432a11bbbd26e", "Flagged": false, "MoE": false @@ -37740,7 +52253,7 @@ "Merged": true, "Hub License": "cc-by-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "378e5fb671d593432ce6c7ddc19ac8e04a490df8", "Flagged": false, @@ -37807,47 +52320,254 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", - "#Params (B)": 7.24, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "26b1b06ca6ee8db77d915e0ec685b3e999a226d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BlouseJury\/Mistral-7B-Discord-0.1-DPO", + "Average \u2b06\ufe0f": 62.29, + "ARC": 63.23, + "HellaSwag": 83.27, + "MMLU": 62.62, + "TruthfulQA": 55.28, + "Winogrande": 78.93, + "GSM8K": 30.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3fde20529c9b2e25c9cb7a7a28795410e0b4ac21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/mistralv1_gsm8k_merged", + "Average \u2b06\ufe0f": 62.28, + "ARC": 61.35, + "HellaSwag": 83.11, + "MMLU": 63.04, + "TruthfulQA": 39.55, + "Winogrande": 78.61, + "GSM8K": 47.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9cb1edd3a535cabc500ce9fb81d98bbfed0b047", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/finetuned-Mistral-7B-Instruct-v0.2-5000-v2.0", + "Average \u2b06\ufe0f": 62.27, + "ARC": 59.3, + "HellaSwag": 82.65, + "MMLU": 58.45, + "TruthfulQA": 59.54, + "Winogrande": 77.66, + "GSM8K": 36.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b32cd037f8c83d08da8a5e593d3cc29de090af1a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Mistral-7B-Instruct-Aya-101", + "Average \u2b06\ufe0f": 62.27, + "ARC": 59.13, + "HellaSwag": 83.2, + "MMLU": 61.96, + "TruthfulQA": 52.71, + "Winogrande": 77.51, + "GSM8K": 39.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7724e49d560d6b030e67aea0fe319020103929c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vmajor\/Orca2-13B-selfmerge-26B", + "Average \u2b06\ufe0f": 62.24, + "ARC": 60.84, + "HellaSwag": 79.84, + "MMLU": 60.32, + "TruthfulQA": 56.38, + "Winogrande": 76.87, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "ms-pl", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "46cdde5be7e3c48ada1bd3143ad593eecfb641e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vmajor\/Orca2-13B-selfmerge-39B", + "Average \u2b06\ufe0f": 62.24, + "ARC": 60.84, + "HellaSwag": 79.84, + "MMLU": 60.32, + "TruthfulQA": 56.38, + "Winogrande": 76.87, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "ms-pl", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7a9e6775716a3947d0e40842b5d61753bc0551ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "0-hero\/Matter-0.1-Slim-7B-C", + "Average \u2b06\ufe0f": 62.23, + "ARC": 61.35, + "HellaSwag": 81.76, + "MMLU": 61.45, + "TruthfulQA": 43.49, + "Winogrande": 77.98, + "GSM8K": 47.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce9d68b563a4ad68ac6349672ca3b2f9ca492957", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/delta-4b-orange", + "Average \u2b06\ufe0f": 62.23, + "ARC": 58.87, + "HellaSwag": 76.59, + "MMLU": 56.5, + "TruthfulQA": 56.82, + "Winogrande": 76.48, + "GSM8K": 48.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b701c3329f7ecb6cafe7f38b27f59eea548a9c92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "gmonsoon\/delta-4b-orange", + "Average \u2b06\ufe0f": 62.23, + "ARC": 58.87, + "HellaSwag": 76.59, + "MMLU": 56.5, + "TruthfulQA": 56.82, + "Winogrande": 76.48, + "GSM8K": 48.14, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.67, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "26b1b06ca6ee8db77d915e0ec685b3e999a226d0", + "Model sha": "b701c3329f7ecb6cafe7f38b27f59eea548a9c92", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "BlouseJury\/Mistral-7B-Discord-0.1-DPO", - "Average \u2b06\ufe0f": 62.29, - "ARC": 63.23, - "HellaSwag": 83.27, - "MMLU": 62.62, - "TruthfulQA": 55.28, - "Winogrande": 78.93, - "GSM8K": 30.4, + "Model": "Sao10K\/Frostwind-v2.1-m7", + "Average \u2b06\ufe0f": 62.23, + "ARC": 61.77, + "HellaSwag": 83.77, + "MMLU": 63.83, + "TruthfulQA": 46.94, + "Winogrande": 78.69, + "GSM8K": 38.36, "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "float16", + "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "3fde20529c9b2e25c9cb7a7a28795410e0b4ac21", + "Model sha": "a6d8e1ec723f87e969f0ece1a2c9223665a34927", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "fzzhang\/mistralv1_gsm8k_merged", - "Average \u2b06\ufe0f": 62.28, - "ARC": 61.35, - "HellaSwag": 83.11, - "MMLU": 63.04, - "TruthfulQA": 39.55, - "Winogrande": 78.61, - "GSM8K": 47.99, + "Model": "juhwanlee\/experiment2-cause-v1", + "Average \u2b06\ufe0f": 62.22, + "ARC": 61.01, + "HellaSwag": 83.38, + "MMLU": 63.75, + "TruthfulQA": 47.2, + "Winogrande": 79.01, + "GSM8K": 38.97, "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", @@ -37857,76 +52577,53 @@ "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "b9cb1edd3a535cabc500ce9fb81d98bbfed0b047", + "Model sha": "f7e94b05758d08a981906a62942283349c561ae7", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "abdulrahman-nuzha\/finetuned-Mistral-7B-Instruct-v0.2-5000-v2.0", - "Average \u2b06\ufe0f": 62.27, - "ARC": 59.3, - "HellaSwag": 82.65, - "MMLU": 58.45, - "TruthfulQA": 59.54, - "Winogrande": 77.66, - "GSM8K": 36.01, + "Model": "juhwanlee\/llmdo-Mistral-7B-case-6", + "Average \u2b06\ufe0f": 62.2, + "ARC": 61.69, + "HellaSwag": 83.59, + "MMLU": 63.25, + "TruthfulQA": 46.27, + "Winogrande": 78.85, + "GSM8K": 39.58, "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "4bit", + "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "b32cd037f8c83d08da8a5e593d3cc29de090af1a", - "Flagged": false, - "MoE": false - }, - { - "T": "\ud83d\udd36", - "Model": "vmajor\/Orca2-13B-selfmerge-26B", - "Average \u2b06\ufe0f": 62.24, - "ARC": 60.84, - "HellaSwag": 79.84, - "MMLU": 60.32, - "TruthfulQA": 56.38, - "Winogrande": 76.87, - "GSM8K": 39.2, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "float16", - "Merged": true, - "Hub License": "ms-pl", - "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, - "Model sha": "46cdde5be7e3c48ada1bd3143ad593eecfb641e7", + "Model sha": "de9932b4d92e3a579c933b51cbdc39fa6fb2bada", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "vmajor\/Orca2-13B-selfmerge-39B", - "Average \u2b06\ufe0f": 62.24, - "ARC": 60.84, - "HellaSwag": 79.84, - "MMLU": 60.32, - "TruthfulQA": 56.38, - "Winogrande": 76.87, - "GSM8K": 39.2, + "Model": "juhwanlee\/llmdo-Mistral-7B-case-1", + "Average \u2b06\ufe0f": 62.19, + "ARC": 62.12, + "HellaSwag": 83.6, + "MMLU": 63.46, + "TruthfulQA": 45.69, + "Winogrande": 79.16, + "GSM8K": 39.12, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "ms-pl", - "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 1.0, + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "7a9e6775716a3947d0e40842b5d61753bc0551ac", + "Model sha": "d9fb9995a0e378f2ed955dc0a24690768e3e81ea", "Flagged": false, "MoE": false }, @@ -37953,6 +52650,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/llmdo-Mistral-7B-case-7", + "Average \u2b06\ufe0f": 62.19, + "ARC": 61.95, + "HellaSwag": 83.54, + "MMLU": 63.13, + "TruthfulQA": 45.83, + "Winogrande": 79.4, + "GSM8K": 39.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b53d30318037781487bb5be6b19ff95b6703bd7e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "andysalerno\/rainbowfish-v7", @@ -37970,12 +52690,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, "Model sha": "896039c526d6d5977fb7943743666b4dc2563b3e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "abacusai\/bigstral-12b-32k", + "Average \u2b06\ufe0f": 62.17, + "ARC": 59.98, + "HellaSwag": 84.1, + "MMLU": 59.14, + "TruthfulQA": 68.21, + "Winogrande": 74.66, + "GSM8K": 26.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "ceb9da24dcd58c01de0eddada94c79f62d7d6436", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Radu1999\/Mistral-Instruct-Ukrainian-SFT", @@ -37993,12 +52736,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "26d1f9e8efdd4a471698cd404ac5d7415e8ac80e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/llmdo-Mistral-7B-case-c-v1", + "Average \u2b06\ufe0f": 62.16, + "ARC": 62.03, + "HellaSwag": 83.55, + "MMLU": 62.69, + "TruthfulQA": 45.82, + "Winogrande": 79.08, + "GSM8K": 39.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a11d4a6dcfbe2dda496aa2a33cd388e8056f95f2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/Orca-2-13b-f16", @@ -38022,6 +52788,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "abacaj\/phi-2-super", + "Average \u2b06\ufe0f": 62.13, + "ARC": 61.86, + "HellaSwag": 76.6, + "MMLU": 58.41, + "TruthfulQA": 48.37, + "Winogrande": 73.01, + "GSM8K": 54.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 80.0, + "Available on the hub": true, + "Model sha": "2d6482f24447855e463fcefc40572505607e5693", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "liminerity\/Liph42", + "Average \u2b06\ufe0f": 62.12, + "ARC": 62.03, + "HellaSwag": 75.87, + "MMLU": 57.37, + "TruthfulQA": 45.94, + "Winogrande": 74.59, + "GSM8K": 56.94, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1a760e1ed7ebe8b202f632e687fb129c87a02537", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Azure99\/blossom-v4-qwen1_5-7b", @@ -38063,7 +52875,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "2a6525f8b5c6d02ef78e716ccb37c6ef1bb1a26d", "Flagged": false, "MoE": false @@ -38085,7 +52897,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "ba7176142c6d3e5b8735b79f68552f16634bbbe7", "Flagged": false, @@ -38114,6 +52926,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/llmdo-Mistral-7B-case-5", + "Average \u2b06\ufe0f": 62.07, + "ARC": 62.2, + "HellaSwag": 83.4, + "MMLU": 63.52, + "TruthfulQA": 45.46, + "Winogrande": 79.32, + "GSM8K": 38.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "abbb0d441f9aff4d4b4edd8969ad1d2139282b55", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-mistral-dolphin-orca-platypus-samantha-7b-dare-0.85", @@ -38183,6 +53018,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-Mistral-7b-v1.2", + "Average \u2b06\ufe0f": 62.04, + "ARC": 57.51, + "HellaSwag": 79.61, + "MMLU": 58.04, + "TruthfulQA": 46.7, + "Winogrande": 75.37, + "GSM8K": 55.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.37, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "52d060cd9e93f176911c91ee232f582f253e7f8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "IDEA-CCNL\/Ziya2-13B-Base", + "Average \u2b06\ufe0f": 62.04, + "ARC": 54.01, + "HellaSwag": 78.9, + "MMLU": 61.32, + "TruthfulQA": 42.74, + "Winogrande": 74.82, + "GSM8K": 60.42, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "91c5a0b534aaae12e59a092459e52814fb42bd88", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "Aeala\/Alpaca-elina-65b", @@ -38206,6 +53087,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Mistral-7B-v0.1-gpt-4-80k", + "Average \u2b06\ufe0f": 62.0, + "ARC": 62.8, + "HellaSwag": 81.05, + "MMLU": 63.21, + "TruthfulQA": 54.6, + "Winogrande": 74.03, + "GSM8K": 36.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dceff6501d72e838b02f13b86ccb622cf6e3d8d7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "kyujinpy\/PlatYi-34B-200K-Q", @@ -38315,7 +53219,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "e37831e09cff71bfa2659430bbfa1a210729ea5a", "Flagged": false, @@ -38338,12 +53242,81 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 624.0, + "Hub \u2764\ufe0f": 642.0, "Available on the hub": true, "Model sha": "2539ff53e6baa4cc603774ad5a2d646f4041ea4e", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-v0.1-gpt-4-60k", + "Average \u2b06\ufe0f": 61.98, + "ARC": 62.88, + "HellaSwag": 80.78, + "MMLU": 62.87, + "TruthfulQA": 53.91, + "Winogrande": 73.72, + "GSM8K": 37.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c3a1e2f26584a0220b79b58485f22318f3e9e923", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Mistral-7B-v0.1-gpt-4-60k", + "Average \u2b06\ufe0f": 61.98, + "ARC": 62.88, + "HellaSwag": 80.78, + "MMLU": 62.87, + "TruthfulQA": 53.91, + "Winogrande": 73.72, + "GSM8K": 37.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2a9f61ae0dc9c9dd6f80efad6b001b72cf90157a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KeyonZeng\/lion-zephyr-7b", + "Average \u2b06\ufe0f": 61.98, + "ARC": 63.05, + "HellaSwag": 84.88, + "MMLU": 60.98, + "TruthfulQA": 58.78, + "Winogrande": 78.22, + "GSM8K": 25.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06b27af23fa0638c7ed705043a4fa4a63a4b90bc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "chargoddard\/MelangeC-70b", @@ -38384,12 +53357,58 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1312.0, + "Hub \u2764\ufe0f": 1396.0, "Available on the hub": true, "Model sha": "8af01af3d4f9dc9b962447180d6d0f8c5315da86", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "01-ai\/Yi-9B-200K", + "Average \u2b06\ufe0f": 61.94, + "ARC": 58.02, + "HellaSwag": 78.58, + "MMLU": 70.34, + "TruthfulQA": 40.63, + "Winogrande": 76.48, + "GSM8K": 47.61, + "Type": "continuously pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.83, + "Hub \u2764\ufe0f": 65.0, + "Available on the hub": true, + "Model sha": "f5ced3c13a454363282a9c463d30b6cf5b989893", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-v0.1-gpt-4-20k", + "Average \u2b06\ufe0f": 61.93, + "ARC": 62.71, + "HellaSwag": 81.73, + "MMLU": 62.85, + "TruthfulQA": 54.7, + "Winogrande": 72.93, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f64d57716913038d3928cef575cdc6c82ae7436f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "vicgalle\/zephyr-7b-truthy", @@ -38430,7 +53449,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "2bf026af438d522268533484a85a3e54178e7809", "Flagged": false, @@ -38482,6 +53501,75 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-2.1-Mistral-7B", + "Average \u2b06\ufe0f": 61.9, + "ARC": 59.9, + "HellaSwag": 83.3, + "MMLU": 61.46, + "TruthfulQA": 47.58, + "Winogrande": 79.01, + "GSM8K": 40.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1f3258db979c9cfc73e9a8a0bbd69757366fc921", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-jondurbin-truthy-dpo", + "Average \u2b06\ufe0f": 61.9, + "ARC": 60.75, + "HellaSwag": 83.89, + "MMLU": 63.65, + "TruthfulQA": 48.45, + "Winogrande": 77.98, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d6705a82098d5f01fb0effbba395c818ad9bf5b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NeuralNovel\/Senzu-7B-v0.1-DPO", + "Average \u2b06\ufe0f": 61.9, + "ARC": 66.72, + "HellaSwag": 84.34, + "MMLU": 62.12, + "TruthfulQA": 45.29, + "Winogrande": 79.95, + "GSM8K": 32.98, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b3f8b6d9d500024ccbe2b2a19eb4850046e24851", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "spmurrayzzz\/Mistral-Syndicate-7B", @@ -38505,16 +53593,62 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v5-mistral-7b", + "Average \u2b06\ufe0f": 61.88, + "ARC": 62.63, + "HellaSwag": 84.26, + "MMLU": 62.45, + "TruthfulQA": 51.83, + "Winogrande": 78.3, + "GSM8K": 31.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67260800a04ea5cc751aec4998c3a74ce5e40c33", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "andysalerno\/rainbowfish-7B-v10", "Average \u2b06\ufe0f": 61.88, - "ARC": 61.18, - "HellaSwag": 82.33, - "MMLU": 63.26, - "TruthfulQA": 49.45, - "Winogrande": 78.06, - "GSM8K": 37.0, + "ARC": 61.18, + "HellaSwag": 82.33, + "MMLU": 63.26, + "TruthfulQA": 49.45, + "Winogrande": 78.06, + "GSM8K": 37.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "22a4cd7ecfdafb957ba2233b9c06fccd70663cfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-2.0-Mistral-7B", + "Average \u2b06\ufe0f": 61.88, + "ARC": 61.09, + "HellaSwag": 83.5, + "MMLU": 63.68, + "TruthfulQA": 41.97, + "Winogrande": 79.24, + "GSM8K": 41.77, "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "MistralForCausalLM", "Weight type": "Original", @@ -38522,9 +53656,9 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "22a4cd7ecfdafb957ba2233b9c06fccd70663cfa", + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "c12978bd7a8322533bfb8e077f32e8de89b2f63c", "Flagged": false, "MoE": false }, @@ -38574,6 +53708,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-tak-stack-dpo", + "Average \u2b06\ufe0f": 61.86, + "ARC": 61.18, + "HellaSwag": 83.98, + "MMLU": 64.32, + "TruthfulQA": 43.8, + "Winogrande": 79.32, + "GSM8K": 38.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43b9486705a45d6da632e36a8c33925d9f36bd7f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NeverSleep\/Noromaid-7b-v0.2", @@ -38591,7 +53748,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "bc35358ec19cf0335642228538a83bb306c0e074", "Flagged": false, @@ -38620,6 +53777,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-3.0-Mixtral-3x7B", + "Average \u2b06\ufe0f": 61.84, + "ARC": 60.67, + "HellaSwag": 83.28, + "MMLU": 63.22, + "TruthfulQA": 43.46, + "Winogrande": 79.01, + "GSM8K": 41.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "5d2ce88eac4a5081053d8400c0d99982147d4933", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/bagel-8x7b-v0.2", @@ -38683,7 +53863,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "bc35358ec19cf0335642228538a83bb306c0e074", "Flagged": false, @@ -38707,7 +53887,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e63792701d6136288b95c9c8f24c0030ff5698b0", "Flagged": false, "MoE": false @@ -38730,7 +53910,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2e9d6998ce40ffb43ba1d8636a84bf38bf922892", "Flagged": false, "MoE": false @@ -38752,7 +53932,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.72, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "e52fa2ef47411cc8bc9f752d1d8d9072b37742e7", "Flagged": false, @@ -38798,7 +53978,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "0e51981702ee1f4c3162915e4ac5233591821af8", "Flagged": false, @@ -38822,11 +54002,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "77f7bf749a6c4561b5364b291152b54ba19a59fb", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "pansophic\/new_model_test2", + "Average \u2b06\ufe0f": 61.7, + "ARC": 62.03, + "HellaSwag": 75.36, + "MMLU": 56.03, + "TruthfulQA": 46.54, + "Winogrande": 77.03, + "GSM8K": 53.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f8b3ddd61dcf89f6ee6c5cac4185ff6c00f767a0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NovoCode\/Metabird-7b-DPO", @@ -38850,6 +54053,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abideen\/Mistral-v2-orpo", + "Average \u2b06\ufe0f": 61.7, + "ARC": 60.92, + "HellaSwag": 83.45, + "MMLU": 63.66, + "TruthfulQA": 44.21, + "Winogrande": 78.37, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e807af8144a42a9fcd61f99da1460229f48b8398", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "amu\/spin-phi2", + "Average \u2b06\ufe0f": 61.68, + "ARC": 63.57, + "HellaSwag": 75.57, + "MMLU": 57.93, + "TruthfulQA": 46.22, + "Winogrande": 73.48, + "GSM8K": 53.3, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "5040b8b4108f00030839472e5c97d7c5944904e7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "fhai50032\/SamChat", @@ -38873,6 +54122,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "amu\/spin-phi2", + "Average \u2b06\ufe0f": 61.67, + "ARC": 63.14, + "HellaSwag": 75.56, + "MMLU": 57.08, + "TruthfulQA": 45.77, + "Winogrande": 74.19, + "GSM8K": 54.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "b206227dcf0c36eb30edcee377e5b0ccdd3668c9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Gryphe\/MythoMist-7b", @@ -38896,6 +54168,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/hyperion-medium-preview", + "Average \u2b06\ufe0f": 61.67, + "ARC": 60.67, + "HellaSwag": 83.67, + "MMLU": 63.73, + "TruthfulQA": 42.93, + "Winogrande": 78.53, + "GSM8K": 40.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "10ca1480890fc2f84c78941d81b3950efbb2c995", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/NeuralHyperion-Medium-Preview", + "Average \u2b06\ufe0f": 61.67, + "ARC": 60.67, + "HellaSwag": 83.67, + "MMLU": 63.73, + "TruthfulQA": 42.93, + "Winogrande": 78.53, + "GSM8K": 40.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "a7c0648096a20b3c92b73628e0fb441f0968820b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NickyNicky\/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2", @@ -38913,12 +54231,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "f01f41dc7c987ad6668931159feaa4469f7dcf3f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "tcapelle\/gemma-7b-zephyr-sft", + "Average \u2b06\ufe0f": 61.64, + "ARC": 61.43, + "HellaSwag": 80.73, + "MMLU": 60.33, + "TruthfulQA": 43.35, + "Winogrande": 74.19, + "GSM8K": 49.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "51918d1d0284e398a08f3b74b642f940efc925be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/gemma-7b-zephyr-sft", + "Average \u2b06\ufe0f": 61.64, + "ARC": 61.43, + "HellaSwag": 80.73, + "MMLU": 60.33, + "TruthfulQA": 43.35, + "Winogrande": 74.19, + "GSM8K": 49.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "51918d1d0284e398a08f3b74b642f940efc925be", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "andysalerno\/rainbowfish-v6", @@ -38965,6 +54329,98 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/gemma-7b-zephyr-dpo", + "Average \u2b06\ufe0f": 61.62, + "ARC": 60.84, + "HellaSwag": 80.44, + "MMLU": 60.6, + "TruthfulQA": 42.48, + "Winogrande": 75.37, + "GSM8K": 49.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a3980aba73509cc3fa7553dd612478ac589255ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tcapelle\/gemma-7b-zephyr-dpo", + "Average \u2b06\ufe0f": 61.62, + "ARC": 60.84, + "HellaSwag": 80.44, + "MMLU": 60.6, + "TruthfulQA": 42.48, + "Winogrande": 75.37, + "GSM8K": 49.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a3980aba73509cc3fa7553dd612478ac589255ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/merlin1", + "Average \u2b06\ufe0f": 61.6, + "ARC": 60.67, + "HellaSwag": 74.55, + "MMLU": 57.86, + "TruthfulQA": 48.35, + "Winogrande": 74.98, + "GSM8K": 53.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eb6ead2cd06e254435c9ea39070bbcefc42e21a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vankhoa\/test_phi2", + "Average \u2b06\ufe0f": 61.6, + "ARC": 61.18, + "HellaSwag": 75.14, + "MMLU": 58.3, + "TruthfulQA": 44.44, + "Winogrande": 74.82, + "GSM8K": 55.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "be1f3e718cf8386d6ce637b9fb2eb37c2deeea09", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "hiyouga\/Qwen-14B-Chat-LLaMAfied", @@ -38982,7 +54438,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 14.17, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "29e92e74dca4a79aa8c2c451287ff97c4dccb323", "Flagged": false, @@ -39005,7 +54461,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 38.5, - "Hub \u2764\ufe0f": 50.0, + "Hub \u2764\ufe0f": 55.0, "Available on the hub": true, "Model sha": "19961590ae95ccd9316b13c66098cd61b28a7d5a", "Flagged": false, @@ -39028,7 +54484,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 523.0, + "Hub \u2764\ufe0f": 531.0, "Available on the hub": true, "Model sha": "3995e9a13d54ce95f0ad55de2eaa92e2dc580174", "Flagged": false, @@ -39051,7 +54507,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 523.0, + "Hub \u2764\ufe0f": 531.0, "Available on the hub": true, "Model sha": "af2489cde09e9d2c175622f651875e83824c4b10", "Flagged": false, @@ -39097,12 +54553,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1312.0, + "Hub \u2764\ufe0f": 1396.0, "Available on the hub": true, "Model sha": "0f17b36adfbe7d86ea1c591a9efeeae17b313f48", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Isaak-Carter\/J.O.S.I.E.3-Beta8-slerp", + "Average \u2b06\ufe0f": 61.56, + "ARC": 60.41, + "HellaSwag": 83.66, + "MMLU": 62.35, + "TruthfulQA": 48.69, + "Winogrande": 78.14, + "GSM8K": 36.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6d97107268cbc28317cba748ce281f11a6f50ce9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "Deci\/DeciLM-7B", @@ -39189,12 +54668,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 523.0, + "Hub \u2764\ufe0f": 531.0, "Available on the hub": true, "Model sha": "3995e9a13d54ce95f0ad55de2eaa92e2dc580174", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mistral2-7b-v20.1-32k", + "Average \u2b06\ufe0f": 61.53, + "ARC": 53.5, + "HellaSwag": 77.76, + "MMLU": 59.76, + "TruthfulQA": 52.97, + "Winogrande": 75.06, + "GSM8K": 50.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "242cedbcfa8d0c846a27ba89675b19335f6444ff", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "teknium\/OpenHermes-2.5-Mistral-7B", @@ -39212,7 +54714,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 662.0, + "Hub \u2764\ufe0f": 739.0, "Available on the hub": true, "Model sha": "2a54cad766bc90828354db5c4199795aecfd0df1", "Flagged": false, @@ -39259,11 +54761,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "17dcf2e98fa91317316b05f5ff27ae24b31139aa", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-3.0-Mistral-7B-alpha", + "Average \u2b06\ufe0f": 61.52, + "ARC": 59.98, + "HellaSwag": 83.48, + "MMLU": 62.5, + "TruthfulQA": 42.82, + "Winogrande": 78.77, + "GSM8K": 41.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "ca8e69436624292143bda2c80be29d9d47becfb1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/Mistral-7B-OpenOrca-lora-merged", @@ -39287,6 +54812,98 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "0-hero\/Matter-0.1-Slim-7B-preview", + "Average \u2b06\ufe0f": 61.51, + "ARC": 59.98, + "HellaSwag": 80.66, + "MMLU": 61.53, + "TruthfulQA": 42.55, + "Winogrande": 77.35, + "GSM8K": 47.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "191ddd498835979ffc2b7bcb405f2f0d1cceed61", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "field2437\/phi-2-test", + "Average \u2b06\ufe0f": 61.51, + "ARC": 60.41, + "HellaSwag": 75.12, + "MMLU": 58.03, + "TruthfulQA": 45.46, + "Winogrande": 74.59, + "GSM8K": 55.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3e927bee6cff8a275a4a6aefa31e3f29a697ad5e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "field2437\/phi-2-platypus-Commercial-lora", + "Average \u2b06\ufe0f": 61.51, + "ARC": 60.41, + "HellaSwag": 75.12, + "MMLU": 58.03, + "TruthfulQA": 45.46, + "Winogrande": 74.59, + "GSM8K": 55.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "30ab76e8ec296e5e49a3a4a6933783964e269b40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/phi-2-logical-sft", + "Average \u2b06\ufe0f": 61.5, + "ARC": 61.35, + "HellaSwag": 75.14, + "MMLU": 57.4, + "TruthfulQA": 44.39, + "Winogrande": 74.9, + "GSM8K": 55.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "6efbdcdfc50d1b9387de01e58c3746f8a1677a61", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NeverSleep\/Noromaid-7b-v0.1.1", @@ -39304,12 +54921,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "349a2eb5c61e3e13c2b39d15c7b94f5c31ab6bd5", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/zephyr-7b-gemma-v0.1", + "Average \u2b06\ufe0f": 61.48, + "ARC": 57.94, + "HellaSwag": 82.91, + "MMLU": 58.98, + "TruthfulQA": 52.47, + "Winogrande": 72.53, + "GSM8K": 44.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 106.0, + "Available on the hub": true, + "Model sha": "19186e70e5679c47aaef473ae2fd56e20765088d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/robin-65b-v2-fp16", @@ -39393,7 +55033,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 19.99, "Hub \u2764\ufe0f": 0.0, @@ -39419,7 +55059,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 662.0, + "Hub \u2764\ufe0f": 739.0, "Available on the hub": true, "Model sha": "2a54cad766bc90828354db5c4199795aecfd0df1", "Flagged": false, @@ -39442,9 +55082,55 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "17dcf2e98fa91317316b05f5ff27ae24b31139aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-qwen1.5-en-7b", + "Average \u2b06\ufe0f": 61.44, + "ARC": 53.41, + "HellaSwag": 75.51, + "MMLU": 61.67, + "TruthfulQA": 51.96, + "Winogrande": 70.72, + "GSM8K": 55.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "173ccc71f9c2efca1c3494d94956fe100829e5ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hyperion-1.5-Mistral-7B", + "Average \u2b06\ufe0f": 61.43, + "ARC": 60.49, + "HellaSwag": 83.64, + "MMLU": 63.57, + "TruthfulQA": 41.78, + "Winogrande": 78.61, + "GSM8K": 40.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, - "Model sha": "17dcf2e98fa91317316b05f5ff27ae24b31139aa", + "Model sha": "ff35c0c0b6f925ac510a6692cc21e813457b1fbb", "Flagged": false, "MoE": false }, @@ -39466,7 +55152,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "c1b344f0efaacd2309d22dcbe4358a00bdd50f15", "Flagged": false, "MoE": false @@ -39488,7 +55174,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 46.0, "Available on the hub": true, "Model sha": "13f00a0e36500c80ce12870ea513846a066004af", "Flagged": false, @@ -39540,6 +55226,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "zhengchenphd\/ICE-GRT", + "Average \u2b06\ufe0f": 61.39, + "ARC": 62.88, + "HellaSwag": 86.14, + "MMLU": 57.34, + "TruthfulQA": 53.17, + "Winogrande": 77.11, + "GSM8K": 31.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "51b7c0c3f8439d648190c140dea1e14cab40ac11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-distilabel-truthy-dpo", + "Average \u2b06\ufe0f": 61.39, + "ARC": 60.92, + "HellaSwag": 83.64, + "MMLU": 64.18, + "TruthfulQA": 45.12, + "Winogrande": 78.37, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "885601cb9baf6c0b18b421e9e36c47692abb898c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "fionazhang\/fine-tune-mistral-environment-merge", @@ -39583,7 +55315,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "2cbe1e99144674ff0570a6a38b75c4666ed16087", - "Flagged": true, + "Flagged": false, "MoE": true }, { @@ -39634,7 +55366,7 @@ }, { "T": "\ud83d\udcac", - "Model": "Mihaiii\/Metis-0.3-merged", + "Model": "Mihaiii\/Metis-0.4", "Average \u2b06\ufe0f": 61.34, "ARC": 62.2, "HellaSwag": 84.0, @@ -39643,21 +55375,21 @@ "Winogrande": 78.14, "GSM8K": 21.83, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "Unknown", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "dbcf2c1f7cbea0bacd756f7d8251b5bb037e28d3", + "Model sha": "c2b149c7df2806add971b2c2ec27288abc18f312", "Flagged": false, "MoE": false }, { "T": "\ud83d\udcac", - "Model": "Mihaiii\/Metis-0.4", + "Model": "Mihaiii\/Metis-0.3-merged", "Average \u2b06\ufe0f": 61.34, "ARC": 62.2, "HellaSwag": 84.0, @@ -39666,15 +55398,15 @@ "Winogrande": 78.14, "GSM8K": 21.83, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "MistralForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "c2b149c7df2806add971b2c2ec27288abc18f312", + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dbcf2c1f7cbea0bacd756f7d8251b5bb037e28d3", "Flagged": false, "MoE": false }, @@ -39718,7 +55450,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 2847.0, + "Hub \u2764\ufe0f": 3014.0, "Available on the hub": true, "Model sha": "d3186761bf5c4409f7679359284066c25ab668ee", "Flagged": false, @@ -39793,6 +55525,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/NeuralHyperion-2.0-Mistral-7B", + "Average \u2b06\ufe0f": 61.27, + "ARC": 57.76, + "HellaSwag": 82.29, + "MMLU": 61.9, + "TruthfulQA": 45.5, + "Winogrande": 79.01, + "GSM8K": 41.17, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "01cfc8a66cab065fba04130e64a89743c881aeca", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "dball\/zephyr-7b-dpo-qlora", @@ -39811,7 +55566,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "8fef86af4ca1c140559450cace2fd1839f979020", "Flagged": false, "MoE": false @@ -39833,7 +55588,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "43abfcab8bf532a2601ed6e61e0c3614272b7df9", "Flagged": false, @@ -39856,7 +55611,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "46d19a6f4e37644a426b0a6917959cf4bb388ef1", "Flagged": false, @@ -39902,12 +55657,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 218.0, + "Hub \u2764\ufe0f": 223.0, "Available on the hub": true, "Model sha": "6dae38060d70b82dcfe787a612d04aaf0adf0738", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/WikiHow-Mistral-Instruct-7B", + "Average \u2b06\ufe0f": 61.25, + "ARC": 60.92, + "HellaSwag": 80.99, + "MMLU": 58.57, + "TruthfulQA": 62.16, + "Winogrande": 74.82, + "GSM8K": 30.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "4ad83e84cf315977c49c96e91dc28f09f86987f9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "openchat\/openchat_3.5", @@ -39925,7 +55703,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 1051.0, + "Hub \u2764\ufe0f": 1078.0, "Available on the hub": true, "Model sha": "5b874a33a91d63023055e6cb2d5d86afe883b4ec", "Flagged": false, @@ -39954,6 +55732,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "clowman\/openchat-mistral-7b-reproduce", + "Average \u2b06\ufe0f": 61.23, + "ARC": 57.25, + "HellaSwag": 80.72, + "MMLU": 61.54, + "TruthfulQA": 55.81, + "Winogrande": 72.53, + "GSM8K": 39.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "338660d3330af39bfadab520d1e925351d7d4924", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "openchat\/openchat_3.5", @@ -39971,7 +55772,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 1051.0, + "Hub \u2764\ufe0f": 1078.0, "Available on the hub": true, "Model sha": "5b874a33a91d63023055e6cb2d5d86afe883b4ec", "Flagged": false, @@ -40000,6 +55801,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "GritLM\/GritLM-7B", + "Average \u2b06\ufe0f": 61.21, + "ARC": 58.11, + "HellaSwag": 80.91, + "MMLU": 60.02, + "TruthfulQA": 45.81, + "Winogrande": 77.82, + "GSM8K": 44.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 46.0, + "Available on the hub": true, + "Model sha": "13f00a0e36500c80ce12870ea513846a066004af", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-65b-gpt4-2.0", @@ -40023,6 +55847,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/DarkForest-20B-v2.0", + "Average \u2b06\ufe0f": 61.19, + "ARC": 63.74, + "HellaSwag": 86.32, + "MMLU": 59.79, + "TruthfulQA": 56.14, + "Winogrande": 77.9, + "GSM8K": 23.28, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "cf6373fce58fce760c958f1504259297fa0bda3b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "huggingface\/llama-65b", @@ -40069,6 +55916,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Liberated-Qwen1.5-7B", + "Average \u2b06\ufe0f": 61.17, + "ARC": 52.05, + "HellaSwag": 76.59, + "MMLU": 61.25, + "TruthfulQA": 50.94, + "Winogrande": 72.14, + "GSM8K": 54.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "8619393688e7a490f4855ce108ca7358503cfe7e", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-mistral-hermes-code-7b", @@ -40230,6 +56100,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Qwen1.5-8x7b-v0.1", + "Average \u2b06\ufe0f": 61.14, + "ARC": 51.62, + "HellaSwag": 75.71, + "MMLU": 59.61, + "TruthfulQA": 55.78, + "Winogrande": 69.93, + "GSM8K": 54.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 38.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "1cc77bff283c5e5fee805d5220dc7da2fbfc29f5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CorticalStack\/mistral-7b-openhermes-2.5-sft", @@ -40245,7 +56138,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -40253,6 +56146,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "maldv\/SHRDFU-7b-beta", + "Average \u2b06\ufe0f": 61.13, + "ARC": 66.38, + "HellaSwag": 85.03, + "MMLU": 60.29, + "TruthfulQA": 49.45, + "Winogrande": 77.74, + "GSM8K": 27.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "069b89231682be68466942567f80c2913199aff5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "ehartford\/dolphin-2.1-mistral-7b", @@ -40271,11 +56187,103 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aa5bd48c8b3040d1155a8fd59328df160aa63680", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 61.12, + "ARC": 59.64, + "HellaSwag": 81.52, + "MMLU": 60.57, + "TruthfulQA": 53.09, + "Winogrande": 76.8, + "GSM8K": 35.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "aad44cdaf573542f8d4821072e8a33f798dfc714", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Replete-AI\/Phi-Elothir", + "Average \u2b06\ufe0f": 61.11, + "ARC": 59.56, + "HellaSwag": 75.63, + "MMLU": 58.45, + "TruthfulQA": 51.23, + "Winogrande": 73.88, + "GSM8K": 47.92, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 5.14, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "147462ec7112778bc5f51b932b9f0691f93314c4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "amu\/spin-phi2-1.5", + "Average \u2b06\ufe0f": 61.11, + "ARC": 63.65, + "HellaSwag": 75.79, + "MMLU": 56.52, + "TruthfulQA": 46.4, + "Winogrande": 73.16, + "GSM8K": 51.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5c9c6b9819b1a1631ac4d6db1e93b011a318756c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "amu\/spin-phi2-2", + "Average \u2b06\ufe0f": 61.11, + "ARC": 63.65, + "HellaSwag": 75.79, + "MMLU": 56.52, + "TruthfulQA": 46.4, + "Winogrande": 73.16, + "GSM8K": 51.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5c9c6b9819b1a1631ac4d6db1e93b011a318756c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Zardos\/Kant-Test-0.1-Mistral-7B", @@ -40299,6 +56307,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "l3utterfly\/phi-2-layla-v1", + "Average \u2b06\ufe0f": 61.09, + "ARC": 60.84, + "HellaSwag": 75.0, + "MMLU": 57.85, + "TruthfulQA": 44.01, + "Winogrande": 74.19, + "GSM8K": 54.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "ee7cc7a033d7ed83df82037a4dca85c19976d8bd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "pinkyponky\/Mistral-7B-Instruct-Sft-Tuned-V0.2", @@ -40314,7 +56345,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -40339,12 +56370,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 14.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "458f098e529e7ec670a02cc7b75a1a74496984a8", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "lole25\/phi-2-sft-lora-ultrachat", + "Average \u2b06\ufe0f": 61.07, + "ARC": 61.26, + "HellaSwag": 74.86, + "MMLU": 57.26, + "TruthfulQA": 45.46, + "Winogrande": 74.19, + "GSM8K": 53.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "09f410606332b5d29075d7031420291e257de570", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "Dans-DiscountModels\/Dans-07YahooAnswers-7b", @@ -40368,6 +56422,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-v0.1-raw-80k", + "Average \u2b06\ufe0f": 61.07, + "ARC": 61.52, + "HellaSwag": 83.57, + "MMLU": 63.67, + "TruthfulQA": 43.02, + "Winogrande": 78.53, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "24fd76a0416c83b6f306db4f3795ed5c576095e7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "TencentARC\/Mistral_Pro_8B_v0.1", @@ -40385,12 +56462,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 8.99, - "Hub \u2764\ufe0f": 48.0, + "Hub \u2764\ufe0f": 62.0, "Available on the hub": true, "Model sha": "acae0ffeb040f1ee654068403a0305263e932ee0", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/experiment2-cause", + "Average \u2b06\ufe0f": 61.05, + "ARC": 60.41, + "HellaSwag": 82.76, + "MMLU": 62.15, + "TruthfulQA": 47.13, + "Winogrande": 78.85, + "GSM8K": 35.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4d6f888de5ba44d5ca8ef766c54e92103a0afe16", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/experiment2-cause-qLoRa", + "Average \u2b06\ufe0f": 61.05, + "ARC": 60.41, + "HellaSwag": 82.76, + "MMLU": 62.15, + "TruthfulQA": 47.13, + "Winogrande": 78.85, + "GSM8K": 35.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4d6f888de5ba44d5ca8ef766c54e92103a0afe16", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "kimwooglae\/AISquare-Instruct-SOLAR-10.7b-v0.5.31", @@ -40414,6 +56537,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "gmonsoon\/Delta-4B-Base", + "Average \u2b06\ufe0f": 61.04, + "ARC": 58.62, + "HellaSwag": 76.29, + "MMLU": 59.06, + "TruthfulQA": 51.74, + "Winogrande": 73.64, + "GSM8K": 46.93, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b052176caad85b31111242ad67aa84a41efb3e13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/delta-4B-super", + "Average \u2b06\ufe0f": 61.04, + "ARC": 58.62, + "HellaSwag": 76.29, + "MMLU": 59.06, + "TruthfulQA": 51.74, + "Winogrande": 73.64, + "GSM8K": 46.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "680f13a7d44182d799a826c52f3929590f5fd4d6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "venkycs\/ZySec-7B-Adapter", @@ -40437,6 +56606,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "KeyonZeng\/philion-2", + "Average \u2b06\ufe0f": 61.02, + "ARC": 61.6, + "HellaSwag": 75.06, + "MMLU": 58.12, + "TruthfulQA": 44.47, + "Winogrande": 74.27, + "GSM8K": 52.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "90f0c46c25ed0bc5bf1cbec18405e2793b7a3d58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/OpenCerebrum-1.0-7b-SFT", + "Average \u2b06\ufe0f": 61.01, + "ARC": 60.07, + "HellaSwag": 83.25, + "MMLU": 62.71, + "TruthfulQA": 41.45, + "Winogrande": 79.16, + "GSM8K": 39.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "05f8aa218b005048ad9aef2e72852b4ac376766a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-mistral-hermes-code-7b", @@ -40478,11 +56693,103 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aa5bd48c8b3040d1155a8fd59328df160aa63680", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Mistral-7B-v0.1-activity-fine-tuned-v2", + "Average \u2b06\ufe0f": 60.98, + "ARC": 60.07, + "HellaSwag": 83.3, + "MMLU": 64.09, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "72f64c7d384fde5d89736efa5a514cae84a2995f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Mistral-7B-v0.1-activity-fine-tuned-v3", + "Average \u2b06\ufe0f": 60.98, + "ARC": 60.07, + "HellaSwag": 83.3, + "MMLU": 64.09, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ee975408108178dcd9b4f3bfbb5ed000357ce6b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Mistral-7B-v0.1-activity-fine-tuned-v5", + "Average \u2b06\ufe0f": 60.98, + "ARC": 60.07, + "HellaSwag": 83.3, + "MMLU": 64.09, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ddeca14550068d75b10801ab1d261632b15f6264", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Mistral-7B-v0.1-gpt-4-20k", + "Average \u2b06\ufe0f": 60.98, + "ARC": 60.07, + "HellaSwag": 83.3, + "MMLU": 64.09, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "31724e80517950b4b80e03754619be2b24b824af", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Cartinoe5930\/Llama2_init_Mistral", @@ -40523,7 +56830,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2845.0, + "Hub \u2764\ufe0f": 3047.0, "Available on the hub": true, "Model sha": "e836d8f71b5812f9fee65618453dc537c66bd82a", "Flagged": false, @@ -40544,7 +56851,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -40621,6 +56928,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Mistralpaca-7B", + "Average \u2b06\ufe0f": 60.94, + "ARC": 62.03, + "HellaSwag": 83.44, + "MMLU": 59.5, + "TruthfulQA": 53.17, + "Winogrande": 74.35, + "GSM8K": 33.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a118f6f3cb1121fb6ce916c24280874b4e2c09d1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Reverb\/Mistral-7B-LoreWeaver", @@ -40684,7 +57014,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "48beb1e9490732abc6f85d92579d407d85e2cf5d", "Flagged": false, @@ -40710,7 +57040,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "814ea2c4ddaf2c1b6e4780ff061f899b684a8275", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -40754,7 +57084,7 @@ "Hub License": "mit", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "120e8a957f9889b744ae4d5fcf871f57f6bb4264", "Flagged": false, "MoE": false @@ -40799,7 +57129,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "0ea960b3343ec36e7f130d45d140fe192acf344b", "Flagged": false, @@ -40843,10 +57173,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 65.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, "Model sha": "aa5bd88bd132925cf2dd5c44eceafdb5ed5e5be4", "Flagged": false, "MoE": false @@ -40874,6 +57204,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-Instruct-v0.2-gpt-4-80k-base_lora", + "Average \u2b06\ufe0f": 60.86, + "ARC": 59.47, + "HellaSwag": 79.7, + "MMLU": 58.5, + "TruthfulQA": 68.32, + "Winogrande": 70.32, + "GSM8K": 28.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dcd5376d301a535e8cb58c78a69c39332848af7c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "huseyinatahaninan\/phi-2-instruction", @@ -40892,7 +57245,7 @@ "Hub License": "mit", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "120e8a957f9889b744ae4d5fcf871f57f6bb4264", "Flagged": false, "MoE": false @@ -40983,12 +57336,58 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "36f6450a618d8e665097df2891f30e0dcbcf82ce", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "linlinlin\/zephy_SFT_Hermes", + "Average \u2b06\ufe0f": 60.8, + "ARC": 60.32, + "HellaSwag": 83.37, + "MMLU": 63.81, + "TruthfulQA": 42.17, + "Winogrande": 78.06, + "GSM8K": 37.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d64495ffe34dbd40d5fe93639ca6f967d7c684cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/llmdo-Mistral-7B-case-c", + "Average \u2b06\ufe0f": 60.8, + "ARC": 60.92, + "HellaSwag": 82.92, + "MMLU": 61.8, + "TruthfulQA": 44.69, + "Winogrande": 78.61, + "GSM8K": 35.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8d36b11a83dd1d4f69fbfedcbf13907ffba21756", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "CalderaAI\/30B-Epsilon", @@ -41012,6 +57411,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "awnr\/Mistral-7B-v0.1-half-naive-A", + "Average \u2b06\ufe0f": 60.79, + "ARC": 60.32, + "HellaSwag": 83.22, + "MMLU": 64.16, + "TruthfulQA": 42.28, + "Winogrande": 77.9, + "GSM8K": 36.85, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "76e4d06445c9048988beaa9d44b294258796b98c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-mistral-dolphin-orca-platypus-samantha-7b", @@ -41127,6 +57549,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "l3utterfly\/phi-2-layla-v1-chatml", + "Average \u2b06\ufe0f": 60.77, + "ARC": 60.41, + "HellaSwag": 74.58, + "MMLU": 56.62, + "TruthfulQA": 44.21, + "Winogrande": 74.27, + "GSM8K": 54.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "d65e3ff599f4b83cbf372ecf5665138dc923ddc0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "OpenBuddyEA\/openbuddy-llama-30b-v7.1-bf16", @@ -41145,7 +57590,7 @@ "Hub License": "?", "#Params (B)": 32.35, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "85f7ad9d6ff016312262a47d45ffd07dee54aab0", "Flagged": false, "MoE": false @@ -41167,7 +57612,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "41e912e0f79094a80687f88ca5555f84aa9d307f", "Flagged": false, @@ -41190,7 +57635,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 65.0, + "Hub \u2764\ufe0f": 64.0, "Available on the hub": false, "Model sha": "1a0d1d72a40946463fb4a9780207da19bfecc38b", "Flagged": false, @@ -41213,7 +57658,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "dba42d919d7c2f6ccc2e42a4e75d4225e2725d00", "Flagged": false, @@ -41242,6 +57687,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/merlin1.3", + "Average \u2b06\ufe0f": 60.74, + "ARC": 59.98, + "HellaSwag": 75.19, + "MMLU": 57.66, + "TruthfulQA": 46.77, + "Winogrande": 75.93, + "GSM8K": 48.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4fa78a0c685d8ddeb3977aca081e0da3135a9717", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Venomia-m7", @@ -41265,6 +57733,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "chlee10\/T3Q-platypus-SOLAR-10.7B-v1.0", + "Average \u2b06\ufe0f": 60.71, + "ARC": 62.54, + "HellaSwag": 84.15, + "MMLU": 61.95, + "TruthfulQA": 51.91, + "Winogrande": 83.11, + "GSM8K": 20.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9a088d12a72e8cefe9d42943e64faf08bc0eb5c3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "OpenBuddyEA\/openbuddy-llama-30b-v7.1-bf16", @@ -41283,7 +57774,7 @@ "Hub License": "?", "#Params (B)": 32.35, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "85f7ad9d6ff016312262a47d45ffd07dee54aab0", "Flagged": false, "MoE": false @@ -41305,7 +57796,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 15.83, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "183d749c4556abc66f6fd0d821d1d193e80053c1", "Flagged": false, @@ -41374,7 +57865,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 65.0, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "ae256799615c16443f9c423c653ed9f60577e99e", "Flagged": false, @@ -41395,10 +57886,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 65.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "85ae3b595c6b8415df87000c22bc14ea18c174f5", "Flagged": false, "MoE": false @@ -41443,7 +57934,7 @@ "Merged": true, "Hub License": "other", "#Params (B)": 56.7, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "9d7e28d41f1f3221d5fefc48ed495eb921ad4be6", "Flagged": false, @@ -41495,6 +57986,144 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistralai-case-1-0", + "Average \u2b06\ufe0f": 60.63, + "ARC": 60.41, + "HellaSwag": 83.08, + "MMLU": 62.94, + "TruthfulQA": 41.82, + "Winogrande": 78.69, + "GSM8K": 36.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c2ce0cb3094b8eb6b33cf08247d50a16204dd894", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistralai-case-2-0", + "Average \u2b06\ufe0f": 60.63, + "ARC": 60.41, + "HellaSwag": 83.08, + "MMLU": 62.94, + "TruthfulQA": 41.82, + "Winogrande": 78.69, + "GSM8K": 36.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5721e98796e26536d9df830647cc46cc2b34c0a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistralai-case-0-0", + "Average \u2b06\ufe0f": 60.63, + "ARC": 60.41, + "HellaSwag": 83.08, + "MMLU": 62.94, + "TruthfulQA": 41.82, + "Winogrande": 78.69, + "GSM8K": 36.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "15ba501a51a1404a440b2db715695efc9154027a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/merlin1.5", + "Average \u2b06\ufe0f": 60.62, + "ARC": 59.56, + "HellaSwag": 74.63, + "MMLU": 56.59, + "TruthfulQA": 48.03, + "Winogrande": 74.66, + "GSM8K": 50.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dca1ff5cadc7aec0caffe9dae6252af2ce9c0716", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "amu\/orpo-lora-phi2", + "Average \u2b06\ufe0f": 60.62, + "ARC": 60.32, + "HellaSwag": 74.58, + "MMLU": 58.12, + "TruthfulQA": 44.5, + "Winogrande": 73.72, + "GSM8K": 52.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "646be9d724c5c041121426babe71c02b12d8ba31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "0-hero\/Matter-0.1-Slim-7B-B", + "Average \u2b06\ufe0f": 60.61, + "ARC": 60.75, + "HellaSwag": 81.55, + "MMLU": 61.01, + "TruthfulQA": 41.91, + "Winogrande": 77.82, + "GSM8K": 40.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "195d352943c0e71ddffb12eec30b479a07696d11", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Zephyrus-L1-33B", @@ -41518,6 +58147,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistral-7B-alpaca-1-epoch", + "Average \u2b06\ufe0f": 60.61, + "ARC": 61.77, + "HellaSwag": 82.66, + "MMLU": 63.09, + "TruthfulQA": 43.35, + "Winogrande": 77.9, + "GSM8K": 34.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5da747d1460bf5637b82f9e2e1da0e49eb03ec8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "csujeong\/Mistral-7B-Finetuning-Insurance-16R", + "Average \u2b06\ufe0f": 60.6, + "ARC": 60.84, + "HellaSwag": 83.44, + "MMLU": 63.61, + "TruthfulQA": 43.11, + "Winogrande": 78.45, + "GSM8K": 34.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0d0870a954b4741097e3400d52ba8f82ff553dc5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "indischepartij\/OpenMia-Indo-Mistral-7b-v2", @@ -41558,7 +58233,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 65.0, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "ae256799615c16443f9c423c653ed9f60577e99e", "Flagged": false, @@ -41579,13 +58254,13 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-sa-3.0", + "Hub License": "?", "#Params (B)": 38.5, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a06acd48979617eb1af25ede71b937767889218b", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udcac", @@ -41604,7 +58279,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "405a4f1e6513cd1b8de5eb4e003bb49cc86d1f8a", "Flagged": false, @@ -41628,7 +58303,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "001b48e9aebffb395c698af47b6b48364cc3cbe8", "Flagged": false, "MoE": false @@ -41671,9 +58346,9 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "7752f615d76e515aa956335ba8d2705c2cbc297b", "Flagged": false, @@ -41697,7 +58372,7 @@ "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4ff48527af8c3907129c06160c7f7b7b786a5a79", "Flagged": false, "MoE": false @@ -41719,7 +58394,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 72.82, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 36.0, "Available on the hub": true, "Model sha": "c234d7c9c0fd26efb55757fdbfb604d549539fe0", "Flagged": false, @@ -41742,7 +58417,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": false, "Model sha": "d805640fae5928607626d5c89b66a9aaf98da752", "Flagged": false, @@ -41932,6 +58607,75 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/experiment2-cause-non-qLoRa", + "Average \u2b06\ufe0f": 60.44, + "ARC": 60.32, + "HellaSwag": 82.92, + "MMLU": 62.3, + "TruthfulQA": 45.47, + "Winogrande": 78.06, + "GSM8K": 33.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3236726d4a5c4a3e18a8eedf35593bf4b1c14b8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/experiment2-cause-non", + "Average \u2b06\ufe0f": 60.44, + "ARC": 60.32, + "HellaSwag": 82.92, + "MMLU": 62.3, + "TruthfulQA": 45.47, + "Winogrande": 78.06, + "GSM8K": 33.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3236726d4a5c4a3e18a8eedf35593bf4b1c14b8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_dmbr10_32_sig", + "Average \u2b06\ufe0f": 60.43, + "ARC": 58.62, + "HellaSwag": 82.57, + "MMLU": 61.35, + "TruthfulQA": 44.34, + "Winogrande": 77.9, + "GSM8K": 37.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d028c5bfc34a205d9cb215bbf66371765408283d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "ddyuudd\/mistral_dmbr20_32_sig", @@ -41978,6 +58722,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "pansophic\/m17", + "Average \u2b06\ufe0f": 60.42, + "ARC": 59.64, + "HellaSwag": 74.41, + "MMLU": 56.12, + "TruthfulQA": 46.62, + "Winogrande": 75.93, + "GSM8K": 49.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "af805fe99130a741b4d688f9e048b6f69362522f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "WizardLM\/WizardMath-70B-V1.0", @@ -41995,12 +58762,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 111.0, + "Hub \u2764\ufe0f": 115.0, "Available on the hub": true, "Model sha": "e85b43e53c5379e35393b970c66d76c2d1060381", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "aivince\/alpaca_mistral-7b-v0.2", + "Average \u2b06\ufe0f": 60.41, + "ARC": 60.92, + "HellaSwag": 83.28, + "MMLU": 61.82, + "TruthfulQA": 42.66, + "Winogrande": 79.16, + "GSM8K": 34.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a7f91c5db12f3baf8d4e0279dde5a2183ddb070c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "WizardLM\/WizardMath-70B-V1.0", @@ -42018,12 +58808,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 111.0, + "Hub \u2764\ufe0f": 115.0, "Available on the hub": true, "Model sha": "e85b43e53c5379e35393b970c66d76c2d1060381", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/delta-4B-scientific", + "Average \u2b06\ufe0f": 60.41, + "ARC": 59.39, + "HellaSwag": 74.1, + "MMLU": 57.56, + "TruthfulQA": 48.39, + "Winogrande": 75.93, + "GSM8K": 47.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 4.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ec54bb8cac88216c172e941c3adeeb8e1992f1f2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Xenon1\/Xenon-4", @@ -42064,7 +58877,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "75427e93dc99a5e1d8b9aefa106ad36fc750b744", "Flagged": false, @@ -42093,6 +58906,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "pansophic\/m2", + "Average \u2b06\ufe0f": 60.39, + "ARC": 61.26, + "HellaSwag": 75.28, + "MMLU": 54.73, + "TruthfulQA": 48.17, + "Winogrande": 74.19, + "GSM8K": 48.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1be3a323f2d735eb6aad1905c5bfb2bec4475d6f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/Dolphin2.1-OpenOrca-7B", @@ -42116,6 +58952,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "liminerity\/Mistral-quiet-star", + "Average \u2b06\ufe0f": 60.37, + "ARC": 61.18, + "HellaSwag": 84.59, + "MMLU": 62.03, + "TruthfulQA": 45.1, + "Winogrande": 77.11, + "GSM8K": 32.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4756708f7d5dd7044353e2bfc6d971c9aec7c826", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "marcel\/phi-2-openhermes-30k", @@ -42156,7 +59015,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 29.0, + "Hub \u2764\ufe0f": 31.0, "Available on the hub": true, "Model sha": "a9744d8cf9ce4230678a891bcf8bba7cbc0aaece", "Flagged": false, @@ -42208,6 +59067,121 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-Mistral-7bx2-48layers_v1.2", + "Average \u2b06\ufe0f": 60.36, + "ARC": 56.31, + "HellaSwag": 77.83, + "MMLU": 57.91, + "TruthfulQA": 46.12, + "Winogrande": 74.19, + "GSM8K": 49.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ff242b7f1bcebcc1e0f913b934536e66045d8b4b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/merlin1.2", + "Average \u2b06\ufe0f": 60.36, + "ARC": 59.22, + "HellaSwag": 74.19, + "MMLU": 56.45, + "TruthfulQA": 46.24, + "Winogrande": 74.98, + "GSM8K": 51.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "187ce2e4779483483ddc210ff225720db34cf789", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "unsloth\/mistral-7b-v0.2", + "Average \u2b06\ufe0f": 60.34, + "ARC": 60.49, + "HellaSwag": 82.94, + "MMLU": 63.42, + "TruthfulQA": 41.8, + "Winogrande": 78.69, + "GSM8K": 34.72, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "8b2d7b48e924f9ae1ec3882ce01a7a3e78fa430e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe9", + "Model": "Weyaxi\/Mistral-7B-v0.2-hf-duplicate", + "Average \u2b06\ufe0f": 60.34, + "ARC": 60.49, + "HellaSwag": 82.94, + "MMLU": 63.42, + "TruthfulQA": 41.8, + "Winogrande": 78.69, + "GSM8K": 34.72, + "Type": "continuously pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "835d752a28c1d458d9fcc8f98beb878c4f35a06f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "InnerI\/InnerI-AI-sn6-7B-slerp", + "Average \u2b06\ufe0f": 60.32, + "ARC": 58.36, + "HellaSwag": 77.58, + "MMLU": 58.82, + "TruthfulQA": 54.7, + "Winogrande": 72.93, + "GSM8K": 39.5, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0823e2608713b502626b28a267cf81b7a7cd7d5e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BlouseJury\/Mistral-7B-Discord-0.1", @@ -42294,12 +59268,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 1051.0, + "Hub \u2764\ufe0f": 1078.0, "Available on the hub": true, "Model sha": "5b874a33a91d63023055e6cb2d5d86afe883b4ec", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistralai-case-0-1", + "Average \u2b06\ufe0f": 60.26, + "ARC": 60.84, + "HellaSwag": 83.05, + "MMLU": 62.72, + "TruthfulQA": 41.43, + "Winogrande": 78.85, + "GSM8K": 34.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a0386ced06a6282843b950fb549a28dd96b9fd20", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "PulsarAI\/SlimOpenOrca-Mistral-7B-v2", @@ -42318,7 +59315,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7cd030ccdb169c2685fe028bb4380b91ad74920f", "Flagged": false, "MoE": false @@ -42341,7 +59338,7 @@ "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9aae2b156b24557bb98e515f3a90c7865529d2e9", "Flagged": false, "MoE": false @@ -42363,7 +59360,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": false, "Model sha": "d805640fae5928607626d5c89b66a9aaf98da752", "Flagged": false, @@ -42392,6 +59389,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "pansophic\/m16", + "Average \u2b06\ufe0f": 60.25, + "ARC": 59.81, + "HellaSwag": 74.82, + "MMLU": 56.31, + "TruthfulQA": 47.11, + "Winogrande": 75.14, + "GSM8K": 48.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "61b76c29f02a6b27f17b3e73ce50c218dfc6b7ff", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "vihangd\/smartyplats-7b-v2", @@ -42415,6 +59435,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "pansophic\/m3", + "Average \u2b06\ufe0f": 60.23, + "ARC": 60.41, + "HellaSwag": 74.49, + "MMLU": 56.51, + "TruthfulQA": 44.98, + "Winogrande": 76.72, + "GSM8K": 48.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c55ddfa2a2e72141f5cf6ddefb5596d79efcfd72", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "lilloukas\/GPlatty-30B", @@ -42433,11 +59476,34 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "836cf4dcd60ebe2ff09415c72f809d94639e8d35", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/form1", + "Average \u2b06\ufe0f": 60.23, + "ARC": 58.79, + "HellaSwag": 75.25, + "MMLU": 56.83, + "TruthfulQA": 45.85, + "Winogrande": 74.9, + "GSM8K": 49.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7dceb14eec7636fd7da57fad984333f4e7c07c60", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "argilla\/notus-7b-v1", @@ -42455,7 +59521,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 106.0, + "Hub \u2764\ufe0f": 108.0, "Available on the hub": true, "Model sha": "89f594b32aea9bf5de0abe3877f20ff302549934", "Flagged": false, @@ -42501,7 +59567,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 609.0, + "Hub \u2764\ufe0f": 632.0, "Available on the hub": true, "Model sha": "7233ac83317946d05c474b71cc1379f49eb74c14", "Flagged": false, @@ -42524,12 +59590,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": false, "Model sha": "bf951ef22381c0dbeb69959fb3c06e772adc2426", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/merlin1.4", + "Average \u2b06\ufe0f": 60.15, + "ARC": 59.3, + "HellaSwag": 74.5, + "MMLU": 56.34, + "TruthfulQA": 47.36, + "Winogrande": 74.98, + "GSM8K": 48.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "59f8d7e6aefd0305e7f54a9a405e0ff5f7c6bb0e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-65b-gpt4-1.3", @@ -42553,6 +59642,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Eric111\/Yarn-Mistral-7b-128k-DPO", + "Average \u2b06\ufe0f": 60.15, + "ARC": 60.84, + "HellaSwag": 82.99, + "MMLU": 63.09, + "TruthfulQA": 43.55, + "Winogrande": 78.3, + "GSM8K": 32.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ad6b6614b4647e4c0cd5cc9aa38d71c944697a5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "YeungNLP\/firefly-zephyr-6x7b-lora", @@ -42571,7 +59683,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ebf239f263dc1bfb7cf2030c96f0e967683e5946", "Flagged": false, "MoE": false @@ -42594,7 +59706,7 @@ "Hub License": "?", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "01c9ec549ddc830eaa6639e7e89b6337c51586e3", "Flagged": false, "MoE": false @@ -42660,9 +59772,9 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "64a1984f1cba96880047c8f93a83fde9f5b1df35", "Flagged": false, @@ -42737,6 +59849,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistralai-case-1-1", + "Average \u2b06\ufe0f": 60.06, + "ARC": 60.92, + "HellaSwag": 82.87, + "MMLU": 62.87, + "TruthfulQA": 41.1, + "Winogrande": 78.37, + "GSM8K": 34.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e7b1b13c3618dc97d3562984447af3772d3c76a0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Aspik101\/llama-30b-2048-instruct-PL-lora_unload", @@ -42783,6 +59918,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/groot2", + "Average \u2b06\ufe0f": 60.02, + "ARC": 59.04, + "HellaSwag": 73.88, + "MMLU": 56.38, + "TruthfulQA": 47.41, + "Winogrande": 75.93, + "GSM8K": 47.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b357f5929c8d1919525ed021de639f3059b14d93", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Delcos\/Velara", @@ -42824,7 +59982,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3eca9fdee0ce28d6a4a635a6f19d9a413caee3e7", "Flagged": false, "MoE": false @@ -42852,6 +60010,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "feeltheAGI\/mistral-maths7B", + "Average \u2b06\ufe0f": 59.99, + "ARC": 52.05, + "HellaSwag": 74.77, + "MMLU": 54.54, + "TruthfulQA": 57.3, + "Winogrande": 72.45, + "GSM8K": 48.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "3b0be352fd19f65f76221336594902b4b00b642c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "codellama\/CodeLlama-70b-Instruct-hf", @@ -42869,7 +60050,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 178.0, + "Hub \u2764\ufe0f": 189.0, "Available on the hub": true, "Model sha": "6b762a8d3c16e4397aaa4f4627ebfda5db098831", "Flagged": false, @@ -42892,12 +60073,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "298d2086a949d53af06096d229f64f4719261698", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "0-hero\/Matter-0.1-Slim-7B-A", + "Average \u2b06\ufe0f": 59.96, + "ARC": 60.49, + "HellaSwag": 81.33, + "MMLU": 60.68, + "TruthfulQA": 41.79, + "Winogrande": 77.35, + "GSM8K": 38.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9259ec16319e314d0e189159302f0033cb01e964", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NovoCode\/Novocode7b", @@ -42913,7 +60117,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -42921,6 +60125,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/zephyr-7b-beta-gpt-4-80k", + "Average \u2b06\ufe0f": 59.95, + "ARC": 60.84, + "HellaSwag": 79.08, + "MMLU": 60.67, + "TruthfulQA": 58.4, + "Winogrande": 74.03, + "GSM8K": 26.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4ca0d52d950a5af64434243038f318b3c359f1f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Xenon1\/Zenith-7B-dpo-v1", @@ -42961,7 +60188,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "b491a2e09079cfd8d388a5a65e2c44910b10aad4", "Flagged": false, @@ -42990,6 +60217,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/Blitz-v0.2", + "Average \u2b06\ufe0f": 59.93, + "ARC": 59.04, + "HellaSwag": 83.0, + "MMLU": 62.96, + "TruthfulQA": 42.71, + "Winogrande": 78.3, + "GSM8K": 33.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce6df89ef2377c14f2fb5d9b7810b2f65b7fc997", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Xenon1\/Xenon-2", @@ -43053,7 +60303,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "db8cffdb7d63b88239c3b27b5afe1b433400e72f", "Flagged": false, @@ -43076,7 +60326,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 523.0, + "Hub \u2764\ufe0f": 531.0, "Available on the hub": true, "Model sha": "3995e9a13d54ce95f0ad55de2eaa92e2dc580174", "Flagged": false, @@ -43099,7 +60349,7 @@ "Merged": false, "Hub License": "cc", "#Params (B)": 6.06, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "7a441a69e1ebd192fbf52b904589130c3875aacc", "Flagged": false, @@ -43123,7 +60373,7 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5574a021f55a446a756dcbc776f1765aefc280a1", "Flagged": false, "MoE": false @@ -43191,7 +60441,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 70.0, - "Hub \u2764\ufe0f": 111.0, + "Hub \u2764\ufe0f": 115.0, "Available on the hub": true, "Model sha": "97e5913edd2c593c3eef12070024674e7ee4e16c", "Flagged": false, @@ -43238,11 +60488,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "ffcebbaaabb14ac25326c6385327f73785ec4a95", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "theNovaAI\/Supernova-experimental", + "Average \u2b06\ufe0f": 59.79, + "ARC": 63.05, + "HellaSwag": 83.66, + "MMLU": 56.59, + "TruthfulQA": 49.37, + "Winogrande": 77.35, + "GSM8K": 28.73, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e0b2524a7ac1e08c8c04e50d4461b89699d3603c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "kimwooglae\/AISquare-Instruct-SOLAR-10.7b-v0.5.32", @@ -43283,7 +60556,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "c985a04e76fb00d3c3f65214d0b02c5a751d2274", "Flagged": false, @@ -43399,7 +60672,7 @@ "Hub License": "?", "#Params (B)": 72.82, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "054fbf6f65e7ab7691ec07ec9ad366acf2dd90bf", "Flagged": false, "MoE": false @@ -43450,6 +60723,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistral-7B-alpaca-case-2-2", + "Average \u2b06\ufe0f": 59.73, + "ARC": 63.48, + "HellaSwag": 83.27, + "MMLU": 62.11, + "TruthfulQA": 45.17, + "Winogrande": 77.51, + "GSM8K": 26.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3ba1eb007fbab1e7b7ff8b48159f7a847c3bb400", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-thoughts-mistral-7b", @@ -43560,7 +60856,7 @@ "Hub License": "other", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "7fc4622f783428dcbfba81a7aa8344c84b74a7b3", "Flagged": false, "MoE": false @@ -43629,7 +60925,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6f32722f7d24501036698cbca9c7a3e2336f071f", "Flagged": false, "MoE": false @@ -43651,7 +60947,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 42.0, + "Hub \u2764\ufe0f": 45.0, "Available on the hub": true, "Model sha": "0273c624561fcecc8e8f4030492a9307aa60f945", "Flagged": false, @@ -43680,6 +60976,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "G-reen\/EXPERIMENT-DPO-m7b2-2-merged", + "Average \u2b06\ufe0f": 59.63, + "ARC": 59.47, + "HellaSwag": 82.47, + "MMLU": 62.31, + "TruthfulQA": 40.11, + "Winogrande": 78.3, + "GSM8K": 35.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "df1a7ecdbb41ee220410f243043346af2e8a491a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "sequelbox\/DiamondForce", @@ -43726,6 +61045,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Kunocchini-1.2-7b-longtext", + "Average \u2b06\ufe0f": 59.57, + "ARC": 59.9, + "HellaSwag": 82.51, + "MMLU": 63.05, + "TruthfulQA": 41.72, + "Winogrande": 77.35, + "GSM8K": 32.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c1c34be434bd1819202cc88b2a4eea7d898ebdae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistralai-case-2-1", + "Average \u2b06\ufe0f": 59.57, + "ARC": 60.92, + "HellaSwag": 82.54, + "MMLU": 62.54, + "TruthfulQA": 41.49, + "Winogrande": 78.3, + "GSM8K": 31.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8c1a2a752a63904e81061a7e65920d92fba01929", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "nisten\/BigCodeLlama-92b", @@ -43766,7 +61131,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "76057cc5c1923921162133c81ae7ca0e92755810", "Flagged": false, @@ -43835,7 +61200,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 71.0, + "Hub \u2764\ufe0f": 72.0, "Available on the hub": true, "Model sha": "b8825fe3394608fe84f0f5eb6471454384fb83aa", "Flagged": false, @@ -43907,8 +61272,8 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "56b640240f1aca4a91ccf66de041c86102dfe2c9", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -43953,8 +61318,8 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "56b640240f1aca4a91ccf66de041c86102dfe2c9", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udd36", @@ -43974,11 +61339,57 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1dfa5e16d4be646b496d657d86554482ad48b3c9", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "G-reen\/EXPERIMENT-DPO-m7b2-1-merged", + "Average \u2b06\ufe0f": 59.52, + "ARC": 59.47, + "HellaSwag": 82.42, + "MMLU": 62.21, + "TruthfulQA": 40.01, + "Winogrande": 78.3, + "GSM8K": 34.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f6b3b809c43964a07393735a9216aa65563fb1e1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "zhengchenphd\/Mistral-Plus-7B", + "Average \u2b06\ufe0f": 59.52, + "ARC": 62.2, + "HellaSwag": 84.24, + "MMLU": 63.63, + "TruthfulQA": 35.8, + "Winogrande": 77.74, + "GSM8K": 33.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d7d4ca78648dd7c8833c7029946956619d2d714d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/WizardLM-30B-fp16", @@ -44042,7 +61453,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1047.0, + "Hub \u2764\ufe0f": 1062.0, "Available on the hub": true, "Model sha": "2cd2cd16a6ab22585d643cf264fac73b18e7852a", "Flagged": false, @@ -44094,6 +61505,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Evillain\/StarDust_20B_v0.2", + "Average \u2b06\ufe0f": 59.46, + "ARC": 61.01, + "HellaSwag": 83.76, + "MMLU": 59.29, + "TruthfulQA": 51.43, + "Winogrande": 77.27, + "GSM8K": 24.03, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af50ba3e261a87df9817cd9fcfb9911e03e14c07", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "FelixChao\/Gemma-10.2B", + "Average \u2b06\ufe0f": 59.45, + "ARC": 58.36, + "HellaSwag": 80.35, + "MMLU": 58.44, + "TruthfulQA": 39.46, + "Winogrande": 76.87, + "GSM8K": 43.21, + "Type": "base merges and moerges", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.2, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "28236d28ce6b57ec4217c561ab5b196ccdac7aeb", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "LLMs\/WizardLM-30B-V1.0", @@ -44134,7 +61591,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 532.0, + "Hub \u2764\ufe0f": 554.0, "Available on the hub": true, "Model sha": "d09f1f8ed437d61c1aff94c1beabee554843dcdd", "Flagged": false, @@ -44209,6 +61666,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "FredrikBL\/test-ties", + "Average \u2b06\ufe0f": 59.38, + "ARC": 58.53, + "HellaSwag": 81.66, + "MMLU": 61.7, + "TruthfulQA": 41.14, + "Winogrande": 76.87, + "GSM8K": 36.39, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "99c5b76e67ee862e05e733933ccb5cb382380a94", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "deepseek-ai\/deepseek-llm-7b-chat", @@ -44226,7 +61706,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 58.0, + "Hub \u2764\ufe0f": 61.0, "Available on the hub": true, "Model sha": "afbda8b347ec881666061fa67447046fc5164ec8", "Flagged": false, @@ -44249,12 +61729,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "35cf427cc9af94533baeea8afa1428a0eff78f3f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/mistral-7b-grok", + "Average \u2b06\ufe0f": 59.37, + "ARC": 58.7, + "HellaSwag": 81.88, + "MMLU": 61.55, + "TruthfulQA": 42.07, + "Winogrande": 77.66, + "GSM8K": 34.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 38.0, + "Available on the hub": true, + "Model sha": "038a70da219335747827bc58464bc95dbdbdd623", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/motans1", + "Average \u2b06\ufe0f": 59.37, + "ARC": 58.62, + "HellaSwag": 73.42, + "MMLU": 56.94, + "TruthfulQA": 46.1, + "Winogrande": 74.11, + "GSM8K": 47.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8e66c7f8c142a1eb4786469a68a414cdb2d2b26a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "uukuguy\/speechless-thoughts-mistral-7b-v1.0", @@ -44341,7 +61867,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 71.0, + "Hub \u2764\ufe0f": 74.0, "Available on the hub": true, "Model sha": "08634a81f7bc7343f94d1c82fae461ad9b03e233", "Flagged": false, @@ -44364,7 +61890,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 137.0, + "Hub \u2764\ufe0f": 140.0, "Available on the hub": true, "Model sha": "8e6d0b18be876e0ebfff47d6c4f33d776f189971", "Flagged": false, @@ -44462,6 +61988,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Joseph717171\/Cerebrum-1.0-10.7B", + "Average \u2b06\ufe0f": 59.3, + "ARC": 60.92, + "HellaSwag": 82.92, + "MMLU": 63.84, + "TruthfulQA": 46.2, + "Winogrande": 77.66, + "GSM8K": 24.26, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bbaf12db44e8def28f52c9d536cf95c50e1de081", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ariellee\/SuperPlatty-30B", @@ -44480,7 +62029,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "017e1c32bca060107337dbf26db2044a7caa56f2", "Flagged": false, "MoE": false @@ -44502,7 +62051,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 26.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "ce1fb6a278121df73eee5d7d39dc0d30b214a1b5", "Flagged": false, @@ -44525,7 +62074,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 58.0, + "Hub \u2764\ufe0f": 61.0, "Available on the hub": true, "Model sha": "afbda8b347ec881666061fa67447046fc5164ec8", "Flagged": false, @@ -44591,7 +62140,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, @@ -44669,6 +62218,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wannaphong\/han-llm-7b-v3", + "Average \u2b06\ufe0f": 59.25, + "ARC": 58.7, + "HellaSwag": 81.79, + "MMLU": 59.59, + "TruthfulQA": 43.12, + "Winogrande": 77.11, + "GSM8K": 35.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.27, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4cdb6b256a117955a52bd017f9e2d3bfef859da8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "sethuiyer\/Dr_Samantha_7b_mistral", @@ -44686,12 +62258,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "e0201aa9423f082a4182cbf910d75ba438528ddb", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Corianas\/NearalMistral-2x7B", + "Average \u2b06\ufe0f": 59.24, + "ARC": 57.42, + "HellaSwag": 77.67, + "MMLU": 56.46, + "TruthfulQA": 57.03, + "Winogrande": 75.22, + "GSM8K": 31.61, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d290558a090dfaeeca02e48e04ad0bf9ecdc39c8", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "gaodrew\/gaodrew-llama-30b-instruct-2048-Open-Platypus-100steps", @@ -44755,7 +62350,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.72, - "Hub \u2764\ufe0f": 330.0, + "Hub \u2764\ufe0f": 337.0, "Available on the hub": true, "Model sha": "c9bdb955021a80ae26fa6978891996dbe4951d8d", "Flagged": false, @@ -44778,7 +62373,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "969fbfc7a91f53c8562a2c48a3c24dd3745d5a97", "Flagged": false, @@ -44801,7 +62396,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.7, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "9d6e34fa51cd3c4745a044fbb2bca91b1c9a9f5a", "Flagged": false, @@ -44847,7 +62442,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 36.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": true, "Model sha": "b6e20287ba4156f06b4288d4003acc677040527f", "Flagged": false, @@ -44894,7 +62489,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9609a969ba6429b84e538d96afac55eb133a9983", "Flagged": false, "MoE": false @@ -44939,7 +62534,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "47a417a2167064112038e71f2be30d7293eb485d", "Flagged": false, @@ -44985,7 +62580,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1312.0, + "Hub \u2764\ufe0f": 1396.0, "Available on the hub": true, "Model sha": "8af01af3d4f9dc9b962447180d6d0f8c5315da86", "Flagged": false, @@ -45014,6 +62609,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "wannaphong\/han-llm-7b-v2", + "Average \u2b06\ufe0f": 59.06, + "ARC": 58.79, + "HellaSwag": 81.75, + "MMLU": 59.93, + "TruthfulQA": 42.38, + "Winogrande": 77.98, + "GSM8K": 33.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.27, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e192c06c348f148afe82df13baf56c253eede0e6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NurtureAI\/openchat_3.5-16k", @@ -45031,7 +62649,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 30.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "e8d66e7fb2ebb918f468137ea5fa3dc13ddc69da", "Flagged": false, @@ -45060,6 +62678,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ValiantLabs\/Esper-70b", + "Average \u2b06\ufe0f": 59.03, + "ARC": 56.48, + "HellaSwag": 77.72, + "MMLU": 55.91, + "TruthfulQA": 45.98, + "Winogrande": 73.48, + "GSM8K": 44.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "13c5bb97ed6c5faaaa2e2a57fbb60aaff61a0f4c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "lilloukas\/Platypus-30B", @@ -45078,7 +62719,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "979ad39b58a8e4a9419b7bc7a0dc8419f3912e71", "Flagged": false, "MoE": false @@ -45129,6 +62770,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "ShenaoZ\/0001_dpo_iter_2", + "Average \u2b06\ufe0f": 59.01, + "ARC": 60.41, + "HellaSwag": 84.52, + "MMLU": 60.02, + "TruthfulQA": 53.11, + "Winogrande": 77.19, + "GSM8K": 18.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d9b4ce3898d7e95949fea0ebb846cc255e19df12", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "unaidedelf87777\/wizard-mistral-v0.1", @@ -45152,6 +62816,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Joseph717171\/Mistral-12.25B-v0.2", + "Average \u2b06\ufe0f": 59.01, + "ARC": 58.87, + "HellaSwag": 81.77, + "MMLU": 63.22, + "TruthfulQA": 40.44, + "Winogrande": 77.66, + "GSM8K": 32.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e9bfa6be73552731485ea1a3098888cc2bee5b28", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "alignment-handbook\/zephyr-7b-sft-qlora", @@ -45169,12 +62856,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, "Model sha": "156bec577ff12a65236cfc90860dcc61e96c6fd6", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/test-case-6", + "Average \u2b06\ufe0f": 58.99, + "ARC": 57.34, + "HellaSwag": 78.86, + "MMLU": 58.21, + "TruthfulQA": 49.44, + "Winogrande": 76.87, + "GSM8K": 33.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "49d1b9c1430ebd5ca0562b0c7d5893c5277eb0f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ramachaitanya22\/mistral-7B-finetune-health-fitness", + "Average \u2b06\ufe0f": 58.98, + "ARC": 59.13, + "HellaSwag": 82.65, + "MMLU": 61.93, + "TruthfulQA": 42.07, + "Winogrande": 77.03, + "GSM8K": 31.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0453c4ebdbf0462a0ed55c9a026ca194323e5a11", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "ehartford\/samantha-1.1-llama-33b", @@ -45193,7 +62926,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ad8892a17be1372f611203a4cf71560cc337e458", "Flagged": false, "MoE": false @@ -45308,7 +63041,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a581ab1793366ff2d5f3c966ff0e7b8b1149d775", "Flagged": false, "MoE": false @@ -45330,7 +63063,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "47a417a2167064112038e71f2be30d7293eb485d", "Flagged": false, @@ -45353,7 +63086,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 273.0, + "Hub \u2764\ufe0f": 290.0, "Available on the hub": true, "Model sha": "4570a4edc524fb9f20f605b417bb43828fa5997a", "Flagged": false, @@ -45399,7 +63132,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "aa2c84e89c4c8a10e0569e45021b59e6d1c08bda", "Flagged": false, @@ -45451,6 +63184,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ArtMindia\/artmindia3k", + "Average \u2b06\ufe0f": 58.91, + "ARC": 59.98, + "HellaSwag": 82.99, + "MMLU": 60.99, + "TruthfulQA": 41.61, + "Winogrande": 76.8, + "GSM8K": 31.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a9c25b4b3253b15a9be09c3f1c7bfb96df71d984", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mncai\/Mistral-7B-OpenOrca-1k", @@ -45520,6 +63276,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Cinder-Phi-2-V1-F16-gguf", + "Average \u2b06\ufe0f": 58.86, + "ARC": 58.28, + "HellaSwag": 74.04, + "MMLU": 54.46, + "TruthfulQA": 44.5, + "Winogrande": 74.66, + "GSM8K": 47.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "3d0fc5758f6b55757a669f7f05a9b19af452e045", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "openaccess-ai-collective\/manticore-30b-chat-pyg-alpha", @@ -45560,7 +63339,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "753852b8cb52dc5f0411568e98c0cb445a7835dc", "Flagged": false, @@ -45584,7 +63363,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "36dde2c5b08140d612042d1ae047dd7551b7e15b", "Flagged": false, "MoE": false @@ -45635,6 +63414,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/mistral_11B_instruct_v0.1", + "Average \u2b06\ufe0f": 58.84, + "ARC": 53.75, + "HellaSwag": 74.64, + "MMLU": 58.93, + "TruthfulQA": 63.64, + "Winogrande": 73.56, + "GSM8K": 28.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5e4a8289201232e829ea1c0276d76ce1b003cc20", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "PulsarAI\/Nebula-v2-7B", @@ -45653,7 +63455,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d2a5611f7d7c37bfa2270d1823bceef01c0be383", "Flagged": false, "MoE": false @@ -45675,12 +63477,35 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 23.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "305eea72fb9fe2ac5929a62483ea51f152bcc060", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "TeeZee\/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k", + "Average \u2b06\ufe0f": 58.79, + "ARC": 65.27, + "HellaSwag": 85.62, + "MMLU": 65.61, + "TruthfulQA": 53.46, + "Winogrande": 82.72, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 15.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "feec1455869adb242dbafa1d0e22a81972ee9b79", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Dans-DiscountModels\/Mistral-7b-FFT-Test3", @@ -45744,7 +63569,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "1013d7e539e53c15e5285ed27902a713c8caad09", "Flagged": false, @@ -45773,6 +63598,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/OpenHermes-Gemma-7B", + "Average \u2b06\ufe0f": 58.76, + "ARC": 57.0, + "HellaSwag": 76.3, + "MMLU": 55.74, + "TruthfulQA": 53.14, + "Winogrande": 72.69, + "GSM8K": 37.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "289270b57a23e0db3113437094aba0e9c9deb0c1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Henk717\/airochronos-33B", @@ -45813,7 +63661,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 41.0, + "Hub \u2764\ufe0f": 44.0, "Available on the hub": true, "Model sha": "e9a7f0271fa442d65bf6be87feeb3f4de2f5760e", "Flagged": false, @@ -45905,7 +63753,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": false, "Model sha": "a452045c96ae62379a98ef0d85666616a66e78a6", "Flagged": false, @@ -45957,6 +63805,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "yanolja\/EEVE-Korean-Instruct-2.8B-v1.0", + "Average \u2b06\ufe0f": 58.71, + "ARC": 58.28, + "HellaSwag": 72.42, + "MMLU": 53.35, + "TruthfulQA": 48.32, + "Winogrande": 74.82, + "GSM8K": 45.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.82, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "ba710d9bbd03ec302064e6f19141364f7e01eb00", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "bhenrym14\/mistral-7b-platypus-fp16", @@ -45997,7 +63868,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "7b37775efb34a0734efd60a32781bd706c60e85b", "Flagged": false, @@ -46021,7 +63892,7 @@ "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8e1cbfa67643f49be67a6021db933cdd941a6d2f", "Flagged": false, "MoE": false @@ -46089,8 +63960,8 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "dc66cf314292f3bfd5a2eed74018671effac6405", "Flagged": false, "MoE": false @@ -46113,7 +63984,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f4d471d7a9447d0969a58d5b3146d50cfa3005b3", "Flagged": false, "MoE": false @@ -46135,7 +64006,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 624.0, + "Hub \u2764\ufe0f": 642.0, "Available on the hub": true, "Model sha": "2539ff53e6baa4cc603774ad5a2d646f4041ea4e", "Flagged": false, @@ -46159,7 +64030,7 @@ "Hub License": "?", "#Params (B)": 40.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3d5084b6fbcb9f9f36493d9fd1e3795b0b9860f0", "Flagged": false, "MoE": false @@ -46205,7 +64076,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "b688325e94904c69ab3815543d5ec51e1e869e8b", "Flagged": false, "MoE": false @@ -46273,7 +64144,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "47472b36e181694422564b130ee075ffa596537d", "Flagged": false, @@ -46299,7 +64170,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "55d31300f8972b56320855bb40efb5e3d1e1a6fc", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -46343,7 +64214,7 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c673387016c622fd0a707426953c03957398bc37", "Flagged": false, "MoE": false @@ -46388,7 +64259,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "7b37775efb34a0734efd60a32781bd706c60e85b", "Flagged": false, @@ -46409,9 +64280,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "1d670244f2f70ab35219c9bbf83eef4f5dc28730", "Flagged": false, @@ -46434,7 +64305,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 273.0, + "Hub \u2764\ufe0f": 278.0, "Available on the hub": false, "Model sha": "ef8d6becf883fb3ce52e3706885f761819477ab4", "Flagged": false, @@ -46457,8 +64328,8 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 72.0, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "dc66cf314292f3bfd5a2eed74018671effac6405", "Flagged": false, "MoE": false @@ -46481,7 +64352,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "14e0756c210bcf420fbf825e6b8087ee5c716e7f", "Flagged": false, "MoE": false @@ -46503,7 +64374,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "dad2d749b01cf10b65951dea6e130da8cc53e2c0", "Flagged": false, @@ -46526,7 +64397,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "cda06630a1d8173541431e5ce8bc17dcfaa37e5e", "Flagged": false, @@ -46572,7 +64443,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 35.58, - "Hub \u2764\ufe0f": 520.0, + "Hub \u2764\ufe0f": 534.0, "Available on the hub": true, "Model sha": "56a82ece7a9309189561a590e8f4d2fe0d4be92b", "Flagged": false, @@ -46595,7 +64466,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 62.0, + "Hub \u2764\ufe0f": 63.0, "Available on the hub": true, "Model sha": "7a05c8a2151f7d32252d9ef5db10445c13ae1f20", "Flagged": false, @@ -46664,12 +64535,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "8d302741466512f0621a594fce6bf5b8125c8d4c", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "ZySec-AI\/ZySec-7B", + "Average \u2b06\ufe0f": 58.41, + "ARC": 57.51, + "HellaSwag": 79.73, + "MMLU": 58.65, + "TruthfulQA": 51.11, + "Winogrande": 74.51, + "GSM8K": 28.96, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "4736490de5d4dc374d8c7ee47fd9a1c587f539e7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CalderaAI\/30B-Lazarus", @@ -46754,7 +64648,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -46802,7 +64696,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "1c1f4e9256ac2be145a9106863ee9f2e9d701e74", "Flagged": false, @@ -46823,9 +64717,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 2.78, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "ee382f2c6f1006d6854a1b3cc26cbaa28eeab2cb", "Flagged": false, @@ -46877,6 +64771,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/test-case-3", + "Average \u2b06\ufe0f": 58.34, + "ARC": 57.76, + "HellaSwag": 79.56, + "MMLU": 56.77, + "TruthfulQA": 49.22, + "Winogrande": 75.93, + "GSM8K": 30.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ec6e8c7d2a2f05c7459a5490e18dc99da01e73a1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/SynthIA-v1.3-Nebula-v2-7B", @@ -46900,6 +64817,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "g-ronimo\/phi-2-OpenHermes-2.5-v2", + "Average \u2b06\ufe0f": 58.33, + "ARC": 58.45, + "HellaSwag": 74.57, + "MMLU": 56.43, + "TruthfulQA": 44.89, + "Winogrande": 75.22, + "GSM8K": 40.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "246f56314bb9aada8d50267bc0764c07bdcd8b86", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "kwchoi\/DPO_mistral_v01_7b_ultra_0131_1k_1epoch", @@ -47012,7 +64952,7 @@ "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "e2329c05a6e59660ba3cbcc01adf30a78f852594", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -47033,7 +64973,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2609363766acf308877a71aba352e60d7c044b49", "Flagged": false, "MoE": false @@ -47055,7 +64995,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 42.0, + "Hub \u2764\ufe0f": 46.0, "Available on the hub": true, "Model sha": "8ae3d155e57352d4b7fef1d60f74e8c8650a8ab7", "Flagged": false, @@ -47171,7 +65111,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "67107327d09c2f9bf3e4b316d97767c97f5a0804", "Flagged": false, "MoE": false @@ -47217,7 +65157,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5529ddb255dbdabdd179bdc911f141c3f0d2fb3f", "Flagged": false, "MoE": false @@ -47316,7 +65256,7 @@ }, { "T": "\ud83d\udd36", - "Model": "caisarl76\/mistral-guanaco1k-ep2", + "Model": "caisarl76\/Mistral-7B-guanaco1k-ep2", "Average \u2b06\ufe0f": 58.13, "ARC": 60.07, "HellaSwag": 82.76, @@ -47332,14 +65272,14 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9c9f31f213b69da7797c2c0630c17cf8f785fc13", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "caisarl76\/Mistral-7B-guanaco1k-ep2", + "Model": "caisarl76\/mistral-guanaco1k-ep2", "Average \u2b06\ufe0f": 58.13, "ARC": 60.07, "HellaSwag": 82.76, @@ -47355,11 +65295,34 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9c9f31f213b69da7797c2c0630c17cf8f785fc13", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wannaphong\/han-llm-7b-v1", + "Average \u2b06\ufe0f": 58.13, + "ARC": 58.19, + "HellaSwag": 81.58, + "MMLU": 58.99, + "TruthfulQA": 40.97, + "Winogrande": 77.27, + "GSM8K": 31.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.27, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f09bd92495b986d7b79b3e6ac373a7eddcb715d5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Stheno-1.8-L2-13B", @@ -47401,7 +65364,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1aca45d37eade21eb381aaefc9245b58ec3b7b26", "Flagged": false, "MoE": false @@ -47492,7 +65455,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 40.0, - "Hub \u2764\ufe0f": 2381.0, + "Hub \u2764\ufe0f": 2395.0, "Available on the hub": true, "Model sha": "3d7c5902f1dc9da830979a826cd96114b3ba4ec1", "Flagged": false, @@ -47584,7 +65547,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 62.0, + "Hub \u2764\ufe0f": 72.0, "Available on the hub": true, "Model sha": "35fb2f9cee5dbac35109effc816ca206962dad43", "Flagged": false, @@ -47607,7 +65570,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.73, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "e9698271ea1ab340bacfd5ebf0d77108a6f18a90", "Flagged": false, @@ -47676,7 +65639,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 68.98, - "Hub \u2764\ufe0f": 90.0, + "Hub \u2764\ufe0f": 101.0, "Available on the hub": true, "Model sha": "79467981bab591dd6860707ed517d1186fbcfc1e", "Flagged": false, @@ -47700,11 +65663,34 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bf152c36935acd67a9029c017f0c1ff2d7a92314", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Joseph717171\/Mistral-10.7B-v0.2", + "Average \u2b06\ufe0f": 57.96, + "ARC": 58.28, + "HellaSwag": 80.92, + "MMLU": 63.44, + "TruthfulQA": 40.39, + "Winogrande": 77.35, + "GSM8K": 27.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5e9d95dc097aa3d5e5ee63d696d1697590344747", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "ehartford\/samantha-mistral-7b", @@ -47723,11 +65709,34 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7f9e40543fdff8c3e58eca0390c8a631829c1206", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-SOLAR-11b-v4.0", + "Average \u2b06\ufe0f": 57.95, + "ARC": 63.65, + "HellaSwag": 84.75, + "MMLU": 65.13, + "TruthfulQA": 51.63, + "Winogrande": 82.56, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f1a90b4594dfe14349be1db44ee887856f73a82c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "martyn\/llama2-megamerge-dare-13b-v2", @@ -47815,7 +65824,7 @@ "Hub License": "?", "#Params (B)": 38.5, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "220833f87c233684e8a4b0e03126ffcdffce5229", "Flagged": false, "MoE": true @@ -47835,7 +65844,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -47975,8 +65984,8 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 2.94, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, "Model sha": "ba849c8beeea4d6bffa6db6a590451d911df89ab", "Flagged": false, "MoE": false @@ -47999,7 +66008,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6374baef4cedd41f85c111b8eec3eb38ee24c4b9", "Flagged": false, "MoE": false @@ -48137,7 +66146,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "942af4d59533af09cf9ba13d1e369b8e871a0a4b", "Flagged": false, "MoE": false @@ -48160,7 +66169,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "624be22cfde6797a100230ec9dc1421f52eb0aa2", "Flagged": false, "MoE": false @@ -48188,6 +66197,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral-7b-selfplay-v0", + "Average \u2b06\ufe0f": 57.82, + "ARC": 54.69, + "HellaSwag": 75.69, + "MMLU": 55.4, + "TruthfulQA": 56.28, + "Winogrande": 73.64, + "GSM8K": 31.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f953e2d8749d9dec967dd05d6e649c7c25a9fb23", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "s3nh\/Noromaid-Aeryth-7B", @@ -48229,7 +66261,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3979769be8d92aa2dd0c7aebf385635863f16dd9", "Flagged": false, "MoE": false @@ -48254,7 +66286,7 @@ "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "3979769be8d92aa2dd0c7aebf385635863f16dd9", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -48390,7 +66422,7 @@ "Hub License": "?", "#Params (B)": 14.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e878e1f1f7b533c32beb8e06ebcf0cfa23f3fe9b", "Flagged": false, "MoE": false @@ -48413,11 +66445,34 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "01b0f2046083dd8d9d8f9e626d78d83eaa1d57dd", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Kabster\/Bio-Mistralv2-Squared", + "Average \u2b06\ufe0f": 57.73, + "ARC": 63.31, + "HellaSwag": 84.02, + "MMLU": 60.08, + "TruthfulQA": 60.98, + "Winogrande": 77.9, + "GSM8K": 0.08, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "77aa25e74e78c21e5ede5411d38e819d70d5ba9d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-33b-gpt4-1.2", @@ -48482,7 +66537,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7c05d338e0210072e13eb82b023e7747d5354c6e", "Flagged": false, "MoE": false @@ -48505,11 +66560,57 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "faac4b13e74395ea4b366156fd8bed15498c667c", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Kabster\/Bio-Mistralv2-Squared", + "Average \u2b06\ufe0f": 57.66, + "ARC": 62.97, + "HellaSwag": 84.02, + "MMLU": 60.08, + "TruthfulQA": 60.99, + "Winogrande": 77.74, + "GSM8K": 0.15, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "77aa25e74e78c21e5ede5411d38e819d70d5ba9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Llama-2-13b-chat-hf-activity-fine-tuned-v4", + "Average \u2b06\ufe0f": 57.64, + "ARC": 59.22, + "HellaSwag": 81.67, + "MMLU": 54.51, + "TruthfulQA": 43.82, + "Winogrande": 75.06, + "GSM8K": 31.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3536f3ba1dd84a732958ea563f2a70ecdbb03bcd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "boomerchan\/magpie-13b", @@ -48528,7 +66629,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a58124cdc9f39ccd59d4290a8bdfda93ff3690dc", "Flagged": false, "MoE": false @@ -48551,7 +66652,7 @@ "Hub License": "mit", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "bdc360638c254864af30b5c0e6ff9a7b19e51b46", "Flagged": false, "MoE": false @@ -48574,11 +66675,34 @@ "Hub License": "mit", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "a07fc6ae0f9729767e2cedb229a515e7d84bd87f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "deepseek-ai\/deepseek-math-7b-base", + "Average \u2b06\ufe0f": 57.61, + "ARC": 52.22, + "HellaSwag": 69.49, + "MMLU": 57.25, + "TruthfulQA": 40.71, + "Winogrande": 66.77, + "GSM8K": 59.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "036a8c6189aac6e2fc4e07b46e1e57c6b647bca5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "l3utterfly\/mistral-7b-v0.1-layla-v2", @@ -48625,6 +66749,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "ab24g21\/LaterLlamaV2", + "Average \u2b06\ufe0f": 57.6, + "ARC": 59.04, + "HellaSwag": 81.82, + "MMLU": 54.53, + "TruthfulQA": 44.15, + "Winogrande": 76.09, + "GSM8K": 29.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "66f0995de46d9407f1aa6baa185c6d03e7542ca1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "steve-cse\/MelloGPT", @@ -48711,7 +66858,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "92f9fac4529acacb2c33a35c46917393690c6311", "Flagged": false, @@ -48735,7 +66882,7 @@ "Hub License": "mit", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "2995cd6e9b2780b8a14043fbc4241a81ba6d1feb", "Flagged": false, "MoE": false @@ -48757,12 +66904,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 27.0, + "Hub \u2764\ufe0f": 28.0, "Available on the hub": true, "Model sha": "78188101b6331d9e61ef80f0971d715de100b44a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ab24g21\/llama-2-new", + "Average \u2b06\ufe0f": 57.54, + "ARC": 58.7, + "HellaSwag": 81.54, + "MMLU": 54.59, + "TruthfulQA": 44.58, + "Winogrande": 76.09, + "GSM8K": 29.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "663384b17e7156a858e2f8fdfd7e3ea4bdce105f", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "TheBloke\/tulu-30B-fp16", @@ -48803,7 +66973,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "2711647da9d8da18d746406d60ad8d806b7f1fd7", "Flagged": false, @@ -48849,7 +67019,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "92f9fac4529acacb2c33a35c46917393690c6311", "Flagged": false, @@ -48873,11 +67043,34 @@ "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "9335fee0bbe38195226c63e3f4aa606bbc387e8d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-gemma-7b-v18.1-4k", + "Average \u2b06\ufe0f": 57.49, + "ARC": 54.86, + "HellaSwag": 75.68, + "MMLU": 55.56, + "TruthfulQA": 50.08, + "Winogrande": 68.82, + "GSM8K": 39.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "be808f073ed32bd95263cd08084b096774aef74e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jilp00\/SOLAR-10.7B-tutored", @@ -48896,7 +67089,7 @@ "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "40e46542b4ec136c76f61008a942000ff030cddc", "Flagged": false, "MoE": false @@ -48939,7 +67132,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -48964,7 +67157,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 37.0, "Available on the hub": true, "Model sha": "ee25c078f08b0812d82597afa3f5e877c19a5c83", "Flagged": false, @@ -49016,6 +67209,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/autotrain-xva0j-mixtral8x7b", + "Average \u2b06\ufe0f": 57.45, + "ARC": 62.8, + "HellaSwag": 84.44, + "MMLU": 67.27, + "TruthfulQA": 50.13, + "Winogrande": 74.59, + "GSM8K": 5.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc470b098c475a1604d55e197613e5d0bd85859f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "jondurbin\/airoboros-33b-gpt4-1.3", @@ -49056,7 +67272,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "ac279478abd9ddb8d1f5adcc548be0287b963adf", "Flagged": false, @@ -49085,6 +67301,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalleorg\/TruthfulQwen1.5-4B", + "Average \u2b06\ufe0f": 57.41, + "ARC": 47.1, + "HellaSwag": 71.32, + "MMLU": 56.04, + "TruthfulQA": 50.6, + "Winogrande": 66.85, + "GSM8K": 52.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e6dc5fbf051ae3be06259b28cea254e6a76d632e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "hfl\/chinese-alpaca-2-13b", @@ -49102,7 +67341,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 80.0, + "Hub \u2764\ufe0f": 83.0, "Available on the hub": true, "Model sha": "3b2e3895ff83c8892ab20fb8f98754d947879186", "Flagged": false, @@ -49123,10 +67362,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "", "#Params (B)": 7.11, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": false, "Model sha": "ebf138de4fb7a57f0d187ad0ab43abd6b35bfb62", "Flagged": false, "MoE": false @@ -49200,6 +67439,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "gordicaleksa\/YugoGPT", + "Average \u2b06\ufe0f": 57.35, + "ARC": 58.11, + "HellaSwag": 81.45, + "MMLU": 60.68, + "TruthfulQA": 36.6, + "Winogrande": 76.56, + "GSM8K": 30.71, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "254ee66aebc46b483b1a3b4c2bfafb1d523dc18e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "allenai\/digital-socrates-13b", @@ -49217,7 +67479,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "c738ee4bb61e67eebb9d196c440dcb2d99e5f906", "Flagged": false, @@ -49310,7 +67572,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "39ae03b77b4f1d453b02468ce6bb4ddeb6526b77", "Flagged": false, "MoE": false @@ -49338,6 +67600,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "maldv\/electric-mist-7b", + "Average \u2b06\ufe0f": 57.3, + "ARC": 61.18, + "HellaSwag": 82.56, + "MMLU": 59.71, + "TruthfulQA": 45.37, + "Winogrande": 71.51, + "GSM8K": 23.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b224f450fa0db5e09ce96ee3b4c4bc9c2e614c84", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "codellama\/CodeLlama-34b-Instruct-hf", @@ -49355,7 +67640,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 256.0, + "Hub \u2764\ufe0f": 261.0, "Available on the hub": true, "Model sha": "bf5e5060fa30f33149efe84bbcc682001a00ab94", "Flagged": false, @@ -49378,12 +67663,58 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 223.0, + "Hub \u2764\ufe0f": 226.0, "Available on the hub": true, "Model sha": "e7a40134f7eb687c6ab66d445dc7251257f8d391", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/LLaMA2-13B-Estopia", + "Average \u2b06\ufe0f": 57.27, + "ARC": 62.12, + "HellaSwag": 82.53, + "MMLU": 54.99, + "TruthfulQA": 54.18, + "Winogrande": 75.85, + "GSM8K": 13.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "cfbf7f1372454aefb45d27504b11431828ad14f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "XuanXuanXuanXuan\/Mistral-7B-Instruct-v0.1-gpt-4-80k", + "Average \u2b06\ufe0f": 57.27, + "ARC": 55.12, + "HellaSwag": 74.79, + "MMLU": 56.13, + "TruthfulQA": 57.51, + "Winogrande": 72.61, + "GSM8K": 27.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0b74a57c33242b7441a9b85fbcca5d477c3584bd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "PulsarAI\/2x-LoRA-Assemble-Nova-13B", @@ -49402,7 +67733,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2a344b91b28ce4d0bd48b9b5a6cc87b71123eab5", "Flagged": false, "MoE": false @@ -49493,15 +67824,15 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "bbc483fc0a3b88740fd6e04a7fd0c7d98b85cd1d", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "pankajmathur\/orca_mini_v3_13b", + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v3_13b", "Average \u2b06\ufe0f": 57.24, "ARC": 63.14, "HellaSwag": 82.35, @@ -49509,22 +67840,22 @@ "TruthfulQA": 51.81, "Winogrande": 76.48, "GSM8K": 13.12, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", - "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 31.0, - "Available on the hub": true, - "Model sha": "72eec98f68d240a71d3da8a266917b6e754ae831", + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "99904e4119575f2c1606ca1e31d288f38a9f20b5", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "psmathur\/orca_mini_v3_13b", + "T": "\ud83d\udcac", + "Model": "pankajmathur\/orca_mini_v3_13b", "Average \u2b06\ufe0f": 57.24, "ARC": 63.14, "HellaSwag": 82.35, @@ -49532,16 +67863,16 @@ "TruthfulQA": 51.81, "Winogrande": 76.48, "GSM8K": 13.12, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 12.85, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 31.0, "Available on the hub": true, - "Model sha": "99904e4119575f2c1606ca1e31d288f38a9f20b5", + "Model sha": "72eec98f68d240a71d3da8a266917b6e754ae831", "Flagged": false, "MoE": false }, @@ -49632,7 +67963,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "521da4841efa9eee3716294f08fd3326d271b574", "Flagged": false, "MoE": false @@ -49706,6 +68037,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistral-7B-alpaca-case-0-2", + "Average \u2b06\ufe0f": 57.15, + "ARC": 61.69, + "HellaSwag": 81.74, + "MMLU": 60.0, + "TruthfulQA": 43.56, + "Winogrande": 76.95, + "GSM8K": 18.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d8cdb077e67fe9de8fec3ce47b79dab8e1bacf95", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/BrainDerp3", @@ -49749,7 +68103,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "e63d24870c840d47e82b029e7f405baa10ad9ea4", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -49772,7 +68126,7 @@ "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, "Model sha": "afca2c9488cf8738faec4db6721f6a4c755a5d81", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -49907,7 +68261,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 32.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": true, "Model sha": "e4c23af4f5dd88cb27d245e2bfc3b81db652632c", "Flagged": false, @@ -49934,7 +68288,7 @@ "Available on the hub": false, "Model sha": "b97d945f17c9e41dbe1809210c8f818b1cecca7c", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -49961,7 +68315,7 @@ }, { "T": "\ud83d\udd36", - "Model": "stabilityai\/StableBeluga-13B", + "Model": "circulus\/Llama-2-13b-orca-v1", "Average \u2b06\ufe0f": 57.05, "ARC": 62.03, "HellaSwag": 82.27, @@ -49974,17 +68328,17 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": null, - "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 113.0, - "Available on the hub": false, - "Model sha": "1d6eef4cc2b73f39600a568803ad8183f2da4514", + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "e77ec90f432bdffa210a0e4310d117e5d1c662df", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "circulus\/Llama-2-13b-orca-v1", + "Model": "stabilityai\/StableBeluga-13B", "Average \u2b06\ufe0f": 57.05, "ARC": 62.03, "HellaSwag": 82.27, @@ -49997,11 +68351,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "mit", - "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 5.0, - "Available on the hub": true, - "Model sha": "e77ec90f432bdffa210a0e4310d117e5d1c662df", + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 114.0, + "Available on the hub": false, + "Model sha": "1d6eef4cc2b73f39600a568803ad8183f2da4514", "Flagged": false, "MoE": false }, @@ -50022,12 +68376,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 3.95, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "294dbdee5dacecc52c9cc6ba2dba4084addc7b2c", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "TeeZee\/GALAXY_v03_slimorca_1_epoch_50k", + "Average \u2b06\ufe0f": 57.04, + "ARC": 62.71, + "HellaSwag": 84.58, + "MMLU": 65.17, + "TruthfulQA": 47.3, + "Winogrande": 82.48, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 15.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7936789f085412986be9657da573028d8416397", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-33b-gpt4-m2.0", @@ -50068,7 +68445,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "fc46b30e1cf0fe45280fd9b0a948fd9344b31112", "Flagged": false, @@ -50114,7 +68491,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "a4e1b721add286900c5a6f529c3d7a3e0049b2e0", "Flagged": false, @@ -50138,7 +68515,7 @@ "Hub License": "?", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f8332eddcb7f8ab2b5195486d4b508c4628992f6", "Flagged": false, "MoE": false @@ -50184,7 +68561,7 @@ "Hub License": "?", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0024ee75d8ed5d9373ff42df72c21f3217ba9d2e", "Flagged": false, "MoE": false @@ -50206,7 +68583,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "ddc598f492f5098a8e308f51a82834f98f29a4ce", "Flagged": false, @@ -50322,7 +68699,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0ce62a64ca53cd5feb18f523a96dd3be86e6513d", "Flagged": false, "MoE": false @@ -50390,15 +68767,15 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "8f11b7ed191f06add8c7de1a830505289db0afde", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "Yhyu13\/llama-30B-hf-openassitant", + "T": "\ud83d\udfe2", + "Model": "huggingface\/llama-30b", "Average \u2b06\ufe0f": 56.94, "ARC": 61.26, "HellaSwag": 84.73, @@ -50406,22 +68783,22 @@ "TruthfulQA": 42.27, "Winogrande": 80.03, "GSM8K": 14.86, - "Type": "fine-tuned on domain-specific datasets", + "Type": "pretrained", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "fba493af11a73cf5a2ee7857dd7aecb98c659dc4", + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "13c77caa472bfa79d4f3f0ec82cbdc9dd88e5d22", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udfe2", - "Model": "huggingface\/llama-30b", + "T": "\ud83d\udd36", + "Model": "Yhyu13\/llama-30B-hf-openassitant", "Average \u2b06\ufe0f": 56.94, "ARC": 61.26, "HellaSwag": 84.73, @@ -50429,16 +68806,16 @@ "TruthfulQA": 42.27, "Winogrande": 80.03, "GSM8K": 14.86, - "Type": "pretrained", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", - "#Params (B)": 32.53, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "13c77caa472bfa79d4f3f0ec82cbdc9dd88e5d22", + "Hub License": "apache-2.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fba493af11a73cf5a2ee7857dd7aecb98c659dc4", "Flagged": false, "MoE": false }, @@ -50457,9 +68834,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "other", "#Params (B)": 6.06, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "71474831ebfa33d02692e22f2ed7267d534f9e06", "Flagged": false, @@ -50489,8 +68866,8 @@ "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "rombodawg\/LosslessMegaCoder-llama2-13b-mini", + "T": "\ud83d\udd36", + "Model": "andreaskoepf\/llama2-13b-megacode2_min100", "Average \u2b06\ufe0f": 56.92, "ARC": 60.58, "HellaSwag": 81.26, @@ -50498,22 +68875,22 @@ "TruthfulQA": 48.89, "Winogrande": 76.95, "GSM8K": 15.92, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "llama2", + "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 11.0, - "Available on the hub": true, - "Model sha": "1f5609ffd40bc3af2dcbc5c88e9312d47a73c4b4", + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "b38d1b53c358a0313c69bcceebe97628327ada82", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "andreaskoepf\/llama2-13b-megacode2_min100", + "T": "\ud83d\udcac", + "Model": "rombodawg\/LosslessMegaCoder-llama2-13b-mini", "Average \u2b06\ufe0f": 56.92, "ARC": 60.58, "HellaSwag": 81.26, @@ -50521,16 +68898,16 @@ "TruthfulQA": 48.89, "Winogrande": 76.95, "GSM8K": 15.92, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", + "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": false, - "Model sha": "b38d1b53c358a0313c69bcceebe97628327ada82", + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "1f5609ffd40bc3af2dcbc5c88e9312d47a73c4b4", "Flagged": false, "MoE": false }, @@ -50597,7 +68974,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "78441c9cec230d2dc76a746854078fa776a019c6", "Flagged": false, @@ -50621,7 +68998,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a5ef9385d9430a81778183d71b58eb2b869d6a7e", "Flagged": false, "MoE": false @@ -50758,12 +69135,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "4a71ce15f9af6fd25b0cde1612e56a7ee589c3e8", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "XuanXuanXuanXuan\/Llama-2-13b-hf-gpt-4-80k", + "Average \u2b06\ufe0f": 56.79, + "ARC": 60.84, + "HellaSwag": 79.88, + "MMLU": 55.56, + "TruthfulQA": 49.83, + "Winogrande": 72.85, + "GSM8K": 21.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "31b6e9f91da1c9a95a9ec7a480de73641b1afaf4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Locutusque\/Orca-2-13b-SFT_v5", @@ -50787,29 +69187,6 @@ "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udfe2", - "Model": "01-ai\/Yi-6B-200K", - "Average \u2b06\ufe0f": 56.76, - "ARC": 53.75, - "HellaSwag": 75.57, - "MMLU": 64.65, - "TruthfulQA": 41.56, - "Winogrande": 73.64, - "GSM8K": 31.39, - "Type": "pretrained", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "bfloat16", - "Merged": false, - "Hub License": "other", - "#Params (B)": 6.06, - "Hub \u2764\ufe0f": 154.0, - "Available on the hub": true, - "Model sha": "6cb672ed8441c35d043dd3cda448466daa3b38b1", - "Flagged": false, - "MoE": true - }, { "T": "\ud83d\udcac", "Model": "yeontaek\/Platypus2xOpenOrca-13B-IA3-v3", @@ -50851,7 +69228,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5a6c3686749ecb76971a915403da8c07a98078a6", "Flagged": false, "MoE": false @@ -50919,7 +69296,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.06, - "Hub \u2764\ufe0f": 154.0, + "Hub \u2764\ufe0f": 166.0, "Available on the hub": true, "Model sha": "6cb672ed8441c35d043dd3cda448466daa3b38b1", "Flagged": false, @@ -51080,7 +69457,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "233568319a636b6a7b02a4def2c51d08a3e0fbfc", "Flagged": false, @@ -51101,7 +69478,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -51173,7 +69550,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4328809e568f01e3f0a05764e3bb58e901310415", "Flagged": false, "MoE": false @@ -51195,7 +69572,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 29.0, + "Hub \u2764\ufe0f": 30.0, "Available on the hub": true, "Model sha": "1776feacbf1052cff02eb3d7531a854555d3f6dc", "Flagged": false, @@ -51333,7 +69710,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "45db1dd584c06c31e72f9744ebfb531a54898212", "Flagged": false, @@ -51426,7 +69803,7 @@ "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "1b5ac00479a05bb39077a6644e78f1d3a93daf93", "Flagged": false, "MoE": false @@ -51500,6 +69877,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "pansophic\/new_model_test3", + "Average \u2b06\ufe0f": 56.52, + "ARC": 51.79, + "HellaSwag": 78.61, + "MMLU": 49.14, + "TruthfulQA": 46.89, + "Winogrande": 70.48, + "GSM8K": 42.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "StableLmForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5fc0394d59ea72784285eeb2252411b88e9b6d9d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Undi95\/MLewdBoros-L2-13B", @@ -51517,7 +69917,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "a3033ac5825662f1c66418d7543648dc76980185", "Flagged": false, @@ -51548,7 +69948,7 @@ }, { "T": "\ud83d\udcac", - "Model": "PulsarAI\/EnsembleV5-Nova-13B", + "Model": "TFLai\/EnsembleV5-Nova-13B", "Average \u2b06\ufe0f": 56.49, "ARC": 62.71, "HellaSwag": 82.55, @@ -51564,14 +69964,14 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "3e25556187ba576082a85c270d2d4b4ea6ea9f6f", + "Available on the hub": false, + "Model sha": "7ba38d309709d35149b4a18f94096875885035ae", "Flagged": false, "MoE": false }, { "T": "\ud83d\udcac", - "Model": "TFLai\/EnsembleV5-Nova-13B", + "Model": "PulsarAI\/EnsembleV5-Nova-13B", "Average \u2b06\ufe0f": 56.49, "ARC": 62.71, "HellaSwag": 82.55, @@ -51587,8 +69987,8 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "7ba38d309709d35149b4a18f94096875885035ae", + "Available on the hub": false, + "Model sha": "3e25556187ba576082a85c270d2d4b4ea6ea9f6f", "Flagged": false, "MoE": false }, @@ -51609,7 +70009,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 119.0, + "Hub \u2764\ufe0f": 125.0, "Available on the hub": true, "Model sha": "24916f62b8243a7e4646ea53eeb45d890cbd308f", "Flagged": false, @@ -51679,7 +70079,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "761783745fcb97831ad8035d3cbd5de484aca3ce", "Flagged": false, "MoE": false @@ -51701,7 +70101,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 76.0, + "Hub \u2764\ufe0f": 79.0, "Available on the hub": true, "Model sha": "640192e2ba5898f87c407a9f771fc270f7628dee", "Flagged": false, @@ -51745,7 +70145,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", + "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -51794,7 +70194,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ae1145f9fa846ab8d39d8b7da888287ef917efb5", "Flagged": false, "MoE": false @@ -51839,12 +70239,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "c4e7b771e30fdbfd6bd2e66a6928024bd5692bbd", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "NeuralNovel\/Senzu-7B-v0.1", + "Average \u2b06\ufe0f": 56.4, + "ARC": 58.19, + "HellaSwag": 81.98, + "MMLU": 63.2, + "TruthfulQA": 40.2, + "Winogrande": 76.64, + "GSM8K": 18.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "571f2733df7ca66eee20b32674cedce1017e21f6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sao10K\/Mythical-Destroyer-L2-13B", @@ -51885,7 +70308,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "fb65f697de632f2f3fef57fc3cd12fb5e4913a89", "Flagged": false, @@ -51931,7 +70354,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 36.0, "Available on the hub": true, "Model sha": "6f6ec6024ee054020e49fd96f149919692848f0b", "Flagged": false, @@ -52006,6 +70429,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Kabster\/BioMistral-Zephyr-Beta-SLERP", + "Average \u2b06\ufe0f": 56.35, + "ARC": 62.12, + "HellaSwag": 84.13, + "MMLU": 60.63, + "TruthfulQA": 54.6, + "Winogrande": 76.64, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b6f6be7fa65ed209721e55c6545cb332113a6bd5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "bartowski\/internlm2-math-20b-llama", @@ -52072,7 +70518,7 @@ "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "b373eda586a6527e62382eda5480204652a82499", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -52093,7 +70539,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5bd0eb026b12c59fd198f307c0c17188af69744c", "Flagged": false, "MoE": false @@ -52207,7 +70653,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "c56a396342133bbd75ab3f79622c85cb55be49a4", "Flagged": false, @@ -52296,8 +70742,8 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -52320,9 +70766,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 31.0, "Available on the hub": true, "Model sha": "5770d488c48c4c97ee53572dd8577aae584f9230", "Flagged": false, @@ -52346,7 +70792,7 @@ "Hub License": "other", "#Params (B)": 6.06, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "9271df80f5221362cb5ffd71f463f8f8d08c31dc", "Flagged": false, "MoE": false @@ -52368,7 +70814,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "665948fc79acc2bcce3e9e7d2b0689ca43ae62d4", "Flagged": false, @@ -52392,11 +70838,80 @@ "Hub License": "?", "#Params (B)": 11.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9399ea6c2a1d955e31d6b4d68b2b86115aea0e59", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Azazelle\/Moko-DARE", + "Average \u2b06\ufe0f": 56.16, + "ARC": 60.58, + "HellaSwag": 82.08, + "MMLU": 61.94, + "TruthfulQA": 52.17, + "Winogrande": 75.14, + "GSM8K": 5.08, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b95e6fa7ed89fdb901a0e1fba45c94f2154a0c2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mistral-7b-v19.1-4k", + "Average \u2b06\ufe0f": 56.16, + "ARC": 53.41, + "HellaSwag": 74.58, + "MMLU": 57.29, + "TruthfulQA": 48.25, + "Winogrande": 69.93, + "GSM8K": 33.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "df3762aafe547c0c87cfbf7e527c891885e51084", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v5-4b", + "Average \u2b06\ufe0f": 56.16, + "ARC": 46.76, + "HellaSwag": 71.87, + "MMLU": 55.04, + "TruthfulQA": 47.51, + "Winogrande": 67.4, + "GSM8K": 48.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "94ac52d3ed32f070362d6005f5e57d8ffc5e81a5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BFauber\/lora_llama2-13b_10e5_r128_a16", @@ -52483,7 +70998,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "24be61d31af8ac3e8c57d924c749ca3cf5f681ba", "Flagged": false, @@ -52507,7 +71022,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "fbe6f0e32b5ecf9d75510d0b11a286466f46d79e", "Flagged": false, "MoE": false @@ -52598,7 +71113,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "2f0e2cb734685a6ce0736a9f3e909a795d7592cc", "Flagged": false, @@ -52622,7 +71137,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "569f848698a468fb03d37033c67f3734bbaec127", "Flagged": false, "MoE": false @@ -52667,7 +71182,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 89.0, + "Hub \u2764\ufe0f": 95.0, "Available on the hub": true, "Model sha": "9088377314f91af4b48940e09a0c76d0878f5020", "Flagged": false, @@ -52713,7 +71228,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "d37d99b4656190a23ec51baaad4d1bf6421e67c5", "Flagged": false, @@ -52736,12 +71251,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "af473e64f6a4fa02a7e24ee7679eea9505eb179d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/g8s-preview", + "Average \u2b06\ufe0f": 56.04, + "ARC": 49.74, + "HellaSwag": 72.27, + "MMLU": 54.85, + "TruthfulQA": 52.49, + "Winogrande": 67.48, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "64f2e6fd94015d09f6a0e9e5b791cac76828aa2a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BFauber\/lora_llama2-13b_10e5_r2_a4", @@ -52767,7 +71305,7 @@ }, { "T": "\ud83d\udd36", - "Model": "Undi95\/ReMM-SLERP-L2-13B", + "Model": "The-Face-Of-Goonery\/Huginn-13b-v1.2", "Average \u2b06\ufe0f": 56.03, "ARC": 60.92, "HellaSwag": 83.56, @@ -52780,17 +71318,17 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 18.0, - "Available on the hub": true, - "Model sha": "27baccf242bc1dc34fc39661a40bbf867cbea8b5", + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": false, + "Model sha": "cb3562e7aae05a95fe61610b7b8f4957d3529ce7", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "The-Face-Of-Goonery\/Huginn-13b-v1.2", + "Model": "Undi95\/ReMM-SLERP-L2-13B", "Average \u2b06\ufe0f": 56.03, "ARC": 60.92, "HellaSwag": 83.56, @@ -52803,11 +71341,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 12.0, - "Available on the hub": false, - "Model sha": "cb3562e7aae05a95fe61610b7b8f4957d3529ce7", + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "27baccf242bc1dc34fc39661a40bbf867cbea8b5", "Flagged": false, "MoE": false }, @@ -52828,7 +71366,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "5f80b372b493d901cab4490b4f23c71499023615", "Flagged": false, @@ -52857,6 +71395,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-MoE-A2.7B", + "Average \u2b06\ufe0f": 56.03, + "ARC": 54.86, + "HellaSwag": 79.39, + "MMLU": 62.54, + "TruthfulQA": 50.09, + "Winogrande": 72.3, + "GSM8K": 16.98, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.32, + "Hub \u2764\ufe0f": 117.0, + "Available on the hub": false, + "Model sha": "e8c04bdfc419473cfb5e03385ee9b4e9dedca7eb", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "vilm\/Quyen-v0.1", @@ -52920,12 +71481,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 209.0, + "Hub \u2764\ufe0f": 217.0, "Available on the hub": true, "Model sha": "faa4ef8c87dbb00d447904ceb048d49b6a463d07", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Minami-su\/Qwen1.5-7B-Chat_llamafy", + "Average \u2b06\ufe0f": 56.0, + "ARC": 57.59, + "HellaSwag": 78.52, + "MMLU": 61.18, + "TruthfulQA": 57.59, + "Winogrande": 66.46, + "GSM8K": 14.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "19941b2df44ccea90a21c396a5fe19742f20e596", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "The-Face-Of-Goonery\/huginnv1.2", @@ -52944,7 +71528,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aed4ddc951c657993939fa5b87a4088550569a3b", "Flagged": false, "MoE": false @@ -52968,7 +71552,7 @@ "mit" ], "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 277.0, + "Hub \u2764\ufe0f": 289.0, "Available on the hub": true, "Model sha": "8f95aa9cd207db7b24179fc779c2b8973e71bee2", "Flagged": false, @@ -52992,7 +71576,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e355ead3a939f471fe2586201156fb972fad0f4b", "Flagged": false, "MoE": false @@ -53020,6 +71604,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-gemma-7b-v19.1-4k", + "Average \u2b06\ufe0f": 55.95, + "ARC": 55.29, + "HellaSwag": 71.07, + "MMLU": 53.32, + "TruthfulQA": 49.21, + "Winogrande": 67.48, + "GSM8K": 39.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "546da11ac932df3e3792b7b9f98d546754bbc8d5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BFauber\/lora_llama2-13b_10e5_r2_a64", @@ -53106,7 +71713,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "5a45cb2a6442581ce32cc19c561c49cec1db4ebb", "Flagged": false, @@ -53130,7 +71737,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5a54eb9d5a66df4720ec52422f5627ccd94d5fd6", "Flagged": false, "MoE": false @@ -53296,9 +71903,32 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "yanolja\/EEVE-Korean-2.8B-v1.0", + "Average \u2b06\ufe0f": 55.9, + "ARC": 57.25, + "HellaSwag": 72.15, + "MMLU": 51.62, + "TruthfulQA": 44.27, + "Winogrande": 73.72, + "GSM8K": 36.39, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.82, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "94e55e0dcb1cae43ad0ed29ff889b0b8d906ef8f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "openBuddy\/openbuddy-llama2-34b-v11.1-bf16", + "Model": "OpenBuddy\/openbuddy-codellama2-34b-v11.1-bf16", "Average \u2b06\ufe0f": 55.88, "ARC": 50.0, "HellaSwag": 71.19, @@ -53307,21 +71937,21 @@ "Winogrande": 70.8, "GSM8K": 34.57, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", - "#Params (B)": 33.53, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "21ac0d26c0097e5ac5b4a757493574b156da7731", + "Hub License": null, + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "1b361b3634bf59913b47c9dad1b138e99833472b", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "OpenBuddy\/openbuddy-codellama2-34b-v11.1-bf16", + "Model": "openBuddy\/openbuddy-llama2-34b-v11.1-bf16", "Average \u2b06\ufe0f": 55.88, "ARC": 50.0, "HellaSwag": 71.19, @@ -53330,15 +71960,38 @@ "Winogrande": 70.8, "GSM8K": 34.57, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": null, - "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 11.0, + "Hub License": "?", + "#Params (B)": 33.53, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "1b361b3634bf59913b47c9dad1b138e99833472b", + "Model sha": "21ac0d26c0097e5ac5b4a757493574b156da7731", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-tutor-13b-ep3", + "Average \u2b06\ufe0f": 55.88, + "ARC": 57.34, + "HellaSwag": 81.51, + "MMLU": 57.02, + "TruthfulQA": 52.99, + "Winogrande": 74.35, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2cf2424169d31299caff38cd7ac68e69974d6535", "Flagged": false, "MoE": false }, @@ -53365,29 +72018,6 @@ "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udd36", - "Model": "luffycodes\/vicuna-class-tutor-13b-ep3", - "Average \u2b06\ufe0f": 55.88, - "ARC": 57.34, - "HellaSwag": 81.51, - "MMLU": 57.02, - "TruthfulQA": 52.99, - "Winogrande": 74.35, - "GSM8K": 12.05, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "float16", - "Merged": false, - "Hub License": "llama2", - "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "2cf2424169d31299caff38cd7ac68e69974d6535", - "Flagged": false, - "MoE": false - }, { "T": "\ud83d\udd36", "Model": "YeungNLP\/firefly-llama2-13b-v1.2", @@ -53435,8 +72065,8 @@ "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "maywell\/Synatra-V0.1-7B-Instruct", + "T": "\ud83d\udd36", + "Model": "maywell\/Synatra-V0.1-7B", "Average \u2b06\ufe0f": 55.86, "ARC": 55.29, "HellaSwag": 76.63, @@ -53444,22 +72074,22 @@ "TruthfulQA": 55.76, "Winogrande": 72.77, "GSM8K": 19.41, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "MistralForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "cc-by-nc-4.0", - "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 16.0, - "Available on the hub": true, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "7ee3416f31a3c7e8d5ab4295ac1b641075f36345", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "maywell\/Synatra-V0.1-7B", + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-V0.1-7B-Instruct", "Average \u2b06\ufe0f": 55.86, "ARC": 55.29, "HellaSwag": 76.63, @@ -53467,14 +72097,14 @@ "TruthfulQA": 55.76, "Winogrande": 72.77, "GSM8K": 19.41, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 7.11, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "7ee3416f31a3c7e8d5ab4295ac1b641075f36345", "Flagged": false, @@ -53567,7 +72197,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "98731ddd2dd52fd1b2c69c4cb95bbb1ac03ce496", "Flagged": false, "MoE": false @@ -53681,12 +72311,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 10.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, "Model sha": "5fc7d7bb8ee87dab18d74bb1e25024eba3019a0b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "pansophic\/rocket-3B", + "Average \u2b06\ufe0f": 55.77, + "ARC": 50.6, + "HellaSwag": 76.69, + "MMLU": 47.1, + "TruthfulQA": 55.82, + "Winogrande": 67.96, + "GSM8K": 36.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "StableLmForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 67.0, + "Available on the hub": true, + "Model sha": "ddf1caac5a50ff0984f08c9e195eaf952e3b0ca8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NousResearch\/Nous-Hermes-Llama2-13b", @@ -53706,7 +72359,7 @@ "mit" ], "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 277.0, + "Hub \u2764\ufe0f": 289.0, "Available on the hub": true, "Model sha": "8f95aa9cd207db7b24179fc779c2b8973e71bee2", "Flagged": false, @@ -53776,11 +72429,57 @@ "Hub License": "apache-2.0", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "df18562607b2ba0fc296da17c398b9d3451c6a89", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Telugu-LLM-Labs\/Indic-gemma-7b-finetuned-sft-Navarasa-2.0", + "Average \u2b06\ufe0f": 55.74, + "ARC": 54.61, + "HellaSwag": 74.35, + "MMLU": 54.15, + "TruthfulQA": 49.59, + "Winogrande": 69.61, + "GSM8K": 32.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "84d251f088d2954561a4348883ba28f6f3265182", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Abhaykoul\/vortex2", + "Average \u2b06\ufe0f": 55.74, + "ARC": 50.68, + "HellaSwag": 76.72, + "MMLU": 47.11, + "TruthfulQA": 55.83, + "Winogrande": 67.64, + "GSM8K": 36.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "StableLmForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7521183a05815492532f1da972657f06912e406c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "PulsarAI\/CollectiveCognition-v1.1-Nebula-7B", @@ -53799,7 +72498,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c41d373a2d49b79236d6c4d0dfc4086e709c07eb", "Flagged": false, "MoE": false @@ -53913,8 +72612,8 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 506.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 527.0, + "Available on the hub": true, "Model sha": "7da18fb10421c3ae2a1eb92815bad75e84816e35", "Flagged": false, "MoE": false @@ -54053,7 +72752,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.99, - "Hub \u2764\ufe0f": 25.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "c0cbe0b3c88041bb6beef27dbe85146af8dddec9", "Flagged": false, @@ -54099,7 +72798,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "73a27445e5e5a72857626e551c70542ec607f60c", "Flagged": false, @@ -54192,7 +72891,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1a827ccb7f00157b3cc9ce538d61a6ba8d5a65db", "Flagged": false, "MoE": false @@ -54215,11 +72914,34 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a8e18f970f7ca994740177d6c228adee9e17aba9", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "Abhaykoul\/HelpingAI-3B", + "Average \u2b06\ufe0f": 55.59, + "ARC": 50.6, + "HellaSwag": 76.64, + "MMLU": 46.82, + "TruthfulQA": 55.62, + "Winogrande": 67.8, + "GSM8K": 36.09, + "Type": "pretrained", + "Architecture": "StableLmForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "945820ba0c6e153601f477d29eb70661f2af58b1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "defog\/sqlcoder-34b-alpha", @@ -54237,12 +72959,35 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 159.0, + "Hub \u2764\ufe0f": 162.0, "Available on the hub": true, "Model sha": "6712da4d486caec81d6b1b650d0596517052cffe", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/StableBeluga-7B-activity-fine-tuned-v2", + "Average \u2b06\ufe0f": 55.58, + "ARC": 56.23, + "HellaSwag": 79.06, + "MMLU": 52.54, + "TruthfulQA": 50.01, + "Winogrande": 75.53, + "GSM8K": 20.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "97b647167ef3e6a043ff2c7a87ff1da117f32027", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "TFLai\/Stable-Platypus2-13B-QLoRA-0.80-epoch", @@ -54261,7 +73006,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0c15b8540335b3e21a976a5fc5c33b47927fea6c", "Flagged": false, "MoE": false @@ -54283,7 +73028,7 @@ "Merged": false, "Hub License": "artistic-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 27.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": true, "Model sha": "e8e9a4804c842b84def9e9aaae38236d4754f277", "Flagged": false, @@ -54307,7 +73052,7 @@ "Hub License": "?", "#Params (B)": 20.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "79946225fa7a215e0ebcf4440a9cce88e475deaa", "Flagged": false, "MoE": false @@ -54377,7 +73122,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "49bf4a58453d191845668b8ff17e4b8f0e9ccae6", "Flagged": false, @@ -54544,6 +73289,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-1-2", + "Average \u2b06\ufe0f": 55.42, + "ARC": 62.03, + "HellaSwag": 81.3, + "MMLU": 62.95, + "TruthfulQA": 46.81, + "Winogrande": 77.74, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7f94c120e461d0a99ec60d38b124bc8bda47d8cb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "lmsys\/vicuna-13b-v1.5", @@ -54561,7 +73329,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 159.0, + "Hub \u2764\ufe0f": 172.0, "Available on the hub": true, "Model sha": "3deb0106f72a3a433f0c6ea0cb978bdf14bcd3a6", "Flagged": false, @@ -54608,7 +73376,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1c959d4b5d5b8683b051f07475bb5c1ab24c8bb0", "Flagged": false, "MoE": false @@ -54768,7 +73536,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 192.0, + "Hub \u2764\ufe0f": 195.0, "Available on the hub": false, "Model sha": "54f33278a04aa4e612bca482b82f801ab658e890", "Flagged": false, @@ -54815,7 +73583,7 @@ "Hub License": "?", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "22c83f7d68e547fb0b59acfa01c60b108c59fe55", "Flagged": false, "MoE": false @@ -54837,7 +73605,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "fa81ddf8b87ec339b2519044c4271bc59c4b65aa", "Flagged": false, @@ -54884,7 +73652,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "15a99bc147cf9b744cbab7a7c8c5f232cd0c8d10", "Flagged": false, "MoE": false @@ -54953,7 +73721,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f147bf8428c174d1dc0332da626d4b039690ceab", "Flagged": false, "MoE": false @@ -54975,7 +73743,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 157.0, + "Hub \u2764\ufe0f": 160.0, "Available on the hub": true, "Model sha": "d3e967887d285343b8e239e26c6778c26931a536", "Flagged": false, @@ -55050,6 +73818,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ResplendentAI\/Obscura_32k_7B", + "Average \u2b06\ufe0f": 55.3, + "ARC": 55.29, + "HellaSwag": 78.0, + "MMLU": 49.13, + "TruthfulQA": 63.03, + "Winogrande": 69.06, + "GSM8K": 17.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4a17e943e5e358a9ff3a932bbc237814719590d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ewqr2130\/mistral-se-inst-ppo", @@ -55068,7 +73859,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f9d25d717f3972f80336fd15450329e2d8ee3ed4", "Flagged": false, "MoE": false @@ -55113,7 +73904,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 157.0, + "Hub \u2764\ufe0f": 160.0, "Available on the hub": true, "Model sha": "c778b02fdecd4663d2b0a42bfb340fd29969533b", "Flagged": false, @@ -55159,7 +73950,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 19.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": false, "Model sha": "76fb7d00836eb2f1d9c9605d8881d73b782cf324", "Flagged": false, @@ -55182,7 +73973,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "e5d411138e72370c5613dfea0f66ded99f6e62f9", "Flagged": false, @@ -55274,7 +74065,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 46.0, + "Hub \u2764\ufe0f": 49.0, "Available on the hub": true, "Model sha": "f09d0fe655ad57cce9179b7b40ea6f81e07db18c", "Flagged": false, @@ -55297,7 +74088,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": false, "Model sha": "5c8aeb722e11d1c7258abd45f9f2840f57976c28", "Flagged": false, @@ -55318,10 +74109,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 39.0, + "Available on the hub": false, "Model sha": "31103acf93479d5c3865fb9b51dcb38e10d8b801", "Flagged": false, "MoE": false @@ -55344,7 +74135,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1f81c0439f60d848e3cbc7f06fcd58b5161a8557", "Flagged": false, "MoE": false @@ -55389,7 +74180,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "2fcef275782b2c1061cf671d889aea652d13236c", "Flagged": false, @@ -55435,7 +74226,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "5dac6f7559dba1c6fb59fee18c3e713cc3c83db7", "Flagged": false, @@ -55459,11 +74250,34 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d60ffacb4671aa412dde58d6c58173296cb0d566", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "IkariDev\/Athnete-13B", + "Average \u2b06\ufe0f": 55.17, + "ARC": 62.12, + "HellaSwag": 84.36, + "MMLU": 57.58, + "TruthfulQA": 51.05, + "Winogrande": 75.93, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "954188534f72de489fc9fdc628c8041b73f5cc90", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udcac", "Model": "qblocks\/zephyr_7b_norobots", @@ -55482,7 +74296,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "312485e3c11a5cace45ad04dcf87a89df6e69571", "Flagged": false, "MoE": false @@ -55504,7 +74318,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.72, - "Hub \u2764\ufe0f": 55.0, + "Hub \u2764\ufe0f": 100.0, "Available on the hub": true, "Model sha": "0addb6bfd79e59bce8f61ed60cdafd906c04d447", "Flagged": false, @@ -55597,7 +74411,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "134cea14627fd875f6f277cad92f988024855478", "Flagged": false, "MoE": false @@ -55665,7 +74479,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.72, - "Hub \u2764\ufe0f": 55.0, + "Hub \u2764\ufe0f": 100.0, "Available on the hub": true, "Model sha": "0addb6bfd79e59bce8f61ed60cdafd906c04d447", "Flagged": false, @@ -55711,7 +74525,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 64.0, + "Hub \u2764\ufe0f": 69.0, "Available on the hub": true, "Model sha": "3cdc103995ccd5fc7fd2cb5f51f71b510466f5fc", "Flagged": false, @@ -55758,7 +74572,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "134cea14627fd875f6f277cad92f988024855478", "Flagged": false, "MoE": false @@ -55780,7 +74594,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "afc39cbb0a3451d31442ff3d4a7a2752e3b0b67b", "Flagged": false, @@ -55826,7 +74640,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 129.0, + "Hub \u2764\ufe0f": 131.0, "Available on the hub": true, "Model sha": "160f58ec85ef25ad935eb583f14c7e8c7f7e7839", "Flagged": false, @@ -55872,7 +74686,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 258.0, + "Hub \u2764\ufe0f": 264.0, "Available on the hub": true, "Model sha": "cb69cda10a72bc9736b1c10181ac41f28b69ff9b", "Flagged": false, @@ -55921,7 +74735,7 @@ "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "4d3b1d7a4a5e243d3b8882abaa4b4a13d0ecbce4", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -55964,7 +74778,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "cf9a561b57145748455fd3e193d2b0e4ae0a0fce", "Flagged": false, @@ -56010,12 +74824,35 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 72.0, + "Hub \u2764\ufe0f": 73.0, "Available on the hub": false, "Model sha": "badd80f8a6f46fb15310fedf6d4db54959854897", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "seb-c\/Psydestroyer-20B", + "Average \u2b06\ufe0f": 55.04, + "ARC": 60.32, + "HellaSwag": 85.17, + "MMLU": 55.56, + "TruthfulQA": 54.83, + "Winogrande": 74.27, + "GSM8K": 0.08, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6a8e7636f7546c0aae531e2c3b76a0653ea6858d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "chargoddard\/llama-2-16b-nastychat", @@ -56033,7 +74870,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 16.19, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": false, "Model sha": "6fb7f82d486b3eee53d750f83cc7eae434349809", "Flagged": false, @@ -56082,7 +74919,7 @@ "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "4d3b1d7a4a5e243d3b8882abaa4b4a13d0ecbce4", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -56171,7 +75008,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 36.0, "Available on the hub": true, "Model sha": "aab7ce4d48b31a295a0116b61569d8e87a09bb7a", "Flagged": false, @@ -56195,7 +75032,7 @@ "Hub License": "?", "#Params (B)": 12.97, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "576094cbf4988baf88b3bb66678be1db70bd720a", "Flagged": false, "MoE": false @@ -56263,7 +75100,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 211.0, + "Hub \u2764\ufe0f": 218.0, "Available on the hub": true, "Model sha": "277697af19d4b267626ebc9f4e078d19a9a0fddf", "Flagged": false, @@ -56307,7 +75144,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -56355,12 +75192,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1329.0, + "Hub \u2764\ufe0f": 1381.0, "Available on the hub": true, "Model sha": "7961f5aa9b736bf8e364b2e6f201190f97a27931", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "maldv\/electric-sheep-7b-alpha", + "Average \u2b06\ufe0f": 54.94, + "ARC": 54.86, + "HellaSwag": 76.43, + "MMLU": 50.45, + "TruthfulQA": 48.26, + "Winogrande": 70.32, + "GSM8K": 29.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "995365226f183101014687b9dc33ea0cd8dc1285", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "WebraftAI\/synapsellm-7b-mistral-v0.4-preview3", @@ -56407,6 +75267,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Llama-2-13b-chat-hf-gpt-4-80k-base_lora", + "Average \u2b06\ufe0f": 54.93, + "ARC": 55.38, + "HellaSwag": 75.69, + "MMLU": 53.99, + "TruthfulQA": 50.93, + "Winogrande": 69.85, + "GSM8K": 23.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "75febccaa3daa15c1df629b1a1405f173f98e284", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/wizardLM-13B-1.0-fp16", @@ -56425,7 +75308,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b79733805e98e668ff9a459975c259881b1b8014", "Flagged": false, "MoE": false @@ -56516,8 +75399,8 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 869.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 921.0, + "Available on the hub": true, "Model sha": "f848cf15ab9a51ae5735ab28120a9a0773eeb541", "Flagged": false, "MoE": false @@ -56539,7 +75422,7 @@ "Merged": false, "Hub License": "openrail++", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 31.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "d4af0b233a5b6a214e96582e103396e99dcf5f95", "Flagged": false, @@ -56568,6 +75451,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Qwen1.5-7B-Dutch-Chat-Sft-Bf16", + "Average \u2b06\ufe0f": 54.91, + "ARC": 54.27, + "HellaSwag": 75.53, + "MMLU": 61.98, + "TruthfulQA": 47.26, + "Winogrande": 68.67, + "GSM8K": 21.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a0ecf9ea6e6a1a2b778ddfb6772c40a79ff84921", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/Kimiko-v2-13B-fp16", @@ -56606,9 +75512,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": false, "Model sha": "69615d9a8e1547f2407afd3380868a99f780e008", "Flagged": false, @@ -56677,12 +75583,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "6e918ff9f563552af4ad66f4308f6d040e24af4b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aboros98\/lilo2", + "Average \u2b06\ufe0f": 54.87, + "ARC": 51.88, + "HellaSwag": 72.2, + "MMLU": 46.15, + "TruthfulQA": 47.02, + "Winogrande": 66.06, + "GSM8K": 45.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1e5b27a424bc9372174b76b30a532ee73f392fdb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Mikael110\/llama-2-13b-guanaco-fp16", @@ -56723,7 +75652,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 113.0, + "Hub \u2764\ufe0f": 115.0, "Available on the hub": false, "Model sha": "aed786b0200251c9962ac200c50f7e367f264b46", "Flagged": false, @@ -56772,7 +75701,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5427ceec420f943a0b011a4d96f3efc292306933", "Flagged": false, "MoE": false @@ -56794,7 +75723,7 @@ "Merged": false, "Hub License": "wtfpl", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 119.0, + "Hub \u2764\ufe0f": 128.0, "Available on the hub": true, "Model sha": "3f4f76e2d94308ea6b0edc3de83f18c213a8fde5", "Flagged": false, @@ -56823,6 +75752,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JunchengXie\/Mistral-7B-Instruct-v0.1-gpt-4-80k-base_lora", + "Average \u2b06\ufe0f": 54.84, + "ARC": 53.67, + "HellaSwag": 73.58, + "MMLU": 54.89, + "TruthfulQA": 56.81, + "Winogrande": 72.38, + "GSM8K": 17.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6b896c4b31159fd551634e5d0234d7109870f33e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sail\/Sailor-7B-Chat", + "Average \u2b06\ufe0f": 54.81, + "ARC": 52.3, + "HellaSwag": 75.01, + "MMLU": 56.24, + "TruthfulQA": 44.09, + "Winogrande": 70.8, + "GSM8K": 30.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c7bd0a5e9ec309952f4b8187399314d618da8496", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ajibawa-2023\/Code-13B", @@ -56840,7 +75815,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "91f5a6d5cdf93aeb86dd8965e195d51522957fc6", "Flagged": false, @@ -56864,7 +75839,7 @@ "Hub License": "?", "#Params (B)": 33.48, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3fd110de9282e52f56f999bf1da1a76425f00e29", "Flagged": false, "MoE": false @@ -56910,7 +75885,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2af03c3287c60c4ba2fb6afa86c26cf722ab001d", "Flagged": false, "MoE": false @@ -56932,7 +75907,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 212.0, + "Hub \u2764\ufe0f": 214.0, "Available on the hub": true, "Model sha": "6760d0c07ffdc2405295ed7a29437cf4dc414bac", "Flagged": false, @@ -57027,7 +76002,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3d91f63d82abd598d5b80d24d74feb6b00b7d80f", "Flagged": false, "MoE": false @@ -57095,7 +76070,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 35.0, "Available on the hub": true, "Model sha": "ed15089024f3ecad9a8c4ce1db302cc01aa9f4ee", "Flagged": false, @@ -57141,10 +76116,10 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "cc51a4e64b0821feda101dc04737486b4ff60735", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -57239,6 +76214,75 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "pansophic\/new_model_test", + "Average \u2b06\ufe0f": 54.63, + "ARC": 52.56, + "HellaSwag": 73.65, + "MMLU": 46.02, + "TruthfulQA": 51.25, + "Winogrande": 66.38, + "GSM8K": 37.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b80248dbdf3e3d4ee4a8d498afd8a4d96892ff85", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "ZySec-AI\/ZySec-7B-v2", + "Average \u2b06\ufe0f": 54.63, + "ARC": 53.07, + "HellaSwag": 76.3, + "MMLU": 54.55, + "TruthfulQA": 47.05, + "Winogrande": 68.75, + "GSM8K": 28.05, + "Type": "pretrained", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9554702bbe26b1d1515e75ccb0b3549096622440", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "aihub-app\/ZySec-8B-v2", + "Average \u2b06\ufe0f": 54.63, + "ARC": 53.07, + "HellaSwag": 76.3, + "MMLU": 54.55, + "TruthfulQA": 47.05, + "Winogrande": 68.75, + "GSM8K": 28.05, + "Type": "pretrained", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9554702bbe26b1d1515e75ccb0b3549096622440", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/UltraLM-13B-fp16", @@ -57300,10 +76344,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "891be2d8f205baa04c8a92f6ab1225f0d0c3e5bd", "Flagged": false, "MoE": false @@ -57326,11 +76370,34 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6e49d3d205e7f2e15c01ace0901da8931bbaab3b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-qwen1.5-14b-v20.1-32k", + "Average \u2b06\ufe0f": 54.59, + "ARC": 56.91, + "HellaSwag": 74.57, + "MMLU": 66.72, + "TruthfulQA": 54.28, + "Winogrande": 75.06, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c5449bf8b3ede7b0b5a21d493fd88f6e04158c6e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Weyaxi\/Samantha-Nebula-7B", @@ -57440,7 +76507,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 191.0, + "Hub \u2764\ufe0f": 200.0, "Available on the hub": true, "Model sha": "60e31e6bdcf582ad103b807cb74b73ee1d2c4b17", "Flagged": false, @@ -57466,7 +76533,7 @@ "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "2c4fddeb097636d6462b7628a8e053ad3ff4678c", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -57509,10 +76576,10 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 56.0, + "Hub \u2764\ufe0f": 66.0, "Available on the hub": true, "Model sha": "0d193a4562d6836724485cb7df6e58ca846bbfeb", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -57530,10 +76597,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, "Model sha": "7aedafea409de07a997d70a84e30242c7b86877c", "Flagged": false, "MoE": false @@ -57647,7 +76714,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "c12485aa7b31943113d992076cc2d79dce2a73a4", "Flagged": false, @@ -57671,7 +76738,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0a8560232ff73ca3c3f8e217b4517fa6c4f55558", "Flagged": false, "MoE": false @@ -57699,6 +76766,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "KeyonZeng\/lion-gemma-2b", + "Average \u2b06\ufe0f": 54.46, + "ARC": 51.11, + "HellaSwag": 73.47, + "MMLU": 57.15, + "TruthfulQA": 47.92, + "Winogrande": 70.8, + "GSM8K": 26.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "017d3769a05bcc683b76836d9deb156d8509b02c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Radu1999\/Mister", @@ -57713,11 +76803,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "36cc93cd7bc754a5b23b2d47760ee7ed814d84f3", "Flagged": false, "MoE": false @@ -57768,6 +76858,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Qwen1.5-7B-Dutch-Chat-Sft", + "Average \u2b06\ufe0f": 54.44, + "ARC": 50.68, + "HellaSwag": 73.49, + "MMLU": 60.47, + "TruthfulQA": 43.89, + "Winogrande": 68.75, + "GSM8K": 29.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cab7fdeb7f88e65e991b58016837a1da80e3dbf9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Technoculture\/Medorca-2x7b", @@ -57808,8 +76921,8 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, "Model sha": "14f5dfce0fc441490450aa3c3935a495ebebd7d3", "Flagged": false, "MoE": false @@ -57837,6 +76950,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "KeyonZeng\/lion-gemma-7b-cn-v2", + "Average \u2b06\ufe0f": 54.39, + "ARC": 51.79, + "HellaSwag": 73.86, + "MMLU": 55.2, + "TruthfulQA": 47.99, + "Winogrande": 68.75, + "GSM8K": 28.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "64327e196a32cf63d6ccc78a686e923f31a8f283", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE1_17w-r16", @@ -57878,7 +77014,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aeeded8db9eea97e2e6a2e19a006ce1acd110a82", "Flagged": false, "MoE": false @@ -57946,7 +77082,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 9.05, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "4f06a6151128861d5bb256275620f7eadcab3238", "Flagged": false, @@ -57998,6 +77134,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "1TuanPham\/T-Llama", + "Average \u2b06\ufe0f": 54.34, + "ARC": 54.18, + "HellaSwag": 76.48, + "MMLU": 47.98, + "TruthfulQA": 46.47, + "Winogrande": 71.27, + "GSM8K": 29.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.85, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "967eb6cc60c7d648d7630e6501a4ba33767231ba", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "anhnv125\/llama-op-v4", @@ -58016,7 +77175,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6cd644049de2b944beaefcc6aa34965c00e08529", "Flagged": false, "MoE": false @@ -58113,6 +77272,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "abacusai\/bigyi-15b", + "Average \u2b06\ufe0f": 54.29, + "ARC": 56.06, + "HellaSwag": 75.9, + "MMLU": 64.6, + "TruthfulQA": 37.33, + "Winogrande": 70.24, + "GSM8K": 21.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 15.06, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "5ec2656b39515e3a903adfb05e5022b0f4eb5e2a", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "TheBloke\/WizardLM-13B-V1.1-GPTQ", @@ -58176,7 +77358,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 185.0, + "Hub \u2764\ufe0f": 188.0, "Available on the hub": false, "Model sha": "7900eeb715a49affee9e6390f824e62eea3f3fb1", "Flagged": false, @@ -58199,7 +77381,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "1b822c08b1065d5843cc48bf3a841ac5cd9d3b40", "Flagged": false, @@ -58220,9 +77402,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 12.85, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "aa1d543fe3391fe9f0e6143ef785fffe9c871225", "Flagged": false, @@ -58289,10 +77471,10 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 12.85, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, "Model sha": "7a2eed5038addcf4fa3b8dd358b45eb96134e749", "Flagged": false, "MoE": false @@ -58320,6 +77502,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "gmonsoon\/Delta-4B-notso-base", + "Average \u2b06\ufe0f": 54.23, + "ARC": 57.59, + "HellaSwag": 76.1, + "MMLU": 57.26, + "TruthfulQA": 54.31, + "Winogrande": 76.09, + "GSM8K": 4.02, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6a9afe87c5cc0f8afed83635ac71f0ceff0a1421", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "lgaalves\/llama-2-13b-hf-platypus", @@ -58361,7 +77566,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c318a24121bd69509f395e17a9636093213ece21", "Flagged": false, "MoE": false @@ -58452,7 +77657,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "b05b4c22893e950e8e33acb67087a9acc8f0ab97", "Flagged": false, @@ -58598,7 +77803,7 @@ }, { "T": "\ud83d\udd36", - "Model": "ehartford\/Wizard-Vicuna-13B-Uncensored", + "Model": "TheBloke\/Wizard-Vicuna-13B-Uncensored-HF", "Average \u2b06\ufe0f": 54.14, "ARC": 58.96, "HellaSwag": 81.95, @@ -58607,21 +77812,21 @@ "Winogrande": 75.69, "GSM8K": 8.64, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 12.85, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 204.0, "Available on the hub": true, - "Model sha": "95bfd1640a54e76b3e857c2462fd3a77eca0b275", + "Model sha": "fff9ac7f0e2e7b340f2301f5f089d989fc03be67", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "TheBloke\/Wizard-Vicuna-13B-Uncensored-HF", + "Model": "ehartford\/Wizard-Vicuna-13B-Uncensored", "Average \u2b06\ufe0f": 54.14, "ARC": 58.96, "HellaSwag": 81.95, @@ -58630,15 +77835,15 @@ "Winogrande": 75.69, "GSM8K": 8.64, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", - "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 202.0, - "Available on the hub": true, - "Model sha": "fff9ac7f0e2e7b340f2301f5f089d989fc03be67", + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "95bfd1640a54e76b3e857c2462fd3a77eca0b275", "Flagged": false, "MoE": false }, @@ -58657,10 +77862,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6a0a2b6672c7b36c714a66c4a836e0b50c6cb5e6", "Flagged": false, "MoE": false @@ -58683,7 +77888,7 @@ "Hub License": "mit", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "472d986efb1336e3290518f9aad54db5faa510d5", "Flagged": false, "MoE": false @@ -58728,7 +77933,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": false, "Model sha": "f9ef65a3cf50e3c09ccb443f99225148e08517aa", "Flagged": false, @@ -58774,7 +77979,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 27.0, + "Hub \u2764\ufe0f": 28.0, "Available on the hub": true, "Model sha": "ba4536aed022c49bda60e1b56a0dbefc2ea6a30a", "Flagged": false, @@ -58798,11 +78003,34 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c1a5ad1b5e490ed860eeb1b449a02e14da10717f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/autotrain-ixpiv-6kj1e", + "Average \u2b06\ufe0f": 54.11, + "ARC": 61.69, + "HellaSwag": 82.54, + "MMLU": 58.61, + "TruthfulQA": 45.72, + "Winogrande": 76.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6081141e37bb24ef90b1bb7464d53107e48c5fb4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "IkariDev\/Athena-v1", @@ -58912,7 +78140,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.06, - "Hub \u2764\ufe0f": 346.0, + "Hub \u2764\ufe0f": 355.0, "Available on the hub": true, "Model sha": "e00f7cbde45745a22625ac85c6ad5d5b9f27098d", "Flagged": false, @@ -58958,7 +78186,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 65.29, - "Hub \u2764\ufe0f": 57.0, + "Hub \u2764\ufe0f": 58.0, "Available on the hub": true, "Model sha": "40a78d91d43ad9aef6663ff15ddc15be9922bce5", "Flagged": false, @@ -59051,7 +78279,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c4710577003a23ca8e9040d16dfb8f3e9bc5d636", "Flagged": false, "MoE": false @@ -59073,7 +78301,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "b05b4c22893e950e8e33acb67087a9acc8f0ab97", "Flagged": false, @@ -59165,7 +78393,7 @@ "Merged": false, "Hub License": "gpl", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 418.0, + "Hub \u2764\ufe0f": 422.0, "Available on the hub": true, "Model sha": "24e8c03148ffd1f3e469744dfc24ad2ad82848f8", "Flagged": false, @@ -59186,7 +78414,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 13.16, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -59196,7 +78424,7 @@ }, { "T": "\ud83d\udcac", - "Model": "The-Face-Of-Goonery\/Huginn-13b-V4", + "Model": "The-Face-Of-Goonery\/Huginn-13b-v4.5", "Average \u2b06\ufe0f": 54.04, "ARC": 60.67, "HellaSwag": 82.34, @@ -59211,15 +78439,15 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": false, - "Model sha": "6186feee849e0c2b7e62d4cbdc4cdc48260ac684", + "Model sha": "f3be56d8bf71a8d3905974b1e5fcba7336b02159", "Flagged": false, "MoE": false }, { "T": "\ud83d\udcac", - "Model": "The-Face-Of-Goonery\/Huginn-13b-v4.5", + "Model": "The-Face-Of-Goonery\/Huginn-v3-13b", "Average \u2b06\ufe0f": 54.04, "ARC": 60.67, "HellaSwag": 82.34, @@ -59234,15 +78462,15 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": false, - "Model sha": "f3be56d8bf71a8d3905974b1e5fcba7336b02159", + "Model sha": "6c2faf828c5380d28c51fcb4d3d0f1a420fb9a9a", "Flagged": false, "MoE": false }, { "T": "\ud83d\udcac", - "Model": "The-Face-Of-Goonery\/Huginn-v3-13b", + "Model": "The-Face-Of-Goonery\/Huginn-13b-V4", "Average \u2b06\ufe0f": 54.04, "ARC": 60.67, "HellaSwag": 82.34, @@ -59257,9 +78485,9 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "6c2faf828c5380d28c51fcb4d3d0f1a420fb9a9a", + "Model sha": "6186feee849e0c2b7e62d4cbdc4cdc48260ac684", "Flagged": false, "MoE": false }, @@ -59280,7 +78508,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 105.0, + "Hub \u2764\ufe0f": 106.0, "Available on the hub": true, "Model sha": "44830f9e1559f318f5dad875bab40d1d1beddbfc", "Flagged": false, @@ -59303,7 +78531,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.06, - "Hub \u2764\ufe0f": 346.0, + "Hub \u2764\ufe0f": 355.0, "Available on the hub": true, "Model sha": "d8029c814d8faa68e1aef2e488f668a3af5d1a8a", "Flagged": false, @@ -59373,7 +78601,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ada55b32fe8ed55b7691d997ad2e86f232c91aad", "Flagged": false, "MoE": false @@ -59395,7 +78623,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "e378a80b22387a5a30ccbb9feaf3e9b0bc3cfc57", "Flagged": false, @@ -59419,7 +78647,7 @@ "Hub License": "?", "#Params (B)": 32.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5818a6344f48dc5a324589b57cb288a9d54c0b79", "Flagged": false, "MoE": false @@ -59490,7 +78718,7 @@ "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "49678a2dd15fb4e1f1b99616ccc1ffd269912833", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -59533,7 +78761,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "209316bea6eab73d8b18fca2a730b1dff3dcf999", "Flagged": false, @@ -59695,7 +78923,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "469c6674ad2190b639d6f5ce6bfecc1463825dfb", "Flagged": false, "MoE": false @@ -59738,14 +78966,37 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "862c90d07e4614122bce660b8e725d142f6526c4", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Qwen1.5-7B-Dutch-Chat-Dpo", + "Average \u2b06\ufe0f": 53.94, + "ARC": 50.77, + "HellaSwag": 74.24, + "MMLU": 60.7, + "TruthfulQA": 42.37, + "Winogrande": 68.11, + "GSM8K": 27.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "014a7afb6a2043c569bb695c2504b344a26ef8cf", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Voicelab\/trurl-2-13b-academic", @@ -59810,7 +79061,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e6c38a7d2f4ba7b867fff421c08c02ba1908224e", "Flagged": false, "MoE": false @@ -59833,7 +79084,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b1ef5adff5ceb06d2d9808bccf5e06705f9e19dc", "Flagged": false, "MoE": false @@ -59902,7 +79153,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aa5b161b39900c5e80d5bb39d098f6333ad964f7", "Flagged": false, "MoE": false @@ -59953,6 +79204,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "sail\/Sailor-7B", + "Average \u2b06\ufe0f": 53.88, + "ARC": 49.83, + "HellaSwag": 76.21, + "MMLU": 54.65, + "TruthfulQA": 40.08, + "Winogrande": 69.14, + "GSM8K": 33.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "f8a0533c4818d021a7dbf985b9779d0a640bae6b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "yeontaek\/llama-2-13b-QLoRA", @@ -60039,7 +79313,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "c1e1e2743ffa7b9369aebac751b04f7e8740f80d", "Flagged": false, @@ -60063,7 +79337,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e96b5245ef97999f143a2c9f9739e5cf52ec0d64", "Flagged": false, "MoE": false @@ -60200,12 +79474,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 19.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "a4e1f8f62740d676c25eedb4f29f4e776dcc0c22", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "sail\/Sailor-7B", + "Average \u2b06\ufe0f": 53.82, + "ARC": 49.83, + "HellaSwag": 76.21, + "MMLU": 54.84, + "TruthfulQA": 40.12, + "Winogrande": 69.38, + "GSM8K": 32.52, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "f8a0533c4818d021a7dbf985b9779d0a640bae6b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "CHIH-HUNG\/llama-2-13b-Open_Platypus_and_ccp_2.6w-3_epoch", @@ -60229,6 +79526,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-MultiLoRA-sharegpt-mmlu-drop-ffn-1.0general", + "Average \u2b06\ufe0f": 53.78, + "ARC": 53.33, + "HellaSwag": 77.41, + "MMLU": 51.04, + "TruthfulQA": 50.33, + "Winogrande": 72.14, + "GSM8K": 18.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ddaea6ff7adaa39cf175bc15732c4004389c6815", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Weyaxi\/test-help-steer-filtered-orig", @@ -60252,6 +79572,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "KeyonZeng\/lion-gemma-7b-cn", + "Average \u2b06\ufe0f": 53.77, + "ARC": 50.6, + "HellaSwag": 73.21, + "MMLU": 55.72, + "TruthfulQA": 46.98, + "Winogrande": 68.11, + "GSM8K": 27.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1ad610e1040eb72e99672ad4a1ba3f33c6aa6b1a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NekoPunchBBB\/Llama-2-13b-hf_Open-Platypus-8bit-att", @@ -60313,10 +79656,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f3d421aadb29830345bf392f793ce3c33e7d68c5", "Flagged": false, "MoE": false @@ -60339,11 +79682,57 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d74752b931bfddaa063a292e7ea85dfb1d7a4998", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ShadowFall09\/tyc_test1", + "Average \u2b06\ufe0f": 53.74, + "ARC": 55.46, + "HellaSwag": 79.29, + "MMLU": 46.58, + "TruthfulQA": 52.05, + "Winogrande": 74.43, + "GSM8K": 14.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "204ab769ed98e2b0a8aa8288cfcd2791a91ebc2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ShadowFall09\/FANNO", + "Average \u2b06\ufe0f": 53.74, + "ARC": 55.46, + "HellaSwag": 79.29, + "MMLU": 46.58, + "TruthfulQA": 52.05, + "Winogrande": 74.43, + "GSM8K": 14.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "204ab769ed98e2b0a8aa8288cfcd2791a91ebc2e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "yeontaek\/Platypus2-13B-QLoRa", @@ -60546,7 +79935,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "08bc7112a775dd4223d441355f3d619694013789", "Flagged": false, "MoE": false @@ -60589,10 +79978,10 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-sa-4.0", + "Hub License": null, "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 19.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": false, "Model sha": "428508a0cf288c0f5b7891c9b2f758ddf4d62c26", "Flagged": false, "MoE": false @@ -60658,10 +80047,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "openrail", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, "Model sha": "c29b67965ea55da3e2ac678eef7ffdf36f8ef5ab", "Flagged": false, "MoE": false @@ -60683,7 +80072,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 8.54, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "8798db2d228a8d460966f3078fe65db7616ec1dd", "Flagged": false, @@ -60691,7 +80080,7 @@ }, { "T": "\ud83d\udd36", - "Model": "TaylorAI\/Flash-Llama-13B", + "Model": "NewstaR\/Starlight-13B", "Average \u2b06\ufe0f": 53.67, "ARC": 59.3, "HellaSwag": 82.15, @@ -60704,11 +80093,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", - "#Params (B)": 13.02, + "Hub License": null, + "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "81b40096471a8980e3e1a8998f358bd363033783", + "Model sha": "cb9fced568b1abd881133c642c427aaa488f00cc", "Flagged": false, "MoE": false }, @@ -60729,7 +80118,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 56.0, + "Hub \u2764\ufe0f": 57.0, "Available on the hub": false, "Model sha": "b2e65e8ad4bb35e5abaee0170ebd5fc2134a50bb", "Flagged": false, @@ -60737,7 +80126,7 @@ }, { "T": "\ud83d\udd36", - "Model": "NewstaR\/Starlight-13B", + "Model": "TaylorAI\/Flash-Llama-13B", "Average \u2b06\ufe0f": 53.67, "ARC": 59.3, "HellaSwag": 82.15, @@ -60750,11 +80139,34 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": null, - "#Params (B)": 13.0, + "Hub License": "", + "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "cb9fced568b1abd881133c642c427aaa488f00cc", + "Model sha": "81b40096471a8980e3e1a8998f358bd363033783", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Qwen1.5-7B-Dutch-Chat", + "Average \u2b06\ufe0f": 53.66, + "ARC": 53.92, + "HellaSwag": 76.03, + "MMLU": 62.38, + "TruthfulQA": 45.34, + "Winogrande": 68.82, + "GSM8K": 15.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "e8981c1824d88d909cc56edc83fe70d79cb5c3b9", "Flagged": false, "MoE": false }, @@ -60868,7 +80280,7 @@ "Hub License": "?", "#Params (B)": 21.83, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "15bca3e9b25cc2f280fec21686ef3bc445217503", "Flagged": false, "MoE": false @@ -60888,10 +80300,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7da6d235d625e16c850ccd0b947dee40071b1f89", "Flagged": false, "MoE": false @@ -61120,7 +80532,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "981454b6a2275f787592589609df7f2bf558706d", "Flagged": false, @@ -61190,7 +80602,7 @@ "Hub License": "?", "#Params (B)": 33.48, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3e8df2cf4a4ee1c0b2d079cb7be70024d425ea8c", "Flagged": false, "MoE": false @@ -61258,12 +80670,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 91.0, + "Hub \u2764\ufe0f": 93.0, "Available on the hub": true, "Model sha": "6a39a8f3839cfc8c6a966f6b4e70472ac6fb719b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-7B-v2.0", + "Average \u2b06\ufe0f": 53.57, + "ARC": 55.89, + "HellaSwag": 76.66, + "MMLU": 52.05, + "TruthfulQA": 44.33, + "Winogrande": 67.64, + "GSM8K": 24.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "d18abf633a1274527b1cb00a5ddfd4dc684ba9bc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "dhmeltzer\/Llama-2-13b-hf-eli5-wiki-1024_r_64_alpha_16_merged", @@ -61327,7 +80762,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 128.0, + "Hub \u2764\ufe0f": 129.0, "Available on the hub": false, "Model sha": "329adcfc39f48dce183eb0b155b732dbe03c6304", "Flagged": false, @@ -61374,7 +80809,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b6d16c3e1cffef5e914863f41fd96152dafddd6f", "Flagged": false, "MoE": false @@ -61396,12 +80831,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 8.54, - "Hub \u2764\ufe0f": 724.0, + "Hub \u2764\ufe0f": 1018.0, "Available on the hub": true, "Model sha": "dec4b13d574762bd36f0a1b75541439bd852b2e8", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/gemma-7b-it-experiment", + "Average \u2b06\ufe0f": 53.56, + "ARC": 51.45, + "HellaSwag": 71.96, + "MMLU": 53.52, + "TruthfulQA": 47.29, + "Winogrande": 67.96, + "GSM8K": 29.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2fd51857cf72e1cce2dc8e39c016306162ee94b9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "dvruette\/oasst-llama-13b-2-epochs", @@ -61609,6 +81067,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/NEBULA-XB-v1.0", + "Average \u2b06\ufe0f": 53.52, + "ARC": 56.66, + "HellaSwag": 81.78, + "MMLU": 60.98, + "TruthfulQA": 44.03, + "Winogrande": 77.66, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 23.82, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1a41b53056d6e3fa55ed55d01d37b8ebefb453ae", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "budecosystem\/code-millenials-34b", @@ -61646,10 +81127,10 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, - "Hub License": "?", + "Merged": true, + "Hub License": "apache-2.0", "#Params (B)": 7.79, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "c7d5d78d4d938d772fe22c7302a8312a40a20645", "Flagged": false, @@ -61670,7 +81151,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "llama2", + "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -61771,8 +81252,8 @@ "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "psmathur\/orca_mini_v3_7b", + "T": "\ud83d\udcac", + "Model": "pankajmathur\/orca_mini_v3_7b", "Average \u2b06\ufe0f": 53.47, "ARC": 56.91, "HellaSwag": 79.64, @@ -61780,22 +81261,22 @@ "TruthfulQA": 50.51, "Winogrande": 74.27, "GSM8K": 7.13, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 6.61, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 40.0, "Available on the hub": true, - "Model sha": "a1583d2f02041fb37df28eeae4da644d8dff33eb", + "Model sha": "f9849ea6bf0f6ebb78dca1cea1c7a3ef8f7d715c", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "pankajmathur\/orca_mini_v3_7b", + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v3_7b", "Average \u2b06\ufe0f": 53.47, "ARC": 56.91, "HellaSwag": 79.64, @@ -61803,16 +81284,16 @@ "TruthfulQA": 50.51, "Winogrande": 74.27, "GSM8K": 7.13, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "LlamaForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", - "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 40.0, - "Available on the hub": true, - "Model sha": "f9849ea6bf0f6ebb78dca1cea1c7a3ef8f7d715c", + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a1583d2f02041fb37df28eeae4da644d8dff33eb", "Flagged": false, "MoE": false }, @@ -61908,6 +81389,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "stabilityai\/stablelm-zephyr-3b", + "Average \u2b06\ufe0f": 53.43, + "ARC": 46.08, + "HellaSwag": 74.16, + "MMLU": 46.17, + "TruthfulQA": 46.49, + "Winogrande": 65.51, + "GSM8K": 42.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "StableLmForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 226.0, + "Available on the hub": true, + "Model sha": "8b471c751c0e78cb46cf9f47738dd0eb45392071", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "TigerResearch\/tigerbot-13b-base", @@ -61926,7 +81430,7 @@ "Hub License": "?", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2df5ed76be7eff0962f2d816a64eca1e78e1cbf3", "Flagged": false, "MoE": false @@ -61995,7 +81499,7 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "3a33eea0858d411617c472c3c0ae39f17d2b3f5d", "Flagged": false, "MoE": false @@ -62017,7 +81521,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 96.0, + "Hub \u2764\ufe0f": 98.0, "Available on the hub": false, "Model sha": "2abf1163dd8c9b11f07d805c06e6ec90a1f2037e", "Flagged": false, @@ -62084,10 +81588,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9d7031e7d956dd2d25c61d85f594d115ce65b172", "Flagged": false, "MoE": false @@ -62161,6 +81665,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Llama-2-7b-chat-hf-activity-fine-tuned-v4", + "Average \u2b06\ufe0f": 53.3, + "ARC": 54.27, + "HellaSwag": 78.1, + "MMLU": 48.44, + "TruthfulQA": 45.77, + "Winogrande": 73.95, + "GSM8K": 19.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c964836b57483ae83e5b7bc1ece1e121a7727a75", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "TheBloke\/vicuna-13b-v1.3.0-GPTQ", @@ -62186,7 +81713,7 @@ }, { "T": "\ud83d\udd36", - "Model": "pillowtalks-ai\/delta13b", + "Model": "eachadea\/vicuna-13b-1.1", "Average \u2b06\ufe0f": 53.29, "ARC": 52.73, "HellaSwag": 80.13, @@ -62199,11 +81726,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": false, - "Model sha": "83fa0860990df1db35550f973ba4306449e35412", + "Hub \u2764\ufe0f": 136.0, + "Available on the hub": true, + "Model sha": "bfcc6ca66694310be6c85ba0638597f4256c4143", "Flagged": false, "MoE": false }, @@ -62225,14 +81752,14 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8c71dbe9221e83d2ec72e4dc08beccfc78b563c0", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "eachadea\/vicuna-13b-1.1", + "Model": "pillowtalks-ai\/delta13b", "Average \u2b06\ufe0f": 53.29, "ARC": 52.73, "HellaSwag": 80.13, @@ -62245,11 +81772,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 136.0, - "Available on the hub": true, - "Model sha": "bfcc6ca66694310be6c85ba0638597f4256c4143", + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "83fa0860990df1db35550f973ba4306449e35412", "Flagged": false, "MoE": false }, @@ -62278,7 +81805,7 @@ }, { "T": "\ud83d\udd36", - "Model": "TheBloke\/Vicuna-13B-CoT-fp16", + "Model": "lmsys\/vicuna-13b-v1.1", "Average \u2b06\ufe0f": 53.28, "ARC": 52.73, "HellaSwag": 80.14, @@ -62291,17 +81818,17 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", + "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 3.0, - "Available on the hub": true, - "Model sha": "fe74a0ece9089828b301bd0f067ae5f257516179", + "Hub \u2764\ufe0f": 97.0, + "Available on the hub": false, + "Model sha": "8c71dbe9221e83d2ec72e4dc08beccfc78b563c0", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "lmsys\/vicuna-13b-delta-v1.1", + "Model": "TheBloke\/Vicuna-13B-CoT-fp16", "Average \u2b06\ufe0f": 53.28, "ARC": 52.73, "HellaSwag": 80.14, @@ -62314,17 +81841,17 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": null, + "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 409.0, - "Available on the hub": false, - "Model sha": "ffed4c7cf1b9814812078efbe29ec3f610ea39e7", + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fe74a0ece9089828b301bd0f067ae5f257516179", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "lmsys\/vicuna-13b-v1.1", + "Model": "lmsys\/vicuna-13b-delta-v1.1", "Average \u2b06\ufe0f": 53.28, "ARC": 52.73, "HellaSwag": 80.14, @@ -62339,9 +81866,9 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 97.0, + "Hub \u2764\ufe0f": 409.0, "Available on the hub": false, - "Model sha": "8c71dbe9221e83d2ec72e4dc08beccfc78b563c0", + "Model sha": "ffed4c7cf1b9814812078efbe29ec3f610ea39e7", "Flagged": false, "MoE": false }, @@ -62362,7 +81889,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 16.23, - "Hub \u2764\ufe0f": 114.0, + "Hub \u2764\ufe0f": 116.0, "Available on the hub": true, "Model sha": "b7db471d1789802a3a8e3b93cdd66a9f046f17c3", "Flagged": false, @@ -62385,7 +81912,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 40.0, + "Hub \u2764\ufe0f": 50.0, "Available on the hub": true, "Model sha": "42d449dc4f42960a52130893843136ab3fed1256", "Flagged": false, @@ -62483,6 +82010,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Llama-2-7b-chat-hf-activity-fine-tuned-v4", + "Average \u2b06\ufe0f": 53.23, + "ARC": 54.35, + "HellaSwag": 78.12, + "MMLU": 48.42, + "TruthfulQA": 45.83, + "Winogrande": 73.32, + "GSM8K": 19.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c964836b57483ae83e5b7bc1ece1e121a7727a75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "liminerity\/mm4-3b", + "Average \u2b06\ufe0f": 53.22, + "ARC": 44.8, + "HellaSwag": 70.41, + "MMLU": 50.9, + "TruthfulQA": 43.2, + "Winogrande": 66.22, + "GSM8K": 43.82, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "0c43811e69b29c71d87b51b9ae94812616111293", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NLUHOPOE\/Mistral-7B-loss-100000", @@ -62523,7 +82096,7 @@ "Merged": false, "Hub License": "openrail", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "d1d27f8f822d083cfb018e9550784a29d97b51a6", "Flagged": false, @@ -62598,6 +82171,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "AllyArc\/llama_allyarc", + "Average \u2b06\ufe0f": 53.2, + "ARC": 54.35, + "HellaSwag": 78.24, + "MMLU": 48.28, + "TruthfulQA": 47.97, + "Winogrande": 72.3, + "GSM8K": 18.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f8aa4cd3c52e97c7b8fdc5107f4622318c523975", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/Mistral-7B-v0.2-OpenHermes", + "Average \u2b06\ufe0f": 53.2, + "ARC": 55.8, + "HellaSwag": 81.61, + "MMLU": 60.0, + "TruthfulQA": 43.09, + "Winogrande": 78.69, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": false, + "Model sha": "3ee2ade8cb70d99a9f616ff7affe31b059d9a1f6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "meta-math\/MetaMath-Llemma-7B", @@ -62615,7 +82234,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "e31ec61dccd8fa24f44f0592a518491ef76a2235", "Flagged": false, @@ -62731,7 +82350,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f7b6c11b4df16079dfdd1e8dd8c489a8835c7cc4", "Flagged": false, "MoE": false @@ -62754,7 +82373,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "45bd1e47218ba2e075e03f6407980eb839e67eb3", "Flagged": false, "MoE": false @@ -62820,10 +82439,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a3ed7416156963f49bf4dc056188e006c0c214d2", "Flagged": false, "MoE": false @@ -62868,7 +82487,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "feb1fa71e0b24261d3ca428b4aed881dd31f166e", "Flagged": false, @@ -62937,7 +82556,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 16.22, - "Hub \u2764\ufe0f": 32.0, + "Hub \u2764\ufe0f": 33.0, "Available on the hub": true, "Model sha": "923f27245d13058c9c1b3ab0eab6c6c93ffc162e", "Flagged": false, @@ -62966,6 +82585,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "InnerI\/InnerIAI-chat-7b-grok", + "Average \u2b06\ufe0f": 53.11, + "ARC": 52.13, + "HellaSwag": 75.38, + "MMLU": 53.86, + "TruthfulQA": 46.56, + "Winogrande": 72.3, + "GSM8K": 18.42, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cda5bfe3c6d6f905461fa4d126ed8357261d5e55", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "itsliupeng\/llama2_7b_mmlu", @@ -63058,6 +82700,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Telugu-LLM-Labs\/Telugu-Llama2-7B-v0-Instruct", + "Average \u2b06\ufe0f": 53.04, + "ARC": 53.41, + "HellaSwag": 78.35, + "MMLU": 47.79, + "TruthfulQA": 43.29, + "Winogrande": 74.19, + "GSM8K": 21.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "b8e2895810d82fb82a811f452b2e53fef949718c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "wei123602\/FINETUNE3_TEST4", @@ -63098,7 +82763,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 42.0, + "Hub \u2764\ufe0f": 44.0, "Available on the hub": true, "Model sha": "1370c7c595e6c8394e6332bc535ae25e21def85b", "Flagged": false, @@ -63122,11 +82787,34 @@ "Hub License": "other", "#Params (B)": 8.54, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "3d6f29fb83a38b1ec0fbfb69af1b345ac657f7cb", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/dhbacmes-3b-slerp", + "Average \u2b06\ufe0f": 53.02, + "ARC": 45.22, + "HellaSwag": 70.77, + "MMLU": 52.94, + "TruthfulQA": 40.41, + "Winogrande": 65.11, + "GSM8K": 43.67, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9e9ceb32aaf18db6e0a122f69356d06c0e36c5f8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-l2-13b-gpt4-1.4.1", @@ -63213,12 +82901,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 27.0, "Available on the hub": true, "Model sha": "32824ba93e88ccfe8464f6d267a5d67024c7722b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "hamxea\/Llama-2-7b-chat-hf-activity-fine-tuned-v3", + "Average \u2b06\ufe0f": 52.99, + "ARC": 53.33, + "HellaSwag": 78.1, + "MMLU": 48.31, + "TruthfulQA": 45.7, + "Winogrande": 73.48, + "GSM8K": 19.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "471e796a06138051def6777c3742d9e196b56e08", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "The-Face-Of-Goonery\/Huginn-19b-prototype", @@ -63236,7 +82947,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 19.36, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "d2c8cc15c57da217ff29ebaaae4bc4f57d6b21b0", "Flagged": false, @@ -63288,6 +82999,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Llama-2-7b-chat-hf-gpt-4-80k", + "Average \u2b06\ufe0f": 52.97, + "ARC": 54.78, + "HellaSwag": 74.63, + "MMLU": 48.77, + "TruthfulQA": 48.45, + "Winogrande": 72.85, + "GSM8K": 18.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8a4c270873b82edf9759cc693028035f36600a22", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ajibawa-2023\/Code-290k-13B", @@ -63305,7 +83039,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "e2595df2aedc1decaf73d167ce0114e7a9cb2126", "Flagged": false, @@ -63328,7 +83062,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "5d26db18b95778c31dc8425871052f495b267563", "Flagged": false, @@ -63374,7 +83108,7 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 19.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "b1a643e32e467d8dd722186d6c36d16ea4281003", "Flagged": false, @@ -63420,7 +83154,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "a3c4bbccca8b650700a49a225582c17bb49b446b", "Flagged": false, @@ -63581,7 +83315,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": false, "Model sha": "71aa919fc15fa9d9def9185791b15a3f76e7bd8d", "Flagged": false, @@ -63627,7 +83361,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "0bf36fdc22bf30632cced8044667d3d46061d619", "Flagged": false, @@ -63765,7 +83499,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "b8e2895810d82fb82a811f452b2e53fef949718c", "Flagged": false, @@ -63788,7 +83522,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 41.0, + "Hub \u2764\ufe0f": 45.0, "Available on the hub": true, "Model sha": "044918151c5b3910d12f2e489fb7c60752048e1e", "Flagged": false, @@ -63811,7 +83545,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 331.0, + "Hub \u2764\ufe0f": 336.0, "Available on the hub": false, "Model sha": "0261af71d7177453889f868d26607dec8d5aaa2e", "Flagged": false, @@ -63855,10 +83589,10 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 22.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "26fdd8fa420d72ed835c7d17086f0441db0985d4", "Flagged": false, "MoE": false @@ -63880,7 +83614,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 48.0, + "Hub \u2764\ufe0f": 49.0, "Available on the hub": false, "Model sha": "12dc8aacb474522ae2a83c18cb0fdf0907987f8f", "Flagged": false, @@ -63904,7 +83638,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1058709314f7ca090937d0a2b7b37b0b3a8f12a3", "Flagged": false, "MoE": false @@ -63972,7 +83706,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 75.0, "Available on the hub": false, "Model sha": "419dc5acc391de54a60d0b041e94e767d1ef2032", "Flagged": false, @@ -63995,7 +83729,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "2a0b52cd72a30d26ef0391c171b64900106a90a6", "Flagged": false, @@ -64070,6 +83804,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "nnethercott\/orca-open_hermes-llava-v1.5-7b-dpo", + "Average \u2b06\ufe0f": 52.71, + "ARC": 53.07, + "HellaSwag": 77.11, + "MMLU": 51.03, + "TruthfulQA": 47.6, + "Winogrande": 71.9, + "GSM8K": 15.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3e40fa364e9071af5000bc6fe15ae89b0a7da87c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "meta-math\/MetaMath-13B-V1.0", @@ -64093,6 +83850,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Llama-2-7b-hf-gpt-4-80k", + "Average \u2b06\ufe0f": 52.71, + "ARC": 55.55, + "HellaSwag": 77.27, + "MMLU": 46.75, + "TruthfulQA": 48.63, + "Winogrande": 74.03, + "GSM8K": 14.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2950495cb5a6eaabf9ae8b31887e47faa80c5d3b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Yehoon\/yehoon_llama2", @@ -64108,10 +83888,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "443cb81ce988ea6c0b1e20132c170463d559367e", "Flagged": false, "MoE": false @@ -64157,7 +83937,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "42dfc6f7d735670e2f3e30b0919708a81f9a0df9", "Flagged": false, "MoE": false @@ -64203,7 +83983,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "42dfc6f7d735670e2f3e30b0919708a81f9a0df9", "Flagged": false, "MoE": false @@ -64294,7 +84074,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 166.0, + "Hub \u2764\ufe0f": 176.0, "Available on the hub": true, "Model sha": "0a5752d096ebab21759dbe203f6b7c7f6092faf2", "Flagged": false, @@ -64432,7 +84212,7 @@ "Merged": false, "Hub License": "openrail", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 297.0, + "Hub \u2764\ufe0f": 302.0, "Available on the hub": true, "Model sha": "72efd71d7f89d9c46008b7a574faf90300ed9ba8", "Flagged": false, @@ -64455,7 +84235,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "e1c3840c716485077b688296fefa8e5641249843", "Flagged": false, @@ -64683,9 +84463,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 3.01, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "7564c055f9aaca4094e955b62f68975ec305d675", "Flagged": false, @@ -64800,7 +84580,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": false, "Model sha": "6d17c854025b0bd54ce572ac803f1bb052875dbf", "Flagged": false, @@ -64893,7 +84673,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1e74a9cca843cdeb8591d4e4f4320dc1870adf1b", "Flagged": false, "MoE": false @@ -64913,10 +84693,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "379cb8f080110f3418155029f534f67a79e25db4", "Flagged": false, "MoE": false @@ -64944,6 +84724,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "yys\/gemma-7B-it-firefly", + "Average \u2b06\ufe0f": 52.45, + "ARC": 48.29, + "HellaSwag": 71.59, + "MMLU": 52.99, + "TruthfulQA": 42.25, + "Winogrande": 67.88, + "GSM8K": 31.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a45132c4f73c4b6cbddf24b6df519381f3a1b66d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ausboss\/llama-13b-supercot", @@ -65054,7 +84857,7 @@ "Hub License": "?", "#Params (B)": 13.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4b5aabc51907e4cba49f373c6dc09a2634f2fb8a", "Flagged": false, "MoE": false @@ -65145,7 +84948,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 21.83, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "29222b05794abb862ad0aaaf3020696c9f599810", "Flagged": false, @@ -65168,7 +84971,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 3.01, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "11267fbddbe8652cff32c1f6c7e3e8ca2f48f28c", "Flagged": false, @@ -65214,7 +85017,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 271.0, + "Hub \u2764\ufe0f": 314.0, "Available on the hub": true, "Model sha": "e7298b35e5460a37b83fb0dc69eae03f46b49275", "Flagged": false, @@ -65307,7 +85110,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ac4218770a58baaaaf25201076fe082abb6ffd13", "Flagged": false, "MoE": false @@ -65350,10 +85153,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": null, + "Hub License": "llama2", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "189304f388007b3be70818d8f9842b4512faf310", "Flagged": false, "MoE": false @@ -65450,6 +85253,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "nnethercott\/llava-v1.5-7b_vicuna", + "Average \u2b06\ufe0f": 52.28, + "ARC": 52.65, + "HellaSwag": 76.09, + "MMLU": 51.68, + "TruthfulQA": 45.86, + "Winogrande": 72.06, + "GSM8K": 15.31, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d33e2a87f99380302bc77ac270630bd7fd23baaf", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "TFLai\/Platypus2-13B-QLoRA-0.80-epoch", @@ -65468,7 +85294,7 @@ "Hub License": "?", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "114eb8efd2de1c9eae85d92de490b95c854dfae9", "Flagged": false, "MoE": false @@ -65514,7 +85340,7 @@ "Hub License": "llama2", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "dffa41945e5bdac60bd7541ef775642a02189d15", "Flagged": false, "MoE": false @@ -65542,6 +85368,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "kalisai\/Nusantara-7b-Indo-Chat", + "Average \u2b06\ufe0f": 52.25, + "ARC": 48.55, + "HellaSwag": 72.84, + "MMLU": 52.03, + "TruthfulQA": 45.63, + "Winogrande": 69.53, + "GSM8K": 24.94, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e6e0dfe507ba70b5f33c1631cd67d35c6484a1cb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "beaugogh\/Llama2-7b-openorca-mc-v1", @@ -65767,7 +85616,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9c4a7444d6fb12931e50f111053e016531fe60b7", "Flagged": false, "MoE": false @@ -65790,7 +85639,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "86329885e029c1f4fb6ff6b6f3409007158499e7", "Flagged": false, "MoE": false @@ -65881,7 +85730,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 174.0, + "Hub \u2764\ufe0f": 207.0, "Available on the hub": true, "Model sha": "de56c35b1763eaae20f4d60efd64af0a9091ebe5", "Flagged": false, @@ -65948,10 +85797,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e92a1439ac8d2edb5e311b8a42e13ed7c5e70db5", "Flagged": false, "MoE": false @@ -65979,6 +85828,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/mistral-7B-alpaca-case-1-2", + "Average \u2b06\ufe0f": 52.01, + "ARC": 57.34, + "HellaSwag": 79.31, + "MMLU": 56.02, + "TruthfulQA": 44.58, + "Winogrande": 74.82, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8df8e9f61a0d5ca5a5d5e7418dc2f9eb348f916b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "wang7776\/Llama-2-7b-chat-hf-20-sparsity", @@ -66020,7 +85892,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cc5ee2231066c147423f89e9df40f7364c3275a5", "Flagged": false, "MoE": false @@ -66042,7 +85914,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 174.0, + "Hub \u2764\ufe0f": 207.0, "Available on the hub": true, "Model sha": "de56c35b1763eaae20f4d60efd64af0a9091ebe5", "Flagged": false, @@ -66065,7 +85937,7 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 100.0, + "Hub \u2764\ufe0f": 101.0, "Available on the hub": true, "Model sha": "4d70cf0047a7a5cd2c864bc2606e81f0830e4405", "Flagged": false, @@ -66094,6 +85966,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-general-temporal-merged", + "Average \u2b06\ufe0f": 51.98, + "ARC": 52.47, + "HellaSwag": 75.83, + "MMLU": 49.09, + "TruthfulQA": 47.06, + "Winogrande": 73.16, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2683a990206099178aab7e09cca5f330151c4e79", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "davzoku\/frankencria-llama2-11b-v1.3-m.1", @@ -66134,7 +86029,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "fdf075081555f3ed84c037e8dd3fe85c3b3609d7", "Flagged": false, @@ -66158,7 +86053,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "70e38a7424544193f0ad6a93ae26a5bfd15e4e90", "Flagged": false, "MoE": false @@ -66227,7 +86122,7 @@ "Hub License": "?", "#Params (B)": 6.06, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "925c5fbaeccb321ba8edbde79c3d994adc460a41", "Flagged": false, "MoE": false @@ -66274,7 +86169,7 @@ "mit" ], "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 61.0, + "Hub \u2764\ufe0f": 64.0, "Available on the hub": true, "Model sha": "60e58acecdc1552e1b1752a38d1d91d942d1c3f0", "Flagged": false, @@ -66343,7 +86238,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "4f9e95665d95b4c692910190ff77257216e476f1", "Flagged": false, @@ -66456,9 +86351,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "4a770caf3509b3fdda5ed54735dc40a8f0442c61", "Flagged": false, @@ -66487,6 +86382,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "LLMNewbie\/vic_critT_20pr", + "Average \u2b06\ufe0f": 51.75, + "ARC": 51.62, + "HellaSwag": 76.39, + "MMLU": 47.66, + "TruthfulQA": 51.93, + "Winogrande": 74.27, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 10.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8999e6a0bafae2926e2e6bf11cf92d32f276b3cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "XuanXuanXuanXuan\/Llama-2-7b-chat-hf-gpt-3.5-80k", + "Average \u2b06\ufe0f": 51.75, + "ARC": 52.05, + "HellaSwag": 73.89, + "MMLU": 48.19, + "TruthfulQA": 44.35, + "Winogrande": 71.98, + "GSM8K": 20.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3dac39a014a4535f0e5075f0cac0b0e0b4740b01", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "decruz07\/llama-2-7b-miniguanaco", @@ -66528,7 +86469,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6073a87872eb36149404bfb7d60e0108074ee1c3", "Flagged": false, "MoE": false @@ -66556,6 +86497,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TheSkullery\/Aurora_22e_Test", + "Average \u2b06\ufe0f": 51.71, + "ARC": 44.8, + "HellaSwag": 64.97, + "MMLU": 62.27, + "TruthfulQA": 50.91, + "Winogrande": 77.9, + "GSM8K": 9.4, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.04, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fc3d8910521ddb84053f0be970467b30da2cbe9d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jphme\/em_german_leo_mistral", @@ -66573,7 +86537,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 56.0, + "Hub \u2764\ufe0f": 61.0, "Available on the hub": true, "Model sha": "aa63a32154923034fb89b1408d3d7ffa994d3327", "Flagged": false, @@ -66626,7 +86590,7 @@ "MoE": false }, { - "T": "\ud83d\udd36", + "T": "\ud83d\udfe9", "Model": "TencentARC\/LLaMA-Pro-8B", "Average \u2b06\ufe0f": 51.67, "ARC": 53.75, @@ -66635,14 +86599,14 @@ "TruthfulQA": 38.86, "Winogrande": 74.19, "GSM8K": 17.82, - "Type": "fine-tuned on domain-specific datasets", + "Type": "continuously pretrained", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": false, "Hub License": "llama2", "#Params (B)": 8.36, - "Hub \u2764\ufe0f": 162.0, + "Hub \u2764\ufe0f": 165.0, "Available on the hub": true, "Model sha": "7a2b46875f68ca276562a44ea99b713d86ddb9f2", "Flagged": false, @@ -66689,7 +86653,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2491546f1219c3e9bb1a8cf37fbecf0b299c2177", "Flagged": false, "MoE": false @@ -66740,6 +86704,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "hongzoh\/Yi-6B_Open-Platypus-v2", + "Average \u2b06\ufe0f": 51.64, + "ARC": 49.91, + "HellaSwag": 72.18, + "MMLU": 57.59, + "TruthfulQA": 42.34, + "Winogrande": 71.98, + "GSM8K": 15.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7844a6dbde22616af0f0221d7f26af03ae6e39f1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "augmxnt\/shisa-base-7b-v1", @@ -66757,7 +86744,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.96, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "5aa465caca707816a4bb36b4980aef5d102d76fb", "Flagged": false, @@ -66803,7 +86790,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 95.0, + "Hub \u2764\ufe0f": 96.0, "Available on the hub": true, "Model sha": "2b099b2be0dafb2606ae9808c0f6183fe4bff7bc", "Flagged": false, @@ -66870,9 +86857,9 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "7928584c0329c3ed88915a823033908be90ba657", "Flagged": false, @@ -67033,7 +87020,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "f9c59fdc14c42d1a84539e4195335da0a10af955", "Flagged": false, @@ -67062,6 +87049,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "deepseek-ai\/deepseek-math-7b-instruct", + "Average \u2b06\ufe0f": 51.48, + "ARC": 53.58, + "HellaSwag": 71.53, + "MMLU": 56.55, + "TruthfulQA": 40.38, + "Winogrande": 65.98, + "GSM8K": 20.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "0a5828f800a36df0fd7f0ed581b983246c0677ff", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "elliotthwang\/Elliott-Chinese-LLaMa-GPTQ-V2.0", @@ -67171,7 +87181,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 412.0, + "Hub \u2764\ufe0f": 417.0, "Available on the hub": true, "Model sha": "23486089ab7ba741b34adc69ab7555885f8abe71", "Flagged": false, @@ -67263,7 +87273,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": false, "Model sha": "762ecb0d85572c8f8bcbca06d27f7f64a4d74615", "Flagged": false, @@ -67355,7 +87365,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 75.0, "Available on the hub": true, "Model sha": "1f30e4f2037e1e30122667639b8ef37138e85057", "Flagged": false, @@ -67378,7 +87388,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 147.0, + "Hub \u2764\ufe0f": 148.0, "Available on the hub": true, "Model sha": "d120381b03051b60a7c77ec3fb1be6c3c1546466", "Flagged": false, @@ -67401,7 +87411,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "10fe70fec0df5c4dcbdfd2e9ec74830c41b3cfd2", "Flagged": false, @@ -67470,7 +87480,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 127.0, + "Hub \u2764\ufe0f": 130.0, "Available on the hub": true, "Model sha": "bf57045473f207bb1de1ed035ace226f4d9f9bba", "Flagged": false, @@ -67522,6 +87532,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "selfrag\/selfrag_llama2_7b", + "Average \u2b06\ufe0f": 51.3, + "ARC": 51.45, + "HellaSwag": 78.48, + "MMLU": 52.0, + "TruthfulQA": 41.73, + "Winogrande": 73.16, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "190261383b0779ff66d2f95a73c7ad267d94b820", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "leonarad\/hope_for", + "Average \u2b06\ufe0f": 51.3, + "ARC": 51.28, + "HellaSwag": 74.74, + "MMLU": 51.56, + "TruthfulQA": 40.73, + "Winogrande": 72.61, + "GSM8K": 16.91, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8a5c594dbd9b000a00ed26c96e5cda964afe5935", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Tap-M\/Luna-AI-Llama2-Uncensored", @@ -67539,7 +87595,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 121.0, + "Hub \u2764\ufe0f": 126.0, "Available on the hub": true, "Model sha": "6b5e1067e412cc5750aec7415a065671df3618be", "Flagged": false, @@ -67769,7 +87825,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "5e66b59c145586266b2351a63f0cf1b4f62f5454", "Flagged": false, @@ -67798,6 +87854,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Joseph717171\/Tess-10.7B-v2.0", + "Average \u2b06\ufe0f": 51.18, + "ARC": 55.12, + "HellaSwag": 74.4, + "MMLU": 50.09, + "TruthfulQA": 44.63, + "Winogrande": 65.27, + "GSM8K": 17.59, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "39dcb3ee299f888a3c3668e0ee4e6532cf1bf161", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "klyang\/MentaLLaMA-chat-7B", @@ -67844,6 +87923,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "leonarad\/hope_for_7b_1.0v", + "Average \u2b06\ufe0f": 51.16, + "ARC": 50.43, + "HellaSwag": 76.44, + "MMLU": 49.68, + "TruthfulQA": 38.66, + "Winogrande": 75.22, + "GSM8K": 16.53, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c5382de58d8be5d79689b9a1f0dcdea72e8b45ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "moondriller\/llama2-13B-eugeneparkthebest", + "Average \u2b06\ufe0f": 51.15, + "ARC": 53.41, + "HellaSwag": 79.25, + "MMLU": 48.28, + "TruthfulQA": 44.42, + "Winogrande": 73.32, + "GSM8K": 8.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.16, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8e0740c8f0a61903c563126bc45d0e9a16547742", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "64bits\/LexPodLM-13B", @@ -67884,7 +88009,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 173.0, + "Hub \u2764\ufe0f": 202.0, "Available on the hub": true, "Model sha": "4c3bc725f71898c6a1acd4ea98a2f8d74d1b1b6b", "Flagged": false, @@ -67936,6 +88061,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ericpolewski\/AIRIC-The-Intern", + "Average \u2b06\ufe0f": 51.13, + "ARC": 52.73, + "HellaSwag": 77.07, + "MMLU": 51.92, + "TruthfulQA": 52.67, + "Winogrande": 70.88, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 20.09, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0b8e768b81fd4718dbd9155becf2c8592704e7e4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "chargoddard\/llama-2-26b-trenchcoat-stack", @@ -68022,7 +88170,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 48.0, + "Hub \u2764\ufe0f": 51.0, "Available on the hub": true, "Model sha": "983f8ad5c156f4a0e4d2b7b5f1146981ad2e8a8b", "Flagged": false, @@ -68066,9 +88214,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "12ab9aed495d8129856fdc469ce3ec672c94e6a3", "Flagged": false, @@ -68115,7 +88263,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "730cbd8f3077f3d24001aab714def991f1e4e7e8", "Flagged": false, "MoE": false @@ -68137,7 +88285,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "503725445dc3bd0377948b3042bda80fc957f85e", "Flagged": false, @@ -68158,9 +88306,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "other", "#Params (B)": 16.38, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 68.0, "Available on the hub": true, "Model sha": "521d2bc4fb69a3f3ae565310fcc3b65f97af2580", "Flagged": false, @@ -68299,11 +88447,34 @@ "Hub License": "?", "#Params (B)": 12.97, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "484c8a18b02f95eb2b6f6302105cf9a329e76ec8", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "deepseek-ai\/deepseek-math-7b-instruct", + "Average \u2b06\ufe0f": 51.03, + "ARC": 53.41, + "HellaSwag": 71.5, + "MMLU": 55.97, + "TruthfulQA": 40.16, + "Winogrande": 65.75, + "GSM8K": 19.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "0a5828f800a36df0fd7f0ed581b983246c0677ff", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "wang7776\/vicuna-7b-v1.3-sparsity-10", @@ -68390,12 +88561,35 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "4e5fa9ae7f572b4841b02c3f96d8a3c7a7e59521", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/llama2-MultiLoRA-sharegpt-mmlu-drop-ffn-1.0general", + "Average \u2b06\ufe0f": 50.98, + "ARC": 53.16, + "HellaSwag": 78.59, + "MMLU": 46.89, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 14.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "33c7717bb3fdfcb3560b0c7c793e5efa6050a392", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Norquinal\/llama-2-7b-claude-chat", @@ -68413,7 +88607,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": false, "Model sha": "e65d34ed31cdcd2637f6284aa0605f30ef5a9381", "Flagged": false, @@ -68459,8 +88653,8 @@ "Merged": false, "Hub License": null, "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 1134.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1261.0, + "Available on the hub": true, "Model sha": "e8f058fa738b6b308540024e9aa12e274e291f75", "Flagged": false, "MoE": false @@ -68483,7 +88677,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5d8e7e5764ace89e6ccd1deece33b0e8a4b4587b", "Flagged": false, "MoE": false @@ -68511,6 +88705,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "maldv\/SHRDFU-7b-delta", + "Average \u2b06\ufe0f": 50.95, + "ARC": 54.18, + "HellaSwag": 77.55, + "MMLU": 55.95, + "TruthfulQA": 46.74, + "Winogrande": 71.27, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bff4000568782b3d5480cbb072c529861887c622", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "dfurman\/llama-2-7b-instruct-peft", @@ -68529,7 +88746,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0fc43413117187e0723cdac133068ab527c80fe2", "Flagged": false, "MoE": false @@ -68552,7 +88769,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bc8c239cacf1e3211f05e27be67a74d84c12aea9", "Flagged": false, "MoE": false @@ -68577,7 +88794,7 @@ "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "163a5bec7b6f5aaa4667aa6a95746deff50ceab1", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -68620,7 +88837,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.91, - "Hub \u2764\ufe0f": 50.0, + "Hub \u2764\ufe0f": 70.0, "Available on the hub": true, "Model sha": "2a050a4c59d687a85324d32e147517992117ed30", "Flagged": false, @@ -68649,6 +88866,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Covasna-0.1", + "Average \u2b06\ufe0f": 50.87, + "ARC": 48.81, + "HellaSwag": 70.07, + "MMLU": 61.9, + "TruthfulQA": 52.64, + "Winogrande": 70.8, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 41.6, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4f14f0584f79adc679d119f09bc69430d42babc1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-Llama2-13b-v1.0", + "Average \u2b06\ufe0f": 50.85, + "ARC": 51.45, + "HellaSwag": 78.57, + "MMLU": 50.99, + "TruthfulQA": 45.17, + "Winogrande": 74.35, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.26, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d946d79639945ec467eae0029696c7af39f15c6e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-l2-13b-2.1", @@ -68690,7 +88953,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ba8e755feab0bbf90675dcb9f8875a42f92112a5", "Flagged": false, "MoE": false @@ -68759,7 +89022,7 @@ "Hub License": "?", "#Params (B)": 12.97, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f87d66f9c4541c575a6fad3c19a31b11568e0dfb", "Flagged": false, "MoE": false @@ -68782,7 +89045,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f98bb987216448aa3aa89e575a7494fae8b68066", "Flagged": false, "MoE": false @@ -68804,8 +89067,8 @@ "Merged": false, "Hub License": null, "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 2867.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 3250.0, + "Available on the hub": true, "Model sha": "b7701a9e825e79a5ab18b5801be113c2160cc627", "Flagged": false, "MoE": false @@ -68825,7 +89088,7 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -68917,7 +89180,7 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -68925,6 +89188,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Replete-AI\/Phi-5B-Test", + "Average \u2b06\ufe0f": 50.71, + "ARC": 54.61, + "HellaSwag": 67.6, + "MMLU": 54.31, + "TruthfulQA": 45.66, + "Winogrande": 71.98, + "GSM8K": 10.08, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 5.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "11cfbf1032e08ec542eb6ab577d17ac18039b731", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "vikash06\/doctorLLM10k", @@ -68963,7 +89249,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -69032,7 +89318,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "bigscience-openrail-m", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -69063,6 +89349,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "XuanXuanXuanXuan\/Llama-2-7b-hf-llama2-raw-80k", + "Average \u2b06\ufe0f": 50.65, + "ARC": 53.41, + "HellaSwag": 78.62, + "MMLU": 46.26, + "TruthfulQA": 38.82, + "Winogrande": 74.66, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f95d50673d3ed6bc65fda776997dbe9069bad1ed", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "vonjack\/Qwen-LLaMAfied-HFTok-7B-Chat", @@ -69155,6 +89464,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "XuanXuanXuanXuan\/Llama-2-7b-hf-gpt-3.5-80k", + "Average \u2b06\ufe0f": 50.63, + "ARC": 53.84, + "HellaSwag": 75.75, + "MMLU": 46.0, + "TruthfulQA": 41.42, + "Winogrande": 72.14, + "GSM8K": 14.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4a1647074aeb3894032fd3dfc5a9f4b214c415bb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "DopeorNope\/LaOT", @@ -69170,14 +89502,37 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "df3a2c77a63a370405c7711b323e7ffa550cdd9e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Llama-2-7b-hf-gpt-3.5-80k", + "Average \u2b06\ufe0f": 50.62, + "ARC": 53.84, + "HellaSwag": 75.77, + "MMLU": 45.98, + "TruthfulQA": 41.42, + "Winogrande": 72.06, + "GSM8K": 14.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "470a75ef677ce4e05306678cdac2174dbbf234e6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "zarakiquemparte\/zaraxls-l2-7b", @@ -69264,7 +89619,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": false, "Model sha": "e26ca5f157c60fc527170cc04db7fc0ea04ad26f", "Flagged": false, @@ -69380,7 +89735,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9d49378c69c00113cf7f6e66d1ddb9d9b003dddc", "Flagged": false, "MoE": false @@ -69402,7 +89757,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "80064d11c557eb1e0ddb52ed060d0e152c764c7c", "Flagged": false, @@ -69445,14 +89800,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 11.07, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "fbc4cdb251bf62307529a45f5ad267eb259761cc", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -69471,7 +89826,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "4157d696bb0015da3ba26a58c1d24925515e4125", "Flagged": false, @@ -69491,7 +89846,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, @@ -69500,6 +89855,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Nekochu\/Luminia-13B-v3", + "Average \u2b06\ufe0f": 50.46, + "ARC": 52.47, + "HellaSwag": 76.08, + "MMLU": 53.6, + "TruthfulQA": 43.74, + "Winogrande": 72.61, + "GSM8K": 4.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "602563f3af32b3c6be067ad522e6f3eaff4f8627", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "WizardLM\/WizardCoder-Python-34B-V1.0", @@ -69517,7 +89895,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 726.0, + "Hub \u2764\ufe0f": 742.0, "Available on the hub": true, "Model sha": "5cdc34e4a81d202f1d4a3b5d60e028aab895dfeb", "Flagged": false, @@ -69537,7 +89915,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, @@ -69632,7 +90010,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 477.0, + "Hub \u2764\ufe0f": 478.0, "Available on the hub": false, "Model sha": "6a571f458cab9a23d14324ec63e0abd1744c8353", "Flagged": false, @@ -69747,7 +90125,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 201.0, + "Hub \u2764\ufe0f": 202.0, "Available on the hub": false, "Model sha": "24fb8e1e9cc78e0aa7ef154b026c4a83296e3fc4", "Flagged": false, @@ -69755,7 +90133,7 @@ }, { "T": "\ud83d\udd36", - "Model": "Ejafa\/vicuna_7B_vanilla_1.1", + "Model": "eachadea\/vicuna-7b-1.1", "Average \u2b06\ufe0f": 50.37, "ARC": 53.67, "HellaSwag": 77.46, @@ -69768,17 +90146,17 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 2.0, - "Available on the hub": false, - "Model sha": "d971d788db19648ad16bf77ec3f1de35ebf9a8e0", + "Hub \u2764\ufe0f": 108.0, + "Available on the hub": true, + "Model sha": "9d8eea215e00b388a22e8f050768ea8911d41f1d", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "eachadea\/vicuna-7b-1.1", + "Model": "Ejafa\/vicuna_7B_vanilla_1.1", "Average \u2b06\ufe0f": 50.37, "ARC": 53.67, "HellaSwag": 77.46, @@ -69791,11 +90169,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 109.0, - "Available on the hub": true, - "Model sha": "9d8eea215e00b388a22e8f050768ea8911d41f1d", + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "d971d788db19648ad16bf77ec3f1de35ebf9a8e0", "Flagged": false, "MoE": false }, @@ -69814,10 +90192,10 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, "Model sha": "dc71924cfb214b91461d35178e6ea6fef7946f13", "Flagged": false, "MoE": false @@ -69837,10 +90215,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1e1709818cca48af4cd31c07c493f996854aa10f", "Flagged": false, "MoE": false @@ -69891,6 +90269,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Llama-2-7b-chat-hf-gpt-3.5-80k-base_lora", + "Average \u2b06\ufe0f": 50.3, + "ARC": 51.45, + "HellaSwag": 69.38, + "MMLU": 48.37, + "TruthfulQA": 46.62, + "Winogrande": 67.4, + "GSM8K": 18.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c975887e34bc74105f8efbded1102c82065de35b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "willnguyen\/lacda-2-7B-chat-v0.1", @@ -69909,7 +90310,7 @@ "Hub License": "llama2", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "afca346816726b83e331bb4d93246ed5146e1675", "Flagged": false, "MoE": false @@ -69931,7 +90332,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.18, - "Hub \u2764\ufe0f": 30.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "8f2f500574cd3c2972f05b7ae6e2807819cce051", "Flagged": false, @@ -69952,9 +90353,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 3.02, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "21c18e02cbd8becf5cb48eaff485379b6d62a2cd", "Flagged": false, @@ -69977,7 +90378,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "579271bebb894d89369205060d151120a217ce81", "Flagged": false, @@ -70046,12 +90447,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 31.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "886af9601d57d8675c09bab02144b68366cd4437", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "TheSkullery\/Aurora-V2-DLEC", + "Average \u2b06\ufe0f": 50.23, + "ARC": 47.7, + "HellaSwag": 69.46, + "MMLU": 52.68, + "TruthfulQA": 51.99, + "Winogrande": 69.61, + "GSM8K": 9.93, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.13, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "af67dd0bf327bbf687a024d47095bc9dac6f6b58", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "vishesht27\/22-Neuro_Model", @@ -70066,11 +90490,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "807caffa6064420c088fadb9f2d34012da6b3236", "Flagged": false, "MoE": false @@ -70093,7 +90517,7 @@ "Hub License": "?", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c2defe28e2f3f10460baf8f778b00986a53aa7a2", "Flagged": false, "MoE": false @@ -70167,6 +90591,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "leonarad\/hope_for_7b_1.1v", + "Average \u2b06\ufe0f": 50.19, + "ARC": 49.49, + "HellaSwag": 75.08, + "MMLU": 48.49, + "TruthfulQA": 40.26, + "Winogrande": 73.64, + "GSM8K": 14.18, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "30361b72ced8acd7cf96ddd136f70407d66ab92e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "RatanRohith\/SRBOSGPT-7B-slerp", @@ -70181,8 +90628,8 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -70213,6 +90660,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "hongzoh\/Yi-6B_Open-Orca", + "Average \u2b06\ufe0f": 50.18, + "ARC": 51.19, + "HellaSwag": 69.6, + "MMLU": 58.06, + "TruthfulQA": 38.63, + "Winogrande": 70.4, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b4918ab9c4fe63dfc38871ecaf59bea7c38a2d9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BFauber\/lora_llama2-7b_10e5", @@ -70253,7 +90723,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 26.0, "Available on the hub": true, "Model sha": "6798d9501a71b203be0610e640ec92fc08ea8dc6", "Flagged": false, @@ -70346,7 +90816,7 @@ "Hub License": "?", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c2defe28e2f3f10460baf8f778b00986a53aa7a2", "Flagged": false, "MoE": false @@ -70368,7 +90838,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 157.0, + "Hub \u2764\ufe0f": 160.0, "Available on the hub": true, "Model sha": "35696b9a7ab330dcbe240ff76fb44ab1eccf45bf", "Flagged": false, @@ -70420,6 +90890,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "stabilityai\/stablelm-2-zephyr-1_6b", + "Average \u2b06\ufe0f": 49.99, + "ARC": 43.69, + "HellaSwag": 69.3, + "MMLU": 42.03, + "TruthfulQA": 45.11, + "Winogrande": 64.48, + "GSM8K": 35.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "StableLmForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.64, + "Hub \u2764\ufe0f": 149.0, + "Available on the hub": true, + "Model sha": "c89d7d19e9781974793a7e9b0fe55bcabcf8abc5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "dhmeltzer\/llama-7b-SFT-qlora-eli5-wiki_DPO_ds_RM_top_2_1024_r_64_alpha_16", @@ -70435,10 +90928,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f1f3b9fdb1e2d8d8fa913d57a8fe15d7bdf72c20", "Flagged": false, "MoE": false @@ -70460,7 +90953,7 @@ "Merged": true, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "828ccce85f9dd3744a9438f140ffb8c06187d165", "Flagged": false, @@ -70506,7 +90999,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "f784afa7887b0738d92ea470797582756f02e630", "Flagged": false, @@ -70575,7 +91068,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "cb0b04b1bff7921614efbd87d5b87bac04c58d13", "Flagged": false, @@ -70621,7 +91114,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "96a9fbe5aaef8410a8d0dad25f3cc97b408c4efb", "Flagged": false, @@ -70736,7 +91229,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 3.95, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "39785f4cca88485960fb2eefe9845fa17a614d6d", "Flagged": false, @@ -70783,7 +91276,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "15b2fa81418792841014f589e61d1d9e30457040", "Flagged": false, "MoE": false @@ -70857,6 +91350,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Llama-2-7b-chat-hf-gpt-4-80k-base_lora", + "Average \u2b06\ufe0f": 49.86, + "ARC": 52.56, + "HellaSwag": 71.37, + "MMLU": 48.34, + "TruthfulQA": 48.22, + "Winogrande": 66.61, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d5109138b21f252053aebbd2c469fdcab6116b93", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Charlie911\/MultiLoRA-llama2-mmlu", @@ -70875,7 +91391,7 @@ "Hub License": "llama2", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "5cd015af30f8676b65320c8e597f12389aa4c576", "Flagged": false, "MoE": false @@ -70897,7 +91413,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "48fca4ba1e2d31ff4fbe6856b9b93ad2d97da8b7", "Flagged": false, @@ -70966,7 +91482,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 44.0, + "Hub \u2764\ufe0f": 47.0, "Available on the hub": true, "Model sha": "06dbd3e0da08255c575e585cb82e0554c1d2707a", "Flagged": false, @@ -70989,7 +91505,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 48.0, + "Hub \u2764\ufe0f": 49.0, "Available on the hub": true, "Model sha": "48fa08b3098a23d3671e09565499a4cfbaff1923", "Flagged": false, @@ -71012,7 +91528,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 119.0, + "Hub \u2764\ufe0f": 121.0, "Available on the hub": false, "Model sha": "ac066c83424c4a7221aa10c0ebe074b24d3bcdb6", "Flagged": false, @@ -71020,7 +91536,7 @@ }, { "T": "\ud83d\udd36", - "Model": "undi95\/llama2-to-mistral-diff", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v4", "Average \u2b06\ufe0f": 49.78, "ARC": 53.41, "HellaSwag": 78.56, @@ -71029,21 +91545,21 @@ "Winogrande": 74.03, "GSM8K": 7.51, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", - "Weight type": "Adapter", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", - "#Params (B)": 0.0, + "Hub License": "", + "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "16c279c5e7d12b8a6ff7771881808ef253a406b9", + "Available on the hub": false, + "Model sha": "405c54ec7aea0735996ef5ff6ede6c35ab930381", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v4", + "Model": "undi95\/llama2-to-mistral-diff", "Average \u2b06\ufe0f": 49.78, "ARC": 53.41, "HellaSwag": 78.56, @@ -71052,15 +91568,15 @@ "Winogrande": 74.03, "GSM8K": 7.51, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", + "Architecture": "Unknown", + "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "", - "#Params (B)": 6.74, + "Hub License": "?", + "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "405c54ec7aea0735996ef5ff6ede6c35ab930381", + "Model sha": "16c279c5e7d12b8a6ff7771881808ef253a406b9", "Flagged": false, "MoE": false }, @@ -71079,10 +91595,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "26626ea669172be6bc8e6b2b0bc5f14aef8061aa", "Flagged": false, "MoE": false @@ -71148,7 +91664,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -71173,7 +91689,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "c7e776f3f3afc0fa22cb7aff0d00522e571e9b29", "Flagged": false, @@ -71220,7 +91736,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ebe2e68699cb7ab6bb22688f265c89be2ac0fa6d", "Flagged": false, "MoE": false @@ -71273,7 +91789,7 @@ }, { "T": "\ud83d\udd36", - "Model": "TaylorAI\/Flash-Llama-7B", + "Model": "NewstaR\/Starlight-7B", "Average \u2b06\ufe0f": 49.73, "ARC": 53.07, "HellaSwag": 78.57, @@ -71286,11 +91802,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "other", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 1.0, - "Available on the hub": false, - "Model sha": "27c84ef23d850582453e1cc2dcea13de48da090f", + "Available on the hub": true, + "Model sha": "1f7436c458ebc3d8d31b91091c1a7a48e942cd3b", "Flagged": false, "MoE": false }, @@ -71319,7 +91835,7 @@ }, { "T": "\ud83d\udd36", - "Model": "NewstaR\/Starlight-7B", + "Model": "TaylorAI\/Flash-Llama-7B", "Average \u2b06\ufe0f": 49.73, "ARC": 53.07, "HellaSwag": 78.57, @@ -71332,11 +91848,11 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", + "Hub License": "", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "1f7436c458ebc3d8d31b91091c1a7a48e942cd3b", + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "27c84ef23d850582453e1cc2dcea13de48da090f", "Flagged": false, "MoE": false }, @@ -71381,11 +91897,34 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "67f2e8af850049a86fb9ee8ef581deb0f51e58e6", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "vitruv\/vitruv_1", + "Average \u2b06\ufe0f": 49.71, + "ARC": 49.91, + "HellaSwag": 76.05, + "MMLU": 48.21, + "TruthfulQA": 41.23, + "Winogrande": 71.59, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1bf67cd0e4e1fd3bb753b51e693a7e11a3c240ec", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "dhmeltzer\/Llama-2-7b-hf-eli5-cleaned-wiki65k-1024_qlora_merged", @@ -71450,7 +91989,7 @@ "Hub License": "apache-2.0", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "9280900648e021d222ebba3689e663d31227d9a1", "Flagged": false, "MoE": false @@ -71470,10 +92009,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9c74b9396ff6b33e7a7622e59aa1f46103d993fe", "Flagged": false, "MoE": false @@ -71518,7 +92057,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 192.0, + "Hub \u2764\ufe0f": 285.0, "Available on the hub": true, "Model sha": "e9a972b12c6b59bfbcf30fe3779c2c933ce755bd", "Flagged": false, @@ -71541,7 +92080,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 34.0, + "Hub \u2764\ufe0f": 35.0, "Available on the hub": true, "Model sha": "a118d2c35573b9a70c6f5b56fba4b657f74ce00c", "Flagged": false, @@ -71564,7 +92103,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 15.52, - "Hub \u2764\ufe0f": 250.0, + "Hub \u2764\ufe0f": 256.0, "Available on the hub": true, "Model sha": "b1bcda690655777373f57ea6614eb095ec2c886f", "Flagged": false, @@ -71587,7 +92126,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 157.0, + "Hub \u2764\ufe0f": 160.0, "Available on the hub": true, "Model sha": "b050a6f17d46e32c4b90a30492f14746589f74b7", "Flagged": false, @@ -71633,7 +92172,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "699491e2e73cc2936205db143f59c1a686b88f14", "Flagged": false, @@ -71679,7 +92218,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "b62f431c88b232204ea7046f9d906ae1daa68437", "Flagged": false, @@ -71708,6 +92247,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/autotrain-8kfjk-b3gva", + "Average \u2b06\ufe0f": 49.59, + "ARC": 50.0, + "HellaSwag": 70.79, + "MMLU": 51.09, + "TruthfulQA": 43.49, + "Winogrande": 63.38, + "GSM8K": 18.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c576dc972d25f57084ed8c80afdae74742eacbda", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "malhajar\/meditron-7b-chat", @@ -71725,7 +92287,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "b2e32b581d1484c831654fb2c03d2d29e7f520d7", "Flagged": false, @@ -71846,6 +92408,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/autotrain-8kfjk-b3gva", + "Average \u2b06\ufe0f": 49.54, + "ARC": 50.17, + "HellaSwag": 70.84, + "MMLU": 51.15, + "TruthfulQA": 43.43, + "Winogrande": 63.46, + "GSM8K": 18.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c576dc972d25f57084ed8c80afdae74742eacbda", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jb723\/llama2-ko-7B-model", @@ -71864,7 +92449,7 @@ "Hub License": "?", "#Params (B)": 6.67, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "03d23910fa0f9b0542ce7634cbcd36983321f55a", "Flagged": false, "MoE": false @@ -71887,7 +92472,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "142e198df473fd0cd4370b0d50be5f57e1da399b", "Flagged": false, "MoE": false @@ -71961,6 +92546,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "JCX-kcuf\/Llama-2-7b-hf-llama2-chat-80k", + "Average \u2b06\ufe0f": 49.49, + "ARC": 53.84, + "HellaSwag": 74.65, + "MMLU": 46.36, + "TruthfulQA": 39.06, + "Winogrande": 71.03, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "945429e199de13ccd374ba7e1d351c9a2d5fe561", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "rombodawg\/Everyone-Coder-33b-Base", @@ -72030,6 +92638,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "sambanovasystems\/SambaLingo-Thai-Chat", + "Average \u2b06\ufe0f": 49.45, + "ARC": 52.73, + "HellaSwag": 78.42, + "MMLU": 43.95, + "TruthfulQA": 40.84, + "Winogrande": 72.22, + "GSM8K": 8.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.95, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "fbe817bea4967720268af0e5793000b109147bde", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "adamo1139\/LWM-7B-1M-1000000ctx-AEZAKMI-3_1-1702", @@ -72094,7 +92725,7 @@ "Hub License": "llama2", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "f023eda0d38152e826136ecb988e8d2bdcc6f46c", "Flagged": false, "MoE": false @@ -72162,7 +92793,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 59.0, + "Hub \u2764\ufe0f": 62.0, "Available on the hub": true, "Model sha": "f0a3613c5da62cbe85fb90ea348932ddfc022b22", "Flagged": false, @@ -72277,7 +92908,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": false, "Model sha": "7c343a501f5cd3b768d2f78d9941b760fd66815d", "Flagged": false, @@ -72300,7 +92931,7 @@ "Merged": false, "Hub License": "openrail", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "9af636df9c8693ea857b62442bd1c6c73d657dc6", "Flagged": false, @@ -72413,9 +93044,9 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 6.61, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "0ae2abdc539a79ad84b141f894d614adf3754882", "Flagged": false, @@ -72507,7 +93138,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 64.0, + "Hub \u2764\ufe0f": 65.0, "Available on the hub": true, "Model sha": "89de33d1ad568855853196802aeaecd799c6586f", "Flagged": false, @@ -72530,7 +93161,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 43.0, + "Hub \u2764\ufe0f": 44.0, "Available on the hub": true, "Model sha": "227253877d67620f45c7b45ff22ead1dc6e03e4f", "Flagged": false, @@ -72576,7 +93207,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 306.0, + "Hub \u2764\ufe0f": 341.0, "Available on the hub": true, "Model sha": "594b9222df90074334697d0ed36ffeb3b478e9ba", "Flagged": false, @@ -72599,7 +93230,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "0715b738e750830ba7213f26fe32fa1cc1bb15b3", "Flagged": false, @@ -72720,6 +93351,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-Gemma-2b", + "Average \u2b06\ufe0f": 48.92, + "ARC": 48.72, + "HellaSwag": 71.41, + "MMLU": 42.9, + "TruthfulQA": 35.77, + "Winogrande": 67.96, + "GSM8K": 26.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "29075d62fc6ffe23c3c517aa9afe5c9fc1621b81", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "PotatoOff\/HamSter-0.2", @@ -72761,7 +93415,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "0b3ef975fb5e8ac1eae775160ab54c98221889df", "Flagged": false, "MoE": false @@ -72784,7 +93438,7 @@ "Hub License": "?", "#Params (B)": 6.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ab2476bffedeed752daedd77e71900578e136e7c", "Flagged": false, "MoE": false @@ -72898,12 +93552,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 69.0, + "Hub \u2764\ufe0f": 74.0, "Available on the hub": true, "Model sha": "acc26c54609e9f18bf31fc5d58b5b533239e0430", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/komodo-7b-chat", + "Average \u2b06\ufe0f": 48.74, + "ARC": 51.45, + "HellaSwag": 77.05, + "MMLU": 44.63, + "TruthfulQA": 40.05, + "Winogrande": 74.43, + "GSM8K": 4.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.76, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a255f2cf5038966136382b2d61c6258ae5b3b20a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Aspik101\/vicuna-7b-v1.3-instruct-pl-lora_unload", @@ -72990,7 +93667,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 65.0, + "Hub \u2764\ufe0f": 68.0, "Available on the hub": true, "Model sha": "976887c5891284db204320860bb84b71d598063e", "Flagged": false, @@ -73059,7 +93736,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "18d34bd9ad2d9674675b2e0d88dee9324b52f2b5", "Flagged": false, @@ -73083,7 +93760,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "efc7cbc5d0461c137e8ea0c83e54bc5357188783", "Flagged": false, "MoE": false @@ -73220,7 +93897,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "717edbee98945192b1a396fc9c337c5b32d6c79c", "Flagged": false, @@ -73289,7 +93966,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 9.05, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 77.0, "Available on the hub": true, "Model sha": "ecd7ab9f6adc36ecbe0d751eeea0d90ae1863c3b", "Flagged": false, @@ -73313,7 +93990,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9025c5f96fef9525da9238369ad082961b0e9494", "Flagged": false, "MoE": false @@ -73335,7 +94012,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 30.4, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "01b331f04153b84a4ac049e71fd122d891424756", "Flagged": false, @@ -73358,7 +94035,7 @@ "Merged": false, "Hub License": "cc", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 52.0, + "Hub \u2764\ufe0f": 56.0, "Available on the hub": true, "Model sha": "b57b9f5ff34059e485b769973d023021fc66a8f7", "Flagged": false, @@ -73451,7 +94128,7 @@ "Hub License": "?", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "1665b271316dfee05b2a8daf8b9d6c22ed0aef60", "Flagged": false, "MoE": false @@ -73525,6 +94202,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Herry443\/Mistral-7B-KNUT-ref-en", + "Average \u2b06\ufe0f": 48.27, + "ARC": 38.99, + "HellaSwag": 70.7, + "MMLU": 23.12, + "TruthfulQA": 48.93, + "Winogrande": 63.46, + "GSM8K": 44.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae87363a861afdf62bf6797b065beb8b749e9981", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/Wizard-Vicuna-7B-Uncensored", + "Average \u2b06\ufe0f": 48.27, + "ARC": 53.41, + "HellaSwag": 78.85, + "MMLU": 37.09, + "TruthfulQA": 43.48, + "Winogrande": 72.22, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1097285acd9c48a1d09bc0a9844d365384732111", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "TheBloke\/Wizard-Vicuna-7B-Uncensored-HF", @@ -73548,29 +94271,6 @@ "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udd36", - "Model": "ehartford\/Wizard-Vicuna-7B-Uncensored", - "Average \u2b06\ufe0f": 48.27, - "ARC": 53.41, - "HellaSwag": 78.85, - "MMLU": 37.09, - "TruthfulQA": 43.48, - "Winogrande": 72.22, - "GSM8K": 4.55, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", - "Weight type": "Original", - "Precision": "float16", - "Merged": false, - "Hub License": "?", - "#Params (B)": 6.61, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "1097285acd9c48a1d09bc0a9844d365384732111", - "Flagged": false, - "MoE": false - }, { "T": "\ud83d\udd36", "Model": "mayacinka\/frankencup-dpo", @@ -73585,11 +94285,11 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 14.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9248c7340053361655743f40acd4b9c1b5d0815d", "Flagged": false, "MoE": false @@ -73611,12 +94311,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 380.0, + "Hub \u2764\ufe0f": 395.0, "Available on the hub": true, "Model sha": "3bec1dcc7cb6f1895a923e66d87438e903bebb57", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "AtAndDev\/Ogno-Monarch-Neurotic-9B-Passthrough", + "Average \u2b06\ufe0f": 48.17, + "ARC": 46.25, + "HellaSwag": 56.06, + "MMLU": 62.92, + "TruthfulQA": 51.03, + "Winogrande": 72.77, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "96b43edd20bf553075e991cda3a8464fd65514f5", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Josephgflowers\/3BigReasonCinder", @@ -73655,10 +94378,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "883b0fa4158de8207d0a94f4b8cb188e6250aa9d", "Flagged": false, "MoE": false @@ -73677,7 +94400,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, + "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, @@ -73726,7 +94449,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 54.0, + "Hub \u2764\ufe0f": 55.0, "Available on the hub": false, "Model sha": "16deb633ef4d6a18d5750239edc5a85ffeaf3918", "Flagged": false, @@ -73818,7 +94541,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "d6317fed3b190cc4d4c27b9f27ccf7c77f0b2e3b", "Flagged": false, @@ -73842,7 +94565,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "81d424a431ab7fa4ff725925b6d0e4269d4563e4", "Flagged": false, "MoE": false @@ -73862,10 +94585,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d20419e1d9e9a6a59ced3edf5169e8e7b3e8394c", "Flagged": false, "MoE": false @@ -73887,7 +94610,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "65bbcb80158a6d2e133bba99a90142caf4e2e242", "Flagged": false, @@ -74002,7 +94725,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "c2497586b28f419ad12c734600d08b2a5784ddc1", "Flagged": false, @@ -74094,7 +94817,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 36.0, "Available on the hub": false, "Model sha": "ef97b878a279cd1765fbed7b8321fb3cff1aa5b5", "Flagged": false, @@ -74186,7 +94909,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 36.0, + "Hub \u2764\ufe0f": 40.0, "Available on the hub": false, "Model sha": "88c5ac07006ea8f1b5d10aa4f03f0d624dd27e56", "Flagged": false, @@ -74238,6 +94961,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "damerajee\/Gaja-v1.00", + "Average \u2b06\ufe0f": 47.69, + "ARC": 52.82, + "HellaSwag": 76.31, + "MMLU": 40.83, + "TruthfulQA": 44.64, + "Winogrande": 70.64, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c5583d6a15a238e6d28c889ab00bf659afd47ef3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "microsoft\/phi-1_5", @@ -74255,7 +95001,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 1.5, - "Hub \u2764\ufe0f": 1216.0, + "Hub \u2764\ufe0f": 1251.0, "Available on the hub": true, "Model sha": "ea95720a352172db6fcbcd89032bfb1cb8481797", "Flagged": false, @@ -74276,9 +95022,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "11a78fd948f70407f78b74fe599af572dbda15fc", "Flagged": false, @@ -74301,7 +95047,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "e326078aa122fb1c4973997952d7b8630071776a", "Flagged": false, @@ -74347,7 +95093,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "cdffb3488c5cb1a9aa5039a6b3bc72af24827db0", "Flagged": false, @@ -74437,10 +95183,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": false, "Model sha": "e3eb8bb0d8840431afe24760d964f8ba57edd83e", "Flagged": false, "MoE": false @@ -74462,12 +95208,35 @@ "Merged": false, "Hub License": null, "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 207.0, + "Hub \u2764\ufe0f": 210.0, "Available on the hub": false, "Model sha": "95be82087c33f14ee9941c812a154a9dd66efe72", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/gemma-2b-it-tamil-v0.1-alpha", + "Average \u2b06\ufe0f": 47.6, + "ARC": 50.09, + "HellaSwag": 71.41, + "MMLU": 39.94, + "TruthfulQA": 42.63, + "Winogrande": 64.96, + "GSM8K": 16.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c1279a2cb3396028129ea74a935c638cb7e3dc95", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Tensoic\/Kan-Llama-SFT-v0.5", @@ -74552,10 +95321,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b6b5c65c5c1cce34d24c8f790bb0cc011e0f0808", "Flagged": false, "MoE": false @@ -74624,7 +95393,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "165850882991d7fa4eabab577a03ed84e0713bfa", "Flagged": false, "MoE": false @@ -74670,7 +95439,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "082cf758aa3f6d8f956056003b5b3b6cde447d88", "Flagged": false, "MoE": false @@ -74761,7 +95530,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "293c24105fa15afa127a2ec3905fdc2a0a3a6dac", "Flagged": false, @@ -74807,15 +95576,15 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 449.0, + "Hub \u2764\ufe0f": 452.0, "Available on the hub": true, "Model sha": "b6d7fde8392250730d24cc2fcfa3b7e5f9a03ce8", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "rufjdk5480\/mixtral-ko-qna-merged", + "T": "\ud83d\udd36", + "Model": "rufjdk5480\/gov-qna-ko-merged", "Average \u2b06\ufe0f": 47.24, "ARC": 39.51, "HellaSwag": 39.06, @@ -74823,22 +95592,22 @@ "TruthfulQA": 48.61, "Winogrande": 56.75, "GSM8K": 27.67, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "810c90db1842f6c5f314f23b7549d58316e0db95", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "rufjdk5480\/gov-qna-ko-merged", + "T": "\ud83d\udcac", + "Model": "rufjdk5480\/mixtral-ko-qna-merged", "Average \u2b06\ufe0f": 47.24, "ARC": 39.51, "HellaSwag": 39.06, @@ -74846,7 +95615,7 @@ "TruthfulQA": 48.61, "Winogrande": 56.75, "GSM8K": 27.67, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", @@ -74854,7 +95623,7 @@ "Hub License": "?", "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "810c90db1842f6c5f314f23b7549d58316e0db95", "Flagged": false, "MoE": false @@ -74876,7 +95645,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 26.0, "Available on the hub": false, "Model sha": "c94f57239fed80eac0dc62507aee049681c799a1", "Flagged": false, @@ -74899,12 +95668,58 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 46.7, - "Hub \u2764\ufe0f": 33.0, + "Hub \u2764\ufe0f": 34.0, "Available on the hub": true, "Model sha": "ce4a4e4ffec063a3e338b6ebc328365270b6c5f0", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Cluj-Napoca-0.3", + "Average \u2b06\ufe0f": 47.22, + "ARC": 49.23, + "HellaSwag": 70.2, + "MMLU": 46.67, + "TruthfulQA": 47.13, + "Winogrande": 70.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 25.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eaa766e5186938eb27048347e0fdf52fd459a185", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Shiki-v2-m7", + "Average \u2b06\ufe0f": 47.21, + "ARC": 47.35, + "HellaSwag": 51.71, + "MMLU": 62.62, + "TruthfulQA": 61.98, + "Winogrande": 59.27, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4a635851e435669456ef761b134f53a6accee259", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "FelixChao\/CodeLlama13B-Finetune-v1", @@ -74928,6 +95743,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/gemma-2b-zephyr-sft", + "Average \u2b06\ufe0f": 47.18, + "ARC": 49.74, + "HellaSwag": 72.38, + "MMLU": 41.37, + "TruthfulQA": 34.42, + "Winogrande": 66.93, + "GSM8K": 18.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "31ba7c6d5ce2db815e874220a107cfa1e36c1e97", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "mosaicml\/mpt-7b-8k-instruct", @@ -74968,7 +95806,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "2f15bd8250d7825307e59cc2c785074ebbec3395", "Flagged": false, @@ -74991,7 +95829,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "2be40b8a7b669c4520bc04ce954bdbd7d4b0da7e", "Flagged": false, @@ -75014,7 +95852,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "24d98f339fabfa479e3c85404f5e4dda9e43dcd1", "Flagged": false, @@ -75037,7 +95875,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 498.0, + "Hub \u2764\ufe0f": 512.0, "Available on the hub": true, "Model sha": "aef6d8946ae1015bdb65c478a2dd73b58daaef47", "Flagged": false, @@ -75066,6 +95904,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "vicgalleorg\/TruthfulQwen1.5-1.8B", + "Average \u2b06\ufe0f": 47.02, + "ARC": 38.74, + "HellaSwag": 61.35, + "MMLU": 46.98, + "TruthfulQA": 40.58, + "Winogrande": 60.38, + "GSM8K": 34.12, + "Type": "base merges and moerges", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "56071d920b03a77d6ea95f97023663a976216de8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "damerajee\/Gaja-vv1", + "Average \u2b06\ufe0f": 47.02, + "ARC": 51.54, + "HellaSwag": 75.49, + "MMLU": 39.94, + "TruthfulQA": 42.32, + "Winogrande": 71.98, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2fda9f5ba3f3d89420ccf442446cf6d442d6cefd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "notstoic\/PygmalionCoT-7b", @@ -75089,6 +95973,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "damerajee\/Gaja-v2.00", + "Average \u2b06\ufe0f": 46.98, + "ARC": 51.79, + "HellaSwag": 75.79, + "MMLU": 40.69, + "TruthfulQA": 41.5, + "Winogrande": 71.9, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a32aaae72fae89719bb3f0f00350d9fa8a3b37cd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "mncai\/chatdoctor", @@ -75106,7 +96013,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": false, "Model sha": "8fdcfdda6877d7f21173dfac48b2c14499ba8264", "Flagged": false, @@ -75153,7 +96060,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "85aa4f67191fd016ab7ea8c389fddb5d9e5a9a52", "Flagged": false, "MoE": false @@ -75175,12 +96082,58 @@ "Merged": false, "Hub License": "other", "#Params (B)": 33.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 76.0, "Available on the hub": true, "Model sha": "e508c81aaf6b8bf8d1c7cbad5c9ddaed85fbb7dd", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/gemma-2b-zephyr-dpo", + "Average \u2b06\ufe0f": 46.92, + "ARC": 49.66, + "HellaSwag": 72.23, + "MMLU": 41.13, + "TruthfulQA": 34.47, + "Winogrande": 66.54, + "GSM8K": 17.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7e2818ec0fd8079c97adebe2bff990313fc0b92e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "damerajee\/Gaja-v2.00-dpo", + "Average \u2b06\ufe0f": 46.91, + "ARC": 51.71, + "HellaSwag": 75.87, + "MMLU": 40.79, + "TruthfulQA": 41.29, + "Winogrande": 71.59, + "GSM8K": 0.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "00fc1c19e31ae84eda0979468ed4a8ae31d5516d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-7b-gpt4-1.3", @@ -75244,7 +96197,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 3.95, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 25.0, "Available on the hub": true, "Model sha": "15bf46b13b1e6b6dd18ff7fa3242af406cc7e791", "Flagged": false, @@ -75265,10 +96218,10 @@ "Weight type": "Adapter", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7f4cbd810b4bef0d75c1fd3f551146b4ea97d9fd", "Flagged": false, "MoE": false @@ -75359,7 +96312,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 30.0, + "Hub \u2764\ufe0f": 34.0, "Available on the hub": true, "Model sha": "33950ffa68b9f8cd5dc2f046c6c9a2d0f0bf7eff", "Flagged": false, @@ -75383,7 +96336,7 @@ "Hub License": "?", "#Params (B)": 34.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c4e02a3a5c7a9d51f8b0cad85952dfdfb34c9413", "Flagged": false, "MoE": false @@ -75428,12 +96381,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.87, - "Hub \u2764\ufe0f": 72.0, + "Hub \u2764\ufe0f": 80.0, "Available on the hub": true, "Model sha": "2cbb156ab4426113115bc3387b06d1940015119a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-2-2", + "Average \u2b06\ufe0f": 46.63, + "ARC": 51.45, + "HellaSwag": 65.86, + "MMLU": 51.77, + "TruthfulQA": 45.12, + "Winogrande": 65.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "03e519df53f8bf918460b63c593d951d09403907", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "vikash06\/llama-2-7b-small-model-new", @@ -75472,10 +96448,10 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7f94b0be78193abc54722cf723541c3800426f7b", "Flagged": false, "MoE": false @@ -75497,7 +96473,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 2.8, - "Hub \u2764\ufe0f": 299.0, + "Hub \u2764\ufe0f": 305.0, "Available on the hub": true, "Model sha": "a4750ace0db6f08d7bbba0aa52a585f231ea3cde", "Flagged": false, @@ -75520,7 +96496,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 257.0, + "Hub \u2764\ufe0f": 258.0, "Available on the hub": false, "Model sha": "cc7773cac2478231807c56ef2f02292d98f85cf5", "Flagged": false, @@ -75543,7 +96519,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.84, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "921f88e4573192da5a10c809ed188603ea0f3937", "Flagged": false, @@ -75589,7 +96565,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.51, - "Hub \u2764\ufe0f": 426.0, + "Hub \u2764\ufe0f": 614.0, "Available on the hub": true, "Model sha": "b903623f4be99493dba7e415a6f6c7c609ecf674", "Flagged": false, @@ -75613,7 +96589,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "305683c1b95f6888b8668dbc6b56d9efa5d07fef", "Flagged": false, "MoE": false @@ -75658,7 +96634,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 30.0, + "Hub \u2764\ufe0f": 34.0, "Available on the hub": true, "Model sha": "33950ffa68b9f8cd5dc2f046c6c9a2d0f0bf7eff", "Flagged": false, @@ -75682,11 +96658,34 @@ "Hub License": "mit", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "a2b71eb940722a0a5597d62044ad2e5d37352a94", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "aloobun\/Synch-Qwen1.5-1.8B", + "Average \u2b06\ufe0f": 46.43, + "ARC": 36.95, + "HellaSwag": 60.19, + "MMLU": 44.82, + "TruthfulQA": 41.44, + "Winogrande": 61.25, + "GSM8K": 33.97, + "Type": "base merges and moerges", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5dede2620e5a01e039d3bdec9aa96b55610cd5b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "0x7194633\/fialka-7B-v3", @@ -75710,6 +96709,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "glenn2\/gemma-2b-lora3", + "Average \u2b06\ufe0f": 46.4, + "ARC": 47.27, + "HellaSwag": 71.83, + "MMLU": 38.04, + "TruthfulQA": 36.42, + "Winogrande": 67.25, + "GSM8K": 17.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6bb2412c1392c2caa989b15d61a14ea7210132f3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jerryjalapeno\/nart-100k-7b", @@ -75727,7 +96749,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": false, "Model sha": "50e61b8e6cc17cb3fbcb490fe3dc7e2c8b248378", "Flagged": false, @@ -75773,7 +96795,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 243.0, + "Hub \u2764\ufe0f": 253.0, "Available on the hub": true, "Model sha": "8416d3fefb0cb3ff5775a7b13c1692d10ff1aa16", "Flagged": false, @@ -75796,12 +96818,127 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.51, - "Hub \u2764\ufe0f": 426.0, + "Hub \u2764\ufe0f": 614.0, "Available on the hub": true, "Model sha": "9d067f00def958594aaa16b39a65b07d69ca655b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/OpenHermes-Gemma-2B", + "Average \u2b06\ufe0f": 46.36, + "ARC": 49.32, + "HellaSwag": 72.26, + "MMLU": 37.67, + "TruthfulQA": 41.69, + "Winogrande": 65.11, + "GSM8K": 12.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b21e7a0b55ceb868e48181071a18fe8d4179fa2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "glenn2\/gemma-2b-lora16b2", + "Average \u2b06\ufe0f": 46.35, + "ARC": 47.53, + "HellaSwag": 71.97, + "MMLU": 38.12, + "TruthfulQA": 36.45, + "Winogrande": 66.93, + "GSM8K": 17.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ef7b5be9df2cabbef92b3021ed16cc869e91c054", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JiheonJeong\/v1", + "Average \u2b06\ufe0f": 46.35, + "ARC": 48.29, + "HellaSwag": 71.74, + "MMLU": 41.78, + "TruthfulQA": 33.09, + "Winogrande": 66.22, + "GSM8K": 16.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "37a45681356a4e8ba769e34ae06e620a7990e7d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "JiheonJeong\/v1", + "Average \u2b06\ufe0f": 46.35, + "ARC": 48.12, + "HellaSwag": 71.6, + "MMLU": 41.83, + "TruthfulQA": 33.04, + "Winogrande": 66.06, + "GSM8K": 17.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "37a45681356a4e8ba769e34ae06e620a7990e7d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Menouar\/gemma-2b-chat-ultra", + "Average \u2b06\ufe0f": 46.35, + "ARC": 48.29, + "HellaSwag": 70.18, + "MMLU": 39.19, + "TruthfulQA": 39.07, + "Winogrande": 65.35, + "GSM8K": 16.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "56cbd4ec1d6dffe7651e9d5a4e34f584b8067627", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jondurbin\/airoboros-7b-gpt4-1.4.1-qlora", @@ -75842,7 +96979,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": false, "Model sha": "9fc1bc4409b9e71f54213245a91c2742fbf7b3d0", "Flagged": false, @@ -75917,6 +97054,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Menouar\/gemma-2b-chat", + "Average \u2b06\ufe0f": 46.2, + "ARC": 48.72, + "HellaSwag": 70.27, + "MMLU": 39.81, + "TruthfulQA": 38.79, + "Winogrande": 65.27, + "GSM8K": 14.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d6e530eee6c7c99a43a5794055854cef6b1e5876", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "YeungNLP\/firefly-llama2-7b-pretrain", @@ -75935,7 +97095,7 @@ "Hub License": "?", "#Params (B)": 6.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "444c85ef809f8793d84b0813ab78bec50700cfcf", "Flagged": false, "MoE": false @@ -75980,7 +97140,7 @@ "Merged": false, "Hub License": "cc-by-nc-nd-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "de4c7af9598bebc47dd43253c972be719f3195d6", "Flagged": false, @@ -76072,7 +97232,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 176.25, - "Hub \u2764\ufe0f": 4415.0, + "Hub \u2764\ufe0f": 4506.0, "Available on the hub": true, "Model sha": "053d9cd9fbe814e091294f67fcfedb3397b954bb", "Flagged": false, @@ -76101,6 +97261,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "NYTK\/PULI-LlumiX-32K", + "Average \u2b06\ufe0f": 46.05, + "ARC": 48.63, + "HellaSwag": 75.0, + "MMLU": 41.65, + "TruthfulQA": 36.93, + "Winogrande": 68.03, + "GSM8K": 6.07, + "Type": "continuously pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "80271481150d842bd15bbb830fa5197296e32c72", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "illuin\/test-custom-llama", @@ -76141,7 +97324,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 39.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": false, "Model sha": "6473f9996d758fde48a181f37cc5de575aff1606", "Flagged": false, @@ -76162,10 +97345,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8e1930bbbbdeb4f6f4639e837f09d9878bbf7831", "Flagged": false, "MoE": false @@ -76233,7 +97416,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.84, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "c754104ac85b9a598fb1f3c7b879af7f87a466ab", "Flagged": false, @@ -76308,6 +97491,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Cluj-Napoca-0.2", + "Average \u2b06\ufe0f": 45.91, + "ARC": 48.89, + "HellaSwag": 68.72, + "MMLU": 43.52, + "TruthfulQA": 44.77, + "Winogrande": 69.53, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 25.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "424f45c510410d6890a928d83061cea53dd078e8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "vikash06\/mistral_v1", @@ -76348,7 +97554,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 123.0, + "Hub \u2764\ufe0f": 128.0, "Available on the hub": true, "Model sha": "b9f91b7351ecd589118d883afa23d5c93a38c612", "Flagged": false, @@ -76400,6 +97606,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "sail\/Sailor-4B-Chat", + "Average \u2b06\ufe0f": 45.8, + "ARC": 45.05, + "HellaSwag": 68.36, + "MMLU": 43.96, + "TruthfulQA": 42.09, + "Winogrande": 66.22, + "GSM8K": 9.1, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "462e04484d1b1dd9c4dffe4f3d2d313e01a7abda", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "universitytehran\/PersianMind-v1.0", + "Average \u2b06\ufe0f": 45.78, + "ARC": 47.18, + "HellaSwag": 71.39, + "MMLU": 47.34, + "TruthfulQA": 41.37, + "Winogrande": 67.4, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 6.82, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "e8acab7aa7d8a5d242cb5fb071a5497c6d1d7377", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "fierysurf\/Kan-LLaMA-7B-SFT-v0.1-sharded", @@ -76446,9 +97698,78 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "M4-ai\/tau-1.8B", + "Average \u2b06\ufe0f": 45.73, + "ARC": 37.2, + "HellaSwag": 60.26, + "MMLU": 45.96, + "TruthfulQA": 39.72, + "Winogrande": 61.09, + "GSM8K": 30.17, + "Type": "continuously pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "8ed0d61c24c9297dd35ade2716717a45db9488d8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "ewqr2130\/llama2-7b-raw-sft", + "Model": "lqtrung1998\/Codellama-7b-hf-ReFT-GSM8k", + "Average \u2b06\ufe0f": 45.69, + "ARC": 43.52, + "HellaSwag": 64.53, + "MMLU": 40.86, + "TruthfulQA": 37.28, + "Winogrande": 64.25, + "GSM8K": 23.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a97add0e026abe7ef5c58e0af0ec79f39eb58876", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Replete-AI\/Phi-Stoma", + "Average \u2b06\ufe0f": 45.68, + "ARC": 48.46, + "HellaSwag": 60.29, + "MMLU": 51.53, + "TruthfulQA": 52.05, + "Winogrande": 61.72, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.82, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "60db09130992566859447366590a4c06256a737f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-7b-raw-sft", "Average \u2b06\ufe0f": 45.67, "ARC": 47.44, "HellaSwag": 75.25, @@ -76465,13 +97786,13 @@ "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "cd167d27b6c116b23863da859a07d08c6359c207", + "Model sha": "e1b241a26e35b87137fba8a54e352f1e4c98eebf", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "ewqr2130\/mistral-7b-raw-sft", + "Model": "ewqr2130\/llama2-7b-raw-sft", "Average \u2b06\ufe0f": 45.67, "ARC": 47.44, "HellaSwag": 75.25, @@ -76488,7 +97809,7 @@ "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "e1b241a26e35b87137fba8a54e352f1e4c98eebf", + "Model sha": "cd167d27b6c116b23863da859a07d08c6359c207", "Flagged": false, "MoE": false }, @@ -76532,7 +97853,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.51, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "33fa56fd6dde243144c8d6ed2e91830f43b69c15", "Flagged": false, @@ -76625,7 +97946,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e01d89d8e444f7d751ea58feaf22ff8c9af69d2a", "Flagged": false, "MoE": false @@ -76647,12 +97968,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "7fe5cb1a7009fdade8dfcfec335527997a730fcf", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "M4-ai\/Hercules-Mini-1.8B", + "Average \u2b06\ufe0f": 45.57, + "ARC": 37.03, + "HellaSwag": 59.53, + "MMLU": 44.77, + "TruthfulQA": 39.24, + "Winogrande": 62.27, + "GSM8K": 30.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1210ddfe213da00db50df5553e1c362e337af9e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-8", + "Average \u2b06\ufe0f": 45.56, + "ARC": 49.49, + "HellaSwag": 78.55, + "MMLU": 30.3, + "TruthfulQA": 37.58, + "Winogrande": 70.48, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36a32f6892c9e0b537b8560dd548b29fd5ccb86a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "yeontaek\/WizardCoder-Python-13B-LoRa", @@ -76762,7 +98129,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.87, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 24.0, "Available on the hub": true, "Model sha": "3fd8340a3683c8e7695c89a463428fcc0b2a875a", "Flagged": false, @@ -76791,6 +98158,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-5", + "Average \u2b06\ufe0f": 45.46, + "ARC": 48.38, + "HellaSwag": 78.51, + "MMLU": 29.52, + "TruthfulQA": 36.03, + "Winogrande": 71.82, + "GSM8K": 8.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7dc60a92b8836324e45efe6e6a769bdf5b964539", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Linly-AI\/Chinese-LLaMA-2-7B-hf", @@ -76808,7 +98198,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 27.0, + "Hub \u2764\ufe0f": 30.0, "Available on the hub": false, "Model sha": "a2d55220b3d0693825fe69e1174653dc6cc4a920", "Flagged": false, @@ -76854,7 +98244,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 501.0, + "Hub \u2764\ufe0f": 506.0, "Available on the hub": false, "Model sha": "64e5c9c9fb53a8e89690c2dee75a5add37f7113e", "Flagged": false, @@ -76875,14 +98265,37 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a7749ff092ef03900de34b69d41c767a6a48ea9e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-0", + "Average \u2b06\ufe0f": 45.38, + "ARC": 49.15, + "HellaSwag": 78.25, + "MMLU": 28.89, + "TruthfulQA": 36.18, + "Winogrande": 71.82, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c27fc771cead6c5556084ea1603a93b5ee29122e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "openthaigpt\/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf", @@ -76900,7 +98313,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "dfc8a1e7ac47765466764dc48c285c5bd23de1fd", "Flagged": false, @@ -76946,7 +98359,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 6.86, - "Hub \u2764\ufe0f": 150.0, + "Hub \u2764\ufe0f": 156.0, "Available on the hub": false, "Model sha": "d5c58cc2cae21b4fb96aaad2658acc898ab22d99", "Flagged": false, @@ -76969,7 +98382,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "b570315dd26452a07cf15cf6feecce839e1327a6", "Flagged": false, @@ -76992,12 +98405,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.02, - "Hub \u2764\ufe0f": 31.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "123d23bd291bb2d5fdb3b91dc1570d0b11654a78", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-c", + "Average \u2b06\ufe0f": 45.29, + "ARC": 48.55, + "HellaSwag": 78.67, + "MMLU": 28.72, + "TruthfulQA": 38.26, + "Winogrande": 70.09, + "GSM8K": 7.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e64962942d53640cc86ec50e3c75b86f1e65d1c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ashercn97\/giraffe-7b", @@ -77038,7 +98474,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 35.0, + "Hub \u2764\ufe0f": 36.0, "Available on the hub": true, "Model sha": "291753b04817a31a742631053ee361874d6db8a4", "Flagged": false, @@ -77090,6 +98526,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "StarFox7\/gemma-2b-dpo-v1", + "Average \u2b06\ufe0f": 45.27, + "ARC": 51.88, + "HellaSwag": 70.87, + "MMLU": 37.7, + "TruthfulQA": 33.15, + "Winogrande": 67.25, + "GSM8K": 10.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1caf66dac8b06385eb8d65f3ae5697fe85d0cf6d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "stabilityai\/stablelm-2-1_6b", @@ -77105,9 +98564,9 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "other", "#Params (B)": 1.64, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 149.0, "Available on the hub": true, "Model sha": "810b45c00ea0af42ded794f9e613f6fc52330921", "Flagged": false, @@ -77153,12 +98612,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.24, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "14b81a0c6870d400cd6216682f182d4615203c2a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "kalisai\/Nusantara-4b-Indo-Chat", + "Average \u2b06\ufe0f": 45.19, + "ARC": 45.39, + "HellaSwag": 70.16, + "MMLU": 38.39, + "TruthfulQA": 38.38, + "Winogrande": 67.25, + "GSM8K": 11.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "9cbf28c0f0ae444f15abe0eaa7955186865ba49b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "luffycodes\/llama-shishya-7b-ep3-v1", @@ -77205,6 +98687,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "abhinand\/gemma-2b-tamil", + "Average \u2b06\ufe0f": 45.13, + "ARC": 47.44, + "HellaSwag": 71.3, + "MMLU": 38.21, + "TruthfulQA": 34.93, + "Winogrande": 65.98, + "GSM8K": 12.89, + "Type": "pretrained", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e0a9e1f7290f59fe0bef30f38cea5bee7a158db", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jlevin\/guanaco-unchained-llama-2-7b", @@ -77220,10 +98725,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "43f3de8bcef63eec03a1b00079c08b5932c1a429", "Flagged": false, "MoE": false @@ -77245,7 +98750,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "d56b5c4f649d8e722efb927d16d7589967a67fbe", "Flagged": false, @@ -77266,14 +98771,60 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "715b03c8573df06f3825d1c08b307e2a83fa8bf9", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Replete-AI\/Phi-Delthanar", + "Average \u2b06\ufe0f": 45.07, + "ARC": 46.67, + "HellaSwag": 60.19, + "MMLU": 51.16, + "TruthfulQA": 50.92, + "Winogrande": 61.48, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.82, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1440f68ce368b8672e43121147592b4fdbbb64d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Telugu-LLM-Labs\/Indic-gemma-2b-finetuned-sft-Navarasa-2.0", + "Average \u2b06\ufe0f": 45.06, + "ARC": 44.71, + "HellaSwag": 68.4, + "MMLU": 38.21, + "TruthfulQA": 44.69, + "Winogrande": 65.11, + "GSM8K": 9.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "90c88dbcd23acbd412378cdd5157a62c6895ff5f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "speechlessai\/speechless-coding-7b-16k-tora", @@ -77291,7 +98842,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "37281f20d54d895f8e3bc660e68564244c775ac2", "Flagged": false, @@ -77320,6 +98871,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-2", + "Average \u2b06\ufe0f": 44.98, + "ARC": 47.18, + "HellaSwag": 78.47, + "MMLU": 28.83, + "TruthfulQA": 38.63, + "Winogrande": 70.4, + "GSM8K": 6.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c58c75c6454865f7f446cd2a4b8dd98b21f607b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kabster\/BioMistral-MedicalQA-FT", + "Average \u2b06\ufe0f": 44.97, + "ARC": 40.02, + "HellaSwag": 67.26, + "MMLU": 23.12, + "TruthfulQA": 47.26, + "Winogrande": 61.56, + "GSM8K": 30.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4f58943fb487b3fe3bb467bfd69a255af18b5c37", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "tyson0420\/stack_codellama-7b-inst", @@ -77343,6 +98940,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/Qwenchana-4B-restart-OH", + "Average \u2b06\ufe0f": 44.96, + "ARC": 45.31, + "HellaSwag": 70.42, + "MMLU": 37.93, + "TruthfulQA": 37.68, + "Winogrande": 66.85, + "GSM8K": 11.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "335319112c7100f8a8b7d54986859157e477b129", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/OpenHermes-Qwen1.5-1.8B", + "Average \u2b06\ufe0f": 44.95, + "ARC": 37.8, + "HellaSwag": 59.73, + "MMLU": 45.8, + "TruthfulQA": 42.28, + "Winogrande": 60.22, + "GSM8K": 23.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "56d69d3040cd98f0958ec216f7beab75f867f6fc", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "csitfun\/llama-7b-logicot", @@ -77360,7 +99003,7 @@ "Merged": false, "Hub License": "cc-by-sa-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "8e9c93c09e6a6c7d504c88d6ca598144829bced8", "Flagged": false, @@ -77384,7 +99027,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "14c23f9fa775ab5ce49010418f00df06d92b0b13", "Flagged": false, "MoE": false @@ -77406,7 +99049,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 63.0, + "Hub \u2764\ufe0f": 64.0, "Available on the hub": true, "Model sha": "612dab2a8b2d77edb4fd36cfc28b3ffbbb20ffc1", "Flagged": false, @@ -77427,9 +99070,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 1.84, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "a38dc9a562b52fe228636ac9099e121524187bf1", "Flagged": false, @@ -77450,9 +99093,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "openrail", "#Params (B)": 12.85, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "675b3e35a9601683c2cb4ec7f1b11d2869842f36", "Flagged": false, @@ -77475,12 +99118,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, "Model sha": "9f1f11790bb0ac4ae6ab8081bf798f5b7cd2331d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "LLM360\/AmberChat", + "Average \u2b06\ufe0f": 44.84, + "ARC": 42.92, + "HellaSwag": 74.01, + "MMLU": 38.75, + "TruthfulQA": 41.18, + "Winogrande": 66.61, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "4c6dc7ae57586801a8d8efe8fcabf98cfe166427", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "mosaicml\/mpt-7b-instruct", @@ -77498,7 +99164,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 450.0, + "Hub \u2764\ufe0f": 457.0, "Available on the hub": false, "Model sha": "925e0d80e50e77aaddaf9c3ced41ca4ea23a1025", "Flagged": false, @@ -77527,6 +99193,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/TruthfulQwen1.5-1.8B", + "Average \u2b06\ufe0f": 44.81, + "ARC": 38.99, + "HellaSwag": 60.43, + "MMLU": 44.54, + "TruthfulQA": 50.86, + "Winogrande": 59.19, + "GSM8K": 14.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "22a0a36aa698afbd83c29bc08d1e91cbb97d4b62", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "zorobin\/mistral-class-shishya-all-hal-7b-ep3", @@ -77573,6 +99262,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Menouar\/saqr-7b-merged", + "Average \u2b06\ufe0f": 44.75, + "ARC": 47.7, + "HellaSwag": 77.51, + "MMLU": 25.78, + "TruthfulQA": 39.38, + "Winogrande": 70.56, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "017423b094eea1bf4b2e8df0939627c7d68c7db6", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "GeneZC\/MiniMA-2-3B", @@ -77613,12 +99325,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.84, - "Hub \u2764\ufe0f": 15.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "2d58d553f3b54abbb6cc49cdb4f2b47336c3c17e", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Abhaykoul\/MediKAI", + "Average \u2b06\ufe0f": 44.74, + "ARC": 46.5, + "HellaSwag": 60.56, + "MMLU": 49.3, + "TruthfulQA": 48.77, + "Winogrande": 61.72, + "GSM8K": 1.59, + "Type": "base merges and moerges", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ba58c6cfe070d77c943251f7e1366cac05a85565", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Writer\/palmyra-med-20b", @@ -77636,7 +99371,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 26.0, + "Hub \u2764\ufe0f": 28.0, "Available on the hub": true, "Model sha": "407810f75698c95000dc0ae1a9a0457be625e972", "Flagged": false, @@ -77665,6 +99400,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "RESMPDEV\/Gemma-Wukong-2b", + "Average \u2b06\ufe0f": 44.64, + "ARC": 45.9, + "HellaSwag": 66.83, + "MMLU": 38.01, + "TruthfulQA": 44.29, + "Winogrande": 62.98, + "GSM8K": 9.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "532616da44668d93da159c4f823ac94772cc2a7c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RESMPDEV\/Gemma-Wukong-2b", + "Average \u2b06\ufe0f": 44.55, + "ARC": 45.31, + "HellaSwag": 66.94, + "MMLU": 38.1, + "TruthfulQA": 44.29, + "Winogrande": 62.59, + "GSM8K": 10.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "532616da44668d93da159c4f823ac94772cc2a7c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "freecs\/ThetaWave-14B-v0.1", @@ -77705,7 +99486,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "e40f072bf68a157a18247eb08bf5b18ab8138986", "Flagged": false, @@ -77751,12 +99532,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.83, - "Hub \u2764\ufe0f": 33.0, + "Hub \u2764\ufe0f": 49.0, "Available on the hub": true, "Model sha": "e2a18423798fa43e6c9935073d9c24c0cd901c6d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "TheDrummer\/Moistral-11B-v2", + "Average \u2b06\ufe0f": 44.48, + "ARC": 45.14, + "HellaSwag": 71.9, + "MMLU": 39.01, + "TruthfulQA": 42.9, + "Winogrande": 67.96, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 11.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "d2e397dae95fca518e5ef43a1c3e3c7231ffdcf7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "qblocks\/falcon_7b_norobots", @@ -77775,7 +99579,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bbe8e4a0c19ec5a94f6eff680b5a55bd08e11e31", "Flagged": false, "MoE": false @@ -77844,11 +99648,34 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bbe8e4a0c19ec5a94f6eff680b5a55bd08e11e31", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "csujeong\/Falcon-7B-Fintued-Finance-Stock-E", + "Average \u2b06\ufe0f": 44.37, + "ARC": 50.09, + "HellaSwag": 78.26, + "MMLU": 27.36, + "TruthfulQA": 36.7, + "Winogrande": 70.72, + "GSM8K": 3.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9f0bd2f7301a8ca44954c2b93359e564b9b61678", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "castorini\/rank_vicuna_7b_v1_fp16", @@ -77912,7 +99739,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 256.0, + "Hub \u2764\ufe0f": 261.0, "Available on the hub": true, "Model sha": "c109b9dde086b31725fa09ff7effdc04c03c033d", "Flagged": false, @@ -77958,15 +99785,15 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "d102fe3b68f1a5a50d547e4fd1c8b33b783c993b", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "anas-awadalla\/mpt-7b", + "T": "\ud83d\udfe2", + "Model": "mosaicml\/mpt-7b", "Average \u2b06\ufe0f": 44.28, "ARC": 47.7, "HellaSwag": 77.57, @@ -77974,22 +99801,22 @@ "TruthfulQA": 33.44, "Winogrande": 72.14, "GSM8K": 4.02, - "Type": "fine-tuned on domain-specific datasets", + "Type": "pretrained", "Architecture": "MPTForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 1139.0, "Available on the hub": false, - "Model sha": "b772e556c8e8a17d087db6935e7cd019e5eefb0f", + "Model sha": "72e5f594ce36f9cabfa2a9fd8f58b491eb467ee7", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udfe2", - "Model": "mosaicml\/mpt-7b", + "T": "\ud83d\udd36", + "Model": "anas-awadalla\/mpt-7b", "Average \u2b06\ufe0f": 44.28, "ARC": 47.7, "HellaSwag": 77.57, @@ -77997,16 +99824,16 @@ "TruthfulQA": 33.44, "Winogrande": 72.14, "GSM8K": 4.02, - "Type": "pretrained", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "MPTForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1129.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, - "Model sha": "72e5f594ce36f9cabfa2a9fd8f58b491eb467ee7", + "Model sha": "b772e556c8e8a17d087db6935e7cd019e5eefb0f", "Flagged": false, "MoE": false }, @@ -78050,7 +99877,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 104.0, + "Hub \u2764\ufe0f": 109.0, "Available on the hub": true, "Model sha": "e5961def23172a2384543940e773ab676033c963", "Flagged": false, @@ -78079,6 +99906,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "sail\/Sailor-4B", + "Average \u2b06\ufe0f": 44.19, + "ARC": 44.45, + "HellaSwag": 69.53, + "MMLU": 38.99, + "TruthfulQA": 37.02, + "Winogrande": 66.06, + "GSM8K": 9.1, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "bc4d4e338bf7e64e52dd05c69bc7e893a21d9dad", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "llm-agents\/tora-code-13b-v1.0", @@ -78142,7 +99992,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 997.0, + "Hub \u2764\ufe0f": 1019.0, "Available on the hub": true, "Model sha": "378337427557d1df3e742264a2901a49f25d4eb1", "Flagged": false, @@ -78171,6 +100021,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "arshadshk\/Mistral-Hinglish-7B-Instruct-v0.2", + "Average \u2b06\ufe0f": 44.09, + "ARC": 40.36, + "HellaSwag": 71.98, + "MMLU": 23.12, + "TruthfulQA": 49.96, + "Winogrande": 66.3, + "GSM8K": 12.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "987a8027701ba1bda62ae86a57051b8b18ce7ef3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "qblocks\/falcon_7b_DolphinCoder", @@ -78189,7 +100062,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "15a07f5340cbb9b6f37db3cda7aa02169feed89f", "Flagged": false, "MoE": false @@ -78212,7 +100085,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "72558e09e54869de3d8fc9fdd42633b81a1839f2", "Flagged": false, "MoE": false @@ -78234,7 +100107,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 4.42, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": false, "Model sha": "8818646580d58ba59268e6d9bb3a43ffafe90fd2", "Flagged": false, @@ -78263,6 +100136,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/gemoy-4b-instruct-scientific", + "Average \u2b06\ufe0f": 44.04, + "ARC": 41.98, + "HellaSwag": 63.05, + "MMLU": 38.73, + "TruthfulQA": 41.96, + "Winogrande": 63.06, + "GSM8K": 15.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.57, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2fd6773d400afdcc4bfce6cefd32551e4087ea69", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "cyberagent\/calm2-7b-chat-dpo-experimental", @@ -78280,12 +100176,35 @@ "Merged": false, "Hub License": "cc-by-4.0", "#Params (B)": 7.01, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "d55a77e9843b4c3848f4e82a4bc303d5a9ec47ff", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Qwen\/Qwen1.5-1.8B-Chat", + "Average \u2b06\ufe0f": 43.99, + "ARC": 38.74, + "HellaSwag": 60.02, + "MMLU": 45.87, + "TruthfulQA": 40.62, + "Winogrande": 59.67, + "GSM8K": 19.03, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "3aede71902ad578aac72678f9f8b6199ca6ab53b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "luffycodes\/llama-class-shishya-7b-ep3", @@ -78332,6 +100251,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/Qwenchana-1.8B", + "Average \u2b06\ufe0f": 43.83, + "ARC": 38.23, + "HellaSwag": 59.92, + "MMLU": 45.78, + "TruthfulQA": 39.58, + "Winogrande": 60.3, + "GSM8K": 19.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7c793e84971c4ebd9c8ec10011f003d8063514b2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Lvxy1117\/amber_fine_tune_sgall", @@ -78372,12 +100314,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 36.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": true, "Model sha": "cf49bc9879266bfc0a0123aaa4ef644af1b20c04", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "sail\/Sailor-4B", + "Average \u2b06\ufe0f": 43.72, + "ARC": 43.86, + "HellaSwag": 69.51, + "MMLU": 37.45, + "TruthfulQA": 37.02, + "Winogrande": 65.67, + "GSM8K": 8.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "bc4d4e338bf7e64e52dd05c69bc7e893a21d9dad", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "AI-Sweden-Models\/gpt-sw3-20b-instruct", @@ -78395,7 +100360,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 20.92, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "006477ad4c4875611f20cd927f1fd76bbf5ba5ba", "Flagged": false, @@ -78418,7 +100383,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.83, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "251a6e5b0749135c6109532734b803d15dd49b7a", "Flagged": false, @@ -78465,7 +100430,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "55b11c279d1a5b83f59cec0381fb41c31fd02d8d", "Flagged": false, "MoE": false @@ -78510,12 +100475,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 213.0, + "Hub \u2764\ufe0f": 257.0, "Available on the hub": true, "Model sha": "cbb77d7448ea3168d884758817e7f895e3828d1c", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Fizzarolli\/sappha-2b-v3", + "Average \u2b06\ufe0f": 43.53, + "ARC": 46.16, + "HellaSwag": 70.73, + "MMLU": 38.63, + "TruthfulQA": 39.94, + "Winogrande": 65.51, + "GSM8K": 0.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "57115346c5f21152c58caf36c5359c8283fe258a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Lvxy1117\/amber_fine_tune_sg_part1", @@ -78579,12 +100567,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "118b6f7cf649f829afdec715eb4720dcd2a572b9", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-13b-hf", + "Average \u2b06\ufe0f": 43.35, + "ARC": 40.87, + "HellaSwag": 63.35, + "MMLU": 32.81, + "TruthfulQA": 43.79, + "Winogrande": 67.17, + "GSM8K": 12.13, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 89.0, + "Available on the hub": true, + "Model sha": "55876f398020b287ac845b34ca08089acf4f4bc3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "NousResearch\/CodeLlama-13b-hf", @@ -78608,29 +100619,6 @@ "Flagged": false, "MoE": false }, - { - "T": "\ud83d\udfe2", - "Model": "codellama\/CodeLlama-13b-hf", - "Average \u2b06\ufe0f": 43.35, - "ARC": 40.87, - "HellaSwag": 63.35, - "MMLU": 32.81, - "TruthfulQA": 43.79, - "Winogrande": 67.17, - "GSM8K": 12.13, - "Type": "pretrained", - "Architecture": "LlamaForCausalLM", - "Weight type": "Original", - "Precision": "float16", - "Merged": false, - "Hub License": "llama2", - "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 81.0, - "Available on the hub": true, - "Model sha": "55876f398020b287ac845b34ca08089acf4f4bc3", - "Flagged": false, - "MoE": false - }, { "T": "?", "Model": "TigerResearch\/tigerbot-7b-sft", @@ -78649,7 +100637,7 @@ "Hub License": "?", "#Params (B)": 7.07, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "98b847905d63f74624e834db1ff95ee2814cbbd3", "Flagged": false, "MoE": false @@ -78671,7 +100659,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.8, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "ae98577d590a16cdbad681e981c5b431f9e246ea", "Flagged": false, @@ -78763,7 +100751,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 60.0, + "Hub \u2764\ufe0f": 67.0, "Available on the hub": true, "Model sha": "f666a1e43500643cb3ff8c988a6ea5b56afe934a", "Flagged": false, @@ -78787,7 +100775,7 @@ "Hub License": "other", "#Params (B)": 8.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "07c78da7631c0e3b0f22558803de182d9255a19b", "Flagged": false, "MoE": false @@ -78809,7 +100797,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 830.0, + "Hub \u2764\ufe0f": 847.0, "Available on the hub": true, "Model sha": "cf4b3c42ce2fdfe24f753f0f0d179202fea59c99", "Flagged": false, @@ -78832,7 +100820,7 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 225.0, + "Hub \u2764\ufe0f": 229.0, "Available on the hub": true, "Model sha": "bed6f3bd18f07a4a379525645cbd86d622b12836", "Flagged": false, @@ -78878,7 +100866,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 830.0, + "Hub \u2764\ufe0f": 847.0, "Available on the hub": true, "Model sha": "eb410fb6ffa9028e97adb801f0d6ec46d02f8b07", "Flagged": false, @@ -78902,7 +100890,7 @@ "Hub License": "?", "#Params (B)": 6.7, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "557b5cbd48a4a4eb5a08e975c4b6e11ac1ed4cbc", "Flagged": false, "MoE": false @@ -78948,11 +100936,34 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5838bea0ad7153520a0a105fb81c5b895820f710", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "aloobun\/Cypher-Mini-1.8B", + "Average \u2b06\ufe0f": 43.05, + "ARC": 39.59, + "HellaSwag": 67.45, + "MMLU": 31.14, + "TruthfulQA": 40.44, + "Winogrande": 65.19, + "GSM8K": 14.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.83, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9d34981cf180b4e84bdf32e39aacb4056a72d406", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "FreedomIntelligence\/phoenix-inst-chat-7b", @@ -78993,7 +101004,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 694.0, + "Hub \u2764\ufe0f": 695.0, "Available on the hub": true, "Model sha": "d386708e84d862a65f7d2b4989f64750cb657227", "Flagged": false, @@ -79062,7 +101073,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 31.0, "Available on the hub": true, "Model sha": "e303cf09e553c38ca5e0c0816d83631801ca5776", "Flagged": false, @@ -79108,7 +101119,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.84, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "a84c11285875fecd9c1cc4e22543efbd4f89f5fe", "Flagged": false, @@ -79131,7 +101142,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 39.0, + "Hub \u2764\ufe0f": 40.0, "Available on the hub": true, "Model sha": "c78df447c70d4677b128b1df864b9fff8338d900", "Flagged": false, @@ -79224,11 +101235,57 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bf8bdcb0c30cceb0ceda33cf5fde683807e39a58", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/gemma-2b-it-sp-test-openherms-step500", + "Average \u2b06\ufe0f": 42.79, + "ARC": 44.03, + "HellaSwag": 62.82, + "MMLU": 37.67, + "TruthfulQA": 45.77, + "Winogrande": 61.17, + "GSM8K": 5.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e545006c78cef3250fb092aa0ffb9a06c6d7487e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/gemma-2b-it-sp-test", + "Average \u2b06\ufe0f": 42.79, + "ARC": 44.03, + "HellaSwag": 62.82, + "MMLU": 37.67, + "TruthfulQA": 45.77, + "Winogrande": 61.17, + "GSM8K": 5.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6cfd509a3b78e16429de3ce822f8ebc086e31a27", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "azarafrooz\/gemma-2b-it-sp-test1", @@ -79269,15 +101326,15 @@ "Merged": false, "Hub License": "other", "#Params (B)": 66.0, - "Hub \u2764\ufe0f": 173.0, + "Hub \u2764\ufe0f": 175.0, "Available on the hub": true, "Model sha": "7259969061237fe940036d22bea0fd349e4485e9", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "Syed-Hasan-8503\/openhermes-gemma-2b-it", + "T": "\ud83d\udcac", + "Model": "abideen\/gemma-2b-openhermes", "Average \u2b06\ufe0f": 42.78, "ARC": 43.94, "HellaSwag": 62.74, @@ -79285,22 +101342,22 @@ "TruthfulQA": 45.83, "Winogrande": 60.93, "GSM8K": 5.61, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "GemmaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 2.51, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, - "Model sha": "a104bc34d3a72e1ed7f3d469591b15dc03dd9725", + "Model sha": "1a8acd4de3c052bd07b6acc89c416d75033e710b", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "abideen\/gemma-2b-openhermes", + "T": "\ud83d\udd36", + "Model": "Syed-Hasan-8503\/openhermes-gemma-2b-it", "Average \u2b06\ufe0f": 42.78, "ARC": 43.94, "HellaSwag": 62.74, @@ -79308,7 +101365,7 @@ "TruthfulQA": 45.83, "Winogrande": 60.93, "GSM8K": 5.61, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "GemmaForCausalLM", "Weight type": "Original", "Precision": "float16", @@ -79317,7 +101374,7 @@ "#Params (B)": 2.51, "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, - "Model sha": "1a8acd4de3c052bd07b6acc89c416d75033e710b", + "Model sha": "a104bc34d3a72e1ed7f3d469591b15dc03dd9725", "Flagged": false, "MoE": false }, @@ -79361,7 +101418,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.51, - "Hub \u2764\ufe0f": 317.0, + "Hub \u2764\ufe0f": 449.0, "Available on the hub": true, "Model sha": "9642e777f24fde593d204a9b2471dce33334e64a", "Flagged": false, @@ -79390,6 +101447,98 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "aloobun\/Cypher-Laser-Mixtral-2x1.8B-v0.1", + "Average \u2b06\ufe0f": 42.65, + "ARC": 40.44, + "HellaSwag": 67.6, + "MMLU": 31.49, + "TruthfulQA": 40.62, + "Winogrande": 65.19, + "GSM8K": 10.54, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 3.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f8a0f5a7244b5631a237efc54ae734b373de7a34", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "aloobun\/Cypher-Mixtral-2x1.8B-v0.1", + "Average \u2b06\ufe0f": 42.62, + "ARC": 40.44, + "HellaSwag": 67.7, + "MMLU": 31.81, + "TruthfulQA": 39.94, + "Winogrande": 65.35, + "GSM8K": 10.46, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 3.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "89bf138c4fef534dd049898eea3791fddb88ce49", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "axxd\/wizardllama-7b", + "Average \u2b06\ufe0f": 42.61, + "ARC": 42.83, + "HellaSwag": 66.2, + "MMLU": 35.44, + "TruthfulQA": 35.71, + "Winogrande": 62.43, + "GSM8K": 13.04, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e399cd6c8855d103be1fb31c797890861db25d12", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Chickaboo\/ChickaQ-V2-Large-Beta", + "Average \u2b06\ufe0f": 42.61, + "ARC": 34.3, + "HellaSwag": 57.87, + "MMLU": 42.33, + "TruthfulQA": 43.85, + "Winogrande": 59.04, + "GSM8K": 18.27, + "Type": "base merges and moerges", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 3.05, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "792fc755898baca487114a97a2fb490de3349ab6", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "VMware\/open-llama-7b-open-instruct", @@ -79459,6 +101608,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Tensoic\/Gemma-2B-Samvaad", + "Average \u2b06\ufe0f": 42.55, + "ARC": 46.59, + "HellaSwag": 68.17, + "MMLU": 33.09, + "TruthfulQA": 39.95, + "Winogrande": 61.64, + "GSM8K": 5.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "6d8968c6515a7cc4a9ddb4aeab32a51115b6d605", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "dvruette\/oasst-gpt-neox-20b-1000-steps", @@ -79519,7 +101691,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 8.99, "Hub \u2764\ufe0f": 0.0, @@ -79592,7 +101764,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7a0aaba040ae0b122737172db4581f2d0b1064bf", "Flagged": false, "MoE": false @@ -79615,7 +101787,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "600d70148047ad1ec7cb99a596dfeb8ba6a2c42c", "Flagged": false, "MoE": false @@ -79637,7 +101809,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 179.0, + "Hub \u2764\ufe0f": 189.0, "Available on the hub": true, "Model sha": "cff055b1e110cbe75c0c3759bd436299c6d6bb66", "Flagged": false, @@ -79691,7 +101863,7 @@ }, { "T": "\ud83d\udd36", - "Model": "togethercomputer\/RedPajama-INCITE-7B-Instruct", + "Model": "togethercomputer\/RedPajama-INCITE-Instruct-7B-v0.1", "Average \u2b06\ufe0f": 42.38, "ARC": 44.11, "HellaSwag": 72.02, @@ -79700,21 +101872,21 @@ "Winogrande": 64.96, "GSM8K": 1.59, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "GPTNeoXForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 103.0, - "Available on the hub": true, + "Hub License": "?", + "#Params (B)": 6.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "95667a602ff2646bf67fe3a57c4eb9a1edec87fe", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "togethercomputer\/RedPajama-INCITE-Instruct-7B-v0.1", + "Model": "togethercomputer\/RedPajama-INCITE-7B-Instruct", "Average \u2b06\ufe0f": 42.38, "ARC": 44.11, "HellaSwag": 72.02, @@ -79723,13 +101895,13 @@ "Winogrande": 64.96, "GSM8K": 1.59, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "GPTNeoXForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 6.65, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 104.0, "Available on the hub": true, "Model sha": "95667a602ff2646bf67fe3a57c4eb9a1edec87fe", "Flagged": false, @@ -79752,7 +101924,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 119.0, + "Hub \u2764\ufe0f": 122.0, "Available on the hub": true, "Model sha": "6fb184ff23774c25bf84b3628e49c8b78372c7be", "Flagged": false, @@ -79798,7 +101970,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 7.07, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "8c2dc302780fe320ee3428f3db2ee7ff3684dcef", "Flagged": false, @@ -79827,6 +101999,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "silvainrichou\/gemma-3b-002", + "Average \u2b06\ufe0f": 42.22, + "ARC": 43.34, + "HellaSwag": 64.06, + "MMLU": 36.86, + "TruthfulQA": 42.68, + "Winogrande": 60.85, + "GSM8K": 5.53, + "Type": "base merges and moerges", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c47cbc0fce360a29ed592e1887602d916a593622", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "OpenAssistant\/pythia-12b-sft-v8-7k-steps", @@ -79867,7 +102062,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 121.0, + "Hub \u2764\ufe0f": 127.0, "Available on the hub": true, "Model sha": "2f4c4f3ebcf171dbbe2bae989ea2d2f3d3486a97", "Flagged": false, @@ -79942,6 +102137,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-SOLAR-11b-v2.0", + "Average \u2b06\ufe0f": 42.19, + "ARC": 41.64, + "HellaSwag": 61.67, + "MMLU": 37.35, + "TruthfulQA": 47.72, + "Winogrande": 63.46, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ad171800ebf03b89cfe6d556a67ad765bb70292f", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "TehVenom\/Moderator-Chan_GPT-JT-6b", @@ -79982,7 +102200,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 128.0, + "Hub \u2764\ufe0f": 130.0, "Available on the hub": true, "Model sha": "76875e6ea8df98157fb032c48ad6e354fd6a077b", "Flagged": false, @@ -80051,7 +102269,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "40086d791942cb28f55e679cd3fb6f6b5ba4effd", "Flagged": false, @@ -80333,6 +102551,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "vitruv\/vitruv_2", + "Average \u2b06\ufe0f": 41.87, + "ARC": 43.34, + "HellaSwag": 68.02, + "MMLU": 32.98, + "TruthfulQA": 36.46, + "Winogrande": 66.46, + "GSM8K": 3.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db9d4443473291aedc6765283d925156c0736a85", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "Aryanne\/ereb-test", @@ -80396,7 +102637,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.84, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "38905b74c36b45f23f416d68dc2f755c81524763", "Flagged": false, @@ -80419,7 +102660,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": false, "Model sha": "e80966ae720de9a844441a4a2bbc661106969915", "Flagged": false, @@ -80465,7 +102706,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.11, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "81ca95a4e93746240994d1e6797ffa64dc796bd9", "Flagged": false, @@ -80511,7 +102752,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.74, - "Hub \u2764\ufe0f": 475.0, + "Hub \u2764\ufe0f": 488.0, "Available on the hub": true, "Model sha": "9369f145ca7b66ef62760f9351af951b2d53b77f", "Flagged": false, @@ -80626,7 +102867,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 92.0, + "Hub \u2764\ufe0f": 93.0, "Available on the hub": true, "Model sha": "78f7e482443971f4873ba3239f0ac810a367833b", "Flagged": false, @@ -80649,7 +102890,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 282.0, + "Hub \u2764\ufe0f": 288.0, "Available on the hub": true, "Model sha": "73c15208cb608be2949b7c6e4ba6d88f0176c267", "Flagged": false, @@ -80741,7 +102982,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.02, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "0a2f9d6bbb3959d68fe52e07ee6f54e8242f91ec", "Flagged": false, @@ -80834,7 +103075,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ca900c8f3145de40cd188c559b2901a2e4711546", "Flagged": false, "MoE": false @@ -80879,7 +103120,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "d434d06249feb6ca511b0a09162130bcc59d84e3", "Flagged": false, @@ -80902,7 +103143,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.0, - "Hub \u2764\ufe0f": 351.0, + "Hub \u2764\ufe0f": 354.0, "Available on the hub": true, "Model sha": "626b8c140cfdedb119dfb78c626cd772283dee33", "Flagged": false, @@ -80926,7 +103167,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6ed0dca683685cb5b9e7df599f87d311f00ba6db", "Flagged": false, "MoE": false @@ -80948,7 +103189,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 75.0, + "Hub \u2764\ufe0f": 79.0, "Available on the hub": true, "Model sha": "1a80940a290452af71caf17a8e520955eb338e0f", "Flagged": false, @@ -80972,7 +103213,7 @@ "Hub License": "?", "#Params (B)": 6.65, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "78f7e482443971f4873ba3239f0ac810a367833b", "Flagged": false, "MoE": false @@ -81063,7 +103304,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.43, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "edbea6fe86d0bc2673c10269828008a1cb451919", "Flagged": false, @@ -81086,7 +103327,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 2.7, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "8eb300dc6a62166048f7ec997a0a2d8d9a5708f2", "Flagged": false, @@ -81178,7 +103419,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.43, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "d860a90ef6b30c695b985dd2ff382d4bbb80e857", "Flagged": false, @@ -81224,7 +103465,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 20.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "dd98d514b5aff4e820922c88a73d6d5bf17f332e", "Flagged": false, @@ -81339,7 +103580,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.43, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "ffc81b58375342f12e38a67272d95458a72e8d09", "Flagged": false, @@ -81362,12 +103603,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 58.0, + "Hub \u2764\ufe0f": 59.0, "Available on the hub": true, "Model sha": "a1fb934dd7bbba8eff8c6052fa469f979803236b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "unit-mesh\/autodev-deepseek-6.7b-finetunes-poc", + "Average \u2b06\ufe0f": 40.95, + "ARC": 35.41, + "HellaSwag": 52.41, + "MMLU": 37.56, + "TruthfulQA": 44.11, + "Winogrande": 56.67, + "GSM8K": 19.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "7d853c1192a8a428dc1db2fe8608143748386fce", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "harborwater\/open-llama-3b-claude-30k", @@ -81385,7 +103649,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.43, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "049db7fda44e5ce1e8febf5c3f45e3a93aaaa859", "Flagged": false, @@ -81593,7 +103857,7 @@ "Hub License": "?", "#Params (B)": 3.43, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4bcf1610eb1f3959568d5acee74833c41502bf04", "Flagged": false, "MoE": false @@ -81638,7 +103902,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.0, - "Hub \u2764\ufe0f": 279.0, + "Hub \u2764\ufe0f": 280.0, "Available on the hub": true, "Model sha": "293df535fe7711a5726987fc2f17dfc87de452a1", "Flagged": false, @@ -81727,7 +103991,7 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 8.99, "Hub \u2764\ufe0f": 0.0, @@ -81753,7 +104017,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 20.92, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "36797b7835a9e656af456e0006465a3af48735fc", "Flagged": false, @@ -81822,12 +104086,35 @@ "Merged": false, "Hub License": null, "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": false, "Model sha": "785793f6b216afd9fc664fc63e8e6c776a016825", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/dolphin-2.6-mistral-7b-dpo-5.93B", + "Average \u2b06\ufe0f": 40.62, + "ARC": 38.99, + "HellaSwag": 61.01, + "MMLU": 27.32, + "TruthfulQA": 53.51, + "Winogrande": 62.67, + "GSM8K": 0.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 5.93, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "eb789a38c4c01a2f0c7130123de0e7806a9b4a8a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "harborwater\/open-llama-3b-everythingLM-2048", @@ -82029,7 +104316,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 68.0, + "Hub \u2764\ufe0f": 69.0, "Available on the hub": true, "Model sha": "e40673a27a4aefcff2c6d2b3b1e0681a38703e4e", "Flagged": false, @@ -82121,7 +104408,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 113.0, + "Hub \u2764\ufe0f": 116.0, "Available on the hub": true, "Model sha": "bce5d60d3b0c68318862270ec4e794d83308d80a", "Flagged": false, @@ -82190,7 +104477,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 33.74, - "Hub \u2764\ufe0f": 91.0, + "Hub \u2764\ufe0f": 93.0, "Available on the hub": true, "Model sha": "3dd8ab05bbd273b9f77088b1d4015b7f1848793d", "Flagged": false, @@ -82265,6 +104552,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Senko-11B-v1", + "Average \u2b06\ufe0f": 40.21, + "ARC": 35.67, + "HellaSwag": 40.86, + "MMLU": 56.77, + "TruthfulQA": 54.78, + "Winogrande": 53.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7d5790f235731602fd9f31eb9180e2ce81ffb780", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "llm-agents\/tora-code-7b-v1.0", @@ -82282,12 +104592,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 11.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": true, "Model sha": "777501b69bb0ba2675abdcaf7b1309ab05320c2e", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/gemoy-4b-instruct", + "Average \u2b06\ufe0f": 40.2, + "ARC": 40.7, + "HellaSwag": 58.03, + "MMLU": 36.42, + "TruthfulQA": 46.64, + "Winogrande": 59.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.05, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "18dae1ff443a44fa20b40b21044a6601b6544d56", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "digitous\/Janin-R", @@ -82377,7 +104710,7 @@ "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "6413b1d9e8b58df9d3aac91a862e8d505d8c6716", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -82397,7 +104730,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 6.0, - "Hub \u2764\ufe0f": 1348.0, + "Hub \u2764\ufe0f": 1362.0, "Available on the hub": true, "Model sha": "47e169305d2e8376be1d31e765533382721b2cc1", "Flagged": false, @@ -82512,7 +104845,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 162.0, + "Hub \u2764\ufe0f": 172.0, "Available on the hub": true, "Model sha": "7affc442e639b8aa1c4b3e98a10a2f45a21b8b4f", "Flagged": false, @@ -82648,7 +104981,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", + "Hub License": "?", "#Params (B)": 15.83, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -82765,7 +105098,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 35.58, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "e2e97475a9775d2fe7afba098aee37e694b9220f", "Flagged": false, @@ -82883,7 +105216,7 @@ "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "f30709dba36c665869f9ac8cd0cef5a8a2e7c8df", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -82903,7 +105236,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 63.0, + "Hub \u2764\ufe0f": 65.0, "Available on the hub": true, "Model sha": "97aa918c383820e1a69f042801091d7deb996c20", "Flagged": false, @@ -82949,7 +105282,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 255.0, + "Hub \u2764\ufe0f": 278.0, "Available on the hub": true, "Model sha": "be52f4ad322f5a47da121c761aeb5ba20ed77b17", "Flagged": false, @@ -83042,7 +105375,7 @@ "Hub License": "?", "#Params (B)": 3.43, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "efa950c69b6cbe1f8629400f3a7e0ccd895551fb", "Flagged": false, "MoE": false @@ -83065,7 +105398,7 @@ "Hub License": "?", "#Params (B)": 3.43, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "efa950c69b6cbe1f8629400f3a7e0ccd895551fb", "Flagged": false, "MoE": false @@ -83087,7 +105420,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.43, - "Hub \u2764\ufe0f": 4.0, + "Hub \u2764\ufe0f": 5.0, "Available on the hub": true, "Model sha": "36841c80535bc3e8403e3cc084e8e65884c75076", "Flagged": false, @@ -83202,7 +105535,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": false, "Model sha": "f4a9d167819eaffcfafffc3e52530d0af04efdf4", "Flagged": false, @@ -83271,7 +105604,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 192.0, + "Hub \u2764\ufe0f": 198.0, "Available on the hub": true, "Model sha": "8a949353677d2b971910a6c4afcc70e95d838c2a", "Flagged": false, @@ -83294,7 +105627,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 31.0, + "Hub \u2764\ufe0f": 32.0, "Available on the hub": true, "Model sha": "c27a7e2360dd313406719980851e89abf46ebb13", "Flagged": false, @@ -83338,10 +105671,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", + "Hub License": "cc-by-sa-3.0", "#Params (B)": 6.0, "Hub \u2764\ufe0f": 1.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "83d8c754aac12f838d7c847d4352a09396c383d0", "Flagged": false, "MoE": false @@ -83386,7 +105719,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "e55ace80c04ed4ace1876ba192e6ecb4ef0353b8", "Flagged": false, @@ -83432,7 +105765,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 72.0, + "Hub \u2764\ufe0f": 73.0, "Available on the hub": true, "Model sha": "1f6ffd8f162030396a3bc1ca2e3504896dbe6434", "Flagged": false, @@ -83478,7 +105811,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 132.0, + "Hub \u2764\ufe0f": 136.0, "Available on the hub": true, "Model sha": "f0e0995eba801096ed04cb87931d96a8316871af", "Flagged": false, @@ -83501,7 +105834,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": false, "Model sha": "f4a9d167819eaffcfafffc3e52530d0af04efdf4", "Flagged": false, @@ -83524,7 +105857,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 7.11, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "7a7f93d4318658b354c5411cde64e9f0121f6b1f", "Flagged": false, @@ -83570,7 +105903,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 12.0, - "Hub \u2764\ufe0f": 1922.0, + "Hub \u2764\ufe0f": 1930.0, "Available on the hub": true, "Model sha": "19308160448536e378e3db21a73a751579ee7fdd", "Flagged": false, @@ -83594,7 +105927,7 @@ "Hub License": "?", "#Params (B)": 6.74, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8619e9870ce3285bf9c2a74921b5947dd6f9e4ac", "Flagged": false, "MoE": false @@ -83619,7 +105952,7 @@ "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "b31d25819e00d5031ccdb22a9584f0850dcfe39c", - "Flagged": true, + "Flagged": false, "MoE": false }, { @@ -83637,7 +105970,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 3.43, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -83645,6 +105978,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "julleong\/illuni-llama-2-ko-7b-test", + "Average \u2b06\ufe0f": 39.41, + "ARC": 43.43, + "HellaSwag": 64.86, + "MMLU": 28.69, + "TruthfulQA": 33.3, + "Winogrande": 63.77, + "GSM8K": 2.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.86, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "104fac91a859164fd379c96814788090bbe22e76", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Fredithefish\/RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4", @@ -83670,7 +106026,7 @@ }, { "T": "\ud83d\udd36", - "Model": "togethercomputer\/RedPajama-INCITE-7B-Chat", + "Model": "togethercomputer\/RedPajama-INCITE-Chat-7B-v0.1", "Average \u2b06\ufe0f": 39.37, "ARC": 42.06, "HellaSwag": 70.82, @@ -83679,21 +106035,21 @@ "Winogrande": 59.83, "GSM8K": 0.45, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "GPTNeoXForCausalLM", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 91.0, - "Available on the hub": true, + "Hub License": "?", + "#Params (B)": 6.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "47b94a739e2f3164b438501c8684acc5d5acc146", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "togethercomputer\/RedPajama-INCITE-Chat-7B-v0.1", + "Model": "togethercomputer\/RedPajama-INCITE-7B-Chat", "Average \u2b06\ufe0f": 39.37, "ARC": 42.06, "HellaSwag": 70.82, @@ -83702,13 +106058,13 @@ "Winogrande": 59.83, "GSM8K": 0.45, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Architecture": "GPTNeoXForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", - "#Params (B)": 6.65, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 92.0, "Available on the hub": true, "Model sha": "47b94a739e2f3164b438501c8684acc5d5acc146", "Flagged": false, @@ -83731,7 +106087,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 10.0, + "Hub \u2764\ufe0f": 12.0, "Available on the hub": false, "Model sha": "bebfcb894b3f5170ce54e3bb98b6e565fae7b6c0", "Flagged": false, @@ -83800,7 +106156,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 760.0, + "Hub \u2764\ufe0f": 778.0, "Available on the hub": false, "Model sha": "a5e85ae1941e31bb705adbcafce9b0dfd6f3a48b", "Flagged": false, @@ -83892,7 +106248,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 141.0, + "Hub \u2764\ufe0f": 144.0, "Available on the hub": true, "Model sha": "d632f0c8b75b1ae5b26b250d25bfba4e99cb7c6f", "Flagged": false, @@ -83915,7 +106271,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "eeec9ee7d50953a27189ac64ee63c93a272d1a12", "Flagged": false, @@ -83984,7 +106340,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 7.07, - "Hub \u2764\ufe0f": 170.0, + "Hub \u2764\ufe0f": 177.0, "Available on the hub": true, "Model sha": "e83e90ba86f87f74aa2731cdab25ccf33976bd66", "Flagged": false, @@ -84053,7 +106409,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.0, - "Hub \u2764\ufe0f": 70.0, + "Hub \u2764\ufe0f": 71.0, "Available on the hub": true, "Model sha": "112a5ad9f556078ab14a5cd93511b9db4a0d4413", "Flagged": false, @@ -84076,7 +106432,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.83, - "Hub \u2764\ufe0f": 22.0, + "Hub \u2764\ufe0f": 39.0, "Available on the hub": true, "Model sha": "3201996d3a41b4a485582164db42ca58d51051aa", "Flagged": false, @@ -84122,7 +106478,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.7, - "Hub \u2764\ufe0f": 86.0, + "Hub \u2764\ufe0f": 88.0, "Available on the hub": true, "Model sha": "9c4d1af96f93224e01d2f69c303fc6d6f686bdcc", "Flagged": false, @@ -84168,7 +106524,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 6.7, - "Hub \u2764\ufe0f": 91.0, + "Hub \u2764\ufe0f": 94.0, "Available on the hub": true, "Model sha": "a45aa65bbeb77c1558bc99bedc6779195462dab0", "Flagged": false, @@ -84191,7 +106547,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 88.0, + "Hub \u2764\ufe0f": 90.0, "Available on the hub": true, "Model sha": "0c66778ee09a036886741707733620b91057909a", "Flagged": false, @@ -84261,7 +106617,7 @@ "Hub License": "?", "#Params (B)": 3.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "fd2754e80ce80757a3a68a840d7d287dd7def676", "Flagged": false, "MoE": false @@ -84375,7 +106731,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 4.78, - "Hub \u2764\ufe0f": 14.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "c80e2f01377d551ad17c8c9bac3f52578c38d653", "Flagged": false, @@ -84582,7 +106938,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 12.0, - "Hub \u2764\ufe0f": 125.0, + "Hub \u2764\ufe0f": 128.0, "Available on the hub": true, "Model sha": "35c9d7f32fbb108fb8b5bdd574eb03369d1eed49", "Flagged": false, @@ -84611,6 +106967,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "sail\/Sailor-1.8B-Chat", + "Average \u2b06\ufe0f": 38.76, + "ARC": 35.75, + "HellaSwag": 57.12, + "MMLU": 38.31, + "TruthfulQA": 38.71, + "Winogrande": 59.12, + "GSM8K": 3.56, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2a3bbb343ffba05985f26f66e2d3ee8e695a2e94", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "KnutJaegersberg\/black_goo_recipe_a", @@ -84743,12 +107122,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.62, - "Hub \u2764\ufe0f": 58.0, + "Hub \u2764\ufe0f": 98.0, "Available on the hub": true, "Model sha": "fedce23ef6393499effdf4958f9b3256f299cc7d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Deathsquad10\/TakeTwo", + "Average \u2b06\ufe0f": 38.6, + "ARC": 37.2, + "HellaSwag": 62.01, + "MMLU": 23.8, + "TruthfulQA": 36.02, + "Winogrande": 70.01, + "GSM8K": 2.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "50248bfc7243ea02712ca694f1f50f1760a378d7", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "matsuo-lab\/weblab-10b", @@ -84766,7 +107168,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 10.0, - "Hub \u2764\ufe0f": 58.0, + "Hub \u2764\ufe0f": 60.0, "Available on the hub": true, "Model sha": "d6fc432983b1633a4c1568d121c60de6b8c3e511", "Flagged": false, @@ -84795,6 +107197,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "InnerI\/I-Code-NousLlama7B-slerp", + "Average \u2b06\ufe0f": 38.56, + "ARC": 40.36, + "HellaSwag": 61.05, + "MMLU": 28.37, + "TruthfulQA": 36.17, + "Winogrande": 64.64, + "GSM8K": 0.76, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b54f03cd80453df7d36065af89660d878dd52a1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "RWKV\/rwkv-raven-7b", @@ -84812,7 +107237,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": false, "Model sha": "a2dfc9f659be13556a25d9e38da642c6f67aeee3", "Flagged": false, @@ -84835,7 +107260,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 85.0, + "Hub \u2764\ufe0f": 88.0, "Available on the hub": true, "Model sha": "094fbdd0c911feb485ce55de1952ab2e75277e1e", "Flagged": false, @@ -84881,7 +107306,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 54.0, + "Hub \u2764\ufe0f": 56.0, "Available on the hub": true, "Model sha": "a1041efcf9599c962822274e92040710579a5bf2", "Flagged": false, @@ -84927,7 +107352,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 9.0, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "029a787e0d98fcd3fecffbfbeb4a75a425474937", "Flagged": false, @@ -85088,7 +107513,7 @@ "Merged": false, "Hub License": "creativeml-openrail-m", "#Params (B)": 6.0, - "Hub \u2764\ufe0f": 709.0, + "Hub \u2764\ufe0f": 716.0, "Available on the hub": true, "Model sha": "30e2405100eac6bd53f75964cc7345eeafd19f7d", "Flagged": false, @@ -85180,7 +107605,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.43, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": true, "Model sha": "520c5f1ceb5c90d4011887e2a8d3becf15e7e66e", "Flagged": false, @@ -85203,7 +107628,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 139.0, + "Hub \u2764\ufe0f": 140.0, "Available on the hub": true, "Model sha": "141067009124b9c0aea62c76b3eb952174864057", "Flagged": false, @@ -85224,7 +107649,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -85270,7 +107695,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -85293,7 +107718,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -85341,12 +107766,127 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.46, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "cb46afdc603e018e2ec4a672769b0e8a473aa88b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Abhaykoul\/Qwen1.5-0.5B-vortex", + "Average \u2b06\ufe0f": 38.15, + "ARC": 31.74, + "HellaSwag": 47.78, + "MMLU": 38.44, + "TruthfulQA": 38.92, + "Winogrande": 56.51, + "GSM8K": 15.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dd2364092537b736e87bafb4b2fd65ea460beb32", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Abhaykoul\/qwen1.5-vortex", + "Average \u2b06\ufe0f": 38.15, + "ARC": 31.74, + "HellaSwag": 47.78, + "MMLU": 38.44, + "TruthfulQA": 38.92, + "Winogrande": 56.51, + "GSM8K": 15.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "52cd90c24411e9474a32c70e78b549e98108206e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lqtrung1998\/galactica-6.7b-ReFT-GSM8k", + "Average \u2b06\ufe0f": 38.15, + "ARC": 40.7, + "HellaSwag": 50.34, + "MMLU": 37.62, + "TruthfulQA": 41.21, + "Winogrande": 58.33, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db019ea6f2762330d09f28bca53a5ecee8e2819a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Abhaykoul\/qwen1.5-vortex", + "Average \u2b06\ufe0f": 38.13, + "ARC": 31.83, + "HellaSwag": 47.71, + "MMLU": 38.66, + "TruthfulQA": 38.98, + "Winogrande": 56.27, + "GSM8K": 15.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "52cd90c24411e9474a32c70e78b549e98108206e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/d-Qwen1.5-0.5B", + "Average \u2b06\ufe0f": 38.07, + "ARC": 30.29, + "HellaSwag": 47.75, + "MMLU": 38.21, + "TruthfulQA": 39.29, + "Winogrande": 55.8, + "GSM8K": 17.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "c845a4ca140e3abfb58793731c4addd4533102b3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "EleutherAI\/pythia-6.7b", @@ -85365,7 +107905,7 @@ "Hub License": "?", "#Params (B)": 6.65, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b666a6e46eeade607c73ed1334ecda3b9345e4bf", "Flagged": false, "MoE": false @@ -85479,7 +108019,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 1.28, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "c7f891765a4d43ac972302a24ed67158cec8dc18", "Flagged": false, @@ -85502,7 +108042,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 6.66, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "ac74fdd938de1ffd34832d66a25db20b0230983e", "Flagged": false, @@ -85569,7 +108109,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -85600,6 +108140,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "RESMPDEV\/Gemma-Wukong1.1-2b", + "Average \u2b06\ufe0f": 37.61, + "ARC": 33.45, + "HellaSwag": 42.39, + "MMLU": 42.52, + "TruthfulQA": 47.73, + "Winogrande": 59.59, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0a04dcf420eb4b1c8ed5eb58afc9cf813b639d0d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "euclaise\/falcon_1b_stage2", @@ -85687,7 +108250,7 @@ "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b3953afa698098e06e03aa14713015b11b4ab421", "Flagged": false, "MoE": false @@ -85733,7 +108296,7 @@ "Hub License": "mit", "#Params (B)": 3.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "e624fdbb538362206af1b98400bf44bbc0247226", "Flagged": false, "MoE": false @@ -85755,10 +108318,56 @@ "Merged": true, "Hub License": "llama2", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 15.0, "Available on the hub": true, "Model sha": "d3e41fef45f6a7d438c46ba7d9fce5d0d486c7a9", - "Flagged": true, + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe9", + "Model": "gemmathon\/gemma-2b-ko-dev-pbmt192", + "Average \u2b06\ufe0f": 37.47, + "ARC": 38.57, + "HellaSwag": 52.95, + "MMLU": 28.71, + "TruthfulQA": 42.54, + "Winogrande": 58.56, + "GSM8K": 3.49, + "Type": "continuously pretrained", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "856bd740a9c014e7dfc7233dbe6b9083f44ac8a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "OEvortex\/vortex-3b-v2", + "Average \u2b06\ufe0f": 37.46, + "ARC": 39.68, + "HellaSwag": 65.04, + "MMLU": 25.09, + "TruthfulQA": 33.8, + "Winogrande": 59.12, + "GSM8K": 2.05, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fff79b81d767be1830b8f9887f1c084b8636711a", + "Flagged": false, "MoE": false }, { @@ -85784,6 +108393,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "RESMPDEV\/Gemma-Wukong1.1-2b", + "Average \u2b06\ufe0f": 37.46, + "ARC": 33.45, + "HellaSwag": 42.42, + "MMLU": 42.94, + "TruthfulQA": 47.7, + "Winogrande": 58.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0a04dcf420eb4b1c8ed5eb58afc9cf813b639d0d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "KoboldAI\/fairseq-dense-2.7B", @@ -85807,6 +108439,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Evaloric\/Evaloric-1.1B-V.0.1", + "Average \u2b06\ufe0f": 37.41, + "ARC": 36.86, + "HellaSwag": 61.9, + "MMLU": 23.96, + "TruthfulQA": 35.4, + "Winogrande": 63.46, + "GSM8K": 2.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4cfcbf3aabd60fdeff47e013c40c0dc211f68ddb", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "cerebras\/Cerebras-GPT-13B", @@ -85830,6 +108485,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ndavidson\/cisco-iNAM-1.1B", + "Average \u2b06\ufe0f": 37.39, + "ARC": 36.01, + "HellaSwag": 60.74, + "MMLU": 26.39, + "TruthfulQA": 39.3, + "Winogrande": 60.46, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1949425f65e6160efec2a0237397f85d9e94fb0", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "gardner\/TinyLlama-1.1B-SlimOrca-Function-Calling-3T", @@ -85876,6 +108554,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "frankenmerger\/MiniLlama-1.8b-Chat-v0.1", + "Average \u2b06\ufe0f": 37.37, + "ARC": 34.73, + "HellaSwag": 62.38, + "MMLU": 25.69, + "TruthfulQA": 38.97, + "Winogrande": 60.54, + "GSM8K": 1.9, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.89, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a880960de7a6340e68ebd92004430eaee3a6890b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "dball\/zephyr-tiny-dpo-qlora", @@ -85894,7 +108595,7 @@ "Hub License": "apache-2.0", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "6c6f2246d4db07605b714f956f5e48878049b7b6", "Flagged": false, "MoE": false @@ -85962,7 +108663,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 812.0, + "Hub \u2764\ufe0f": 880.0, "Available on the hub": true, "Model sha": "de253fa9783f8bd558c9ed398c8ffbe3c55cedb3", "Flagged": false, @@ -85985,7 +108686,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 35.58, - "Hub \u2764\ufe0f": 116.0, + "Hub \u2764\ufe0f": 118.0, "Available on the hub": true, "Model sha": "43c701ddbe0bceac26c860307e06763cc5203500", "Flagged": false, @@ -86006,10 +108707,10 @@ "Weight type": "Adapter", "Precision": "8bit", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 3.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f477d24b00e05fe4c5f8d5f933080994cfd90e4e", "Flagged": false, "MoE": false @@ -86031,7 +108732,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 6.7, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "14fa470051d0bc38fd871643186a9edfd3a8a9aa", "Flagged": false, @@ -86106,6 +108807,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Nekochu\/Confluence-Renegade-7B", + "Average \u2b06\ufe0f": 37.23, + "ARC": 31.91, + "HellaSwag": 45.38, + "MMLU": 31.48, + "TruthfulQA": 51.47, + "Winogrande": 63.14, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "35a69deab8523329176e87313d77c19593f9b89d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "AI-Sweden-Models\/gpt-sw3-6.7b", @@ -86146,12 +108870,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "4cd25191268b231cb584c85ce55285902c9fa31a", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Trelis\/TinyLlama-chat-SFT", + "Average \u2b06\ufe0f": 37.21, + "ARC": 34.47, + "HellaSwag": 61.03, + "MMLU": 25.77, + "TruthfulQA": 39.29, + "Winogrande": 61.25, + "GSM8K": 1.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cad981584d4be97aa49353082af8a771e20e2c3b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "sreeramajay\/TinyLlama-1.1B-orca-v1.0", @@ -86192,7 +108939,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 812.0, + "Hub \u2764\ufe0f": 880.0, "Available on the hub": true, "Model sha": "de253fa9783f8bd558c9ed398c8ffbe3c55cedb3", "Flagged": false, @@ -86215,7 +108962,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "c8fa674a68fe45f8f87a6aef87c8e2cbcee62b81", "Flagged": false, @@ -86267,6 +109014,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "OEvortex\/HelpingAI-Lite-2x1B", + "Average \u2b06\ufe0f": 37.15, + "ARC": 36.09, + "HellaSwag": 61.11, + "MMLU": 25.1, + "TruthfulQA": 37.39, + "Winogrande": 60.85, + "GSM8K": 2.35, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.86, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d7795c76cf4591e0360afbfe956a4146a5834bfc", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "princeton-nlp\/Sheared-LLaMA-1.3B-ShareGPT", @@ -86284,12 +109054,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.3, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "d2f3cfae7746c4ff07353b39828985ea0f36b07d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/d-Qwen1.5-1.8B", + "Average \u2b06\ufe0f": 37.14, + "ARC": 30.89, + "HellaSwag": 49.73, + "MMLU": 37.92, + "TruthfulQA": 42.89, + "Winogrande": 59.19, + "GSM8K": 2.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "12eb58c7ddc17a6eddf5c52a3d9793e1e35464b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Danielbrdz\/Barcenas-Tiny-1.1b-DPO", @@ -86331,7 +109124,7 @@ "Hub License": "?", "#Params (B)": 2.91, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b9d8cace80b1a97f5ed380711aea31f2d1b24310", "Flagged": false, "MoE": false @@ -86399,7 +109192,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.0, - "Hub \u2764\ufe0f": 90.0, + "Hub \u2764\ufe0f": 95.0, "Available on the hub": true, "Model sha": "e4b9872bb803165eb22f0a867d4e6a64d34fce19", "Flagged": false, @@ -86422,12 +109215,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 320.0, + "Hub \u2764\ufe0f": 321.0, "Available on the hub": true, "Model sha": "b073c9bb418ae52ca76b4ab48ac2dfbc8622f434", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "kalisai\/Nusantara-1.8b-Indo-Chat", + "Average \u2b06\ufe0f": 37.06, + "ARC": 35.32, + "HellaSwag": 56.32, + "MMLU": 30.37, + "TruthfulQA": 37.27, + "Winogrande": 59.75, + "GSM8K": 3.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9b92b6cc3f4b3769886aac151edeef9990dcec4b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "xaviviro\/OpenHermes-2.5-FLOR-6.3B", @@ -86445,7 +109261,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 6.3, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "1ac3215a61b2e11010230d52a6153635def819e6", "Flagged": false, @@ -86543,6 +109359,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Abhaykoul\/HelpingAI-Lite-4x1b", + "Average \u2b06\ufe0f": 37.02, + "ARC": 35.84, + "HellaSwag": 61.0, + "MMLU": 25.24, + "TruthfulQA": 37.39, + "Winogrande": 60.77, + "GSM8K": 1.9, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 3.38, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e55836d41118de827f19cef1efc73f1cf1dd3abd", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "Aabbhishekk\/TinyLlama-1.1B-miniguanaco", @@ -86583,12 +109422,35 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 42.0, + "Hub \u2764\ufe0f": 45.0, "Available on the hub": true, "Model sha": "ea1b775799b477fe22e64f8ac9107f28950b5c87", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "sbawa\/elysa_model", + "Average \u2b06\ufe0f": 37.0, + "ARC": 37.54, + "HellaSwag": 60.37, + "MMLU": 25.58, + "TruthfulQA": 37.37, + "Winogrande": 60.22, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f57eba56111fcea5f1438d31d05bc84ccb4fc51c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "AIChenKai\/TinyLlama-1.1B-Chat-v1.0-x2-MoE", @@ -86606,7 +109468,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.86, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "fe49be7cae7eb8362e176e4d371fb9dd8c68422d", "Flagged": false, @@ -86629,7 +109491,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.7, - "Hub \u2764\ufe0f": 34.0, + "Hub \u2764\ufe0f": 37.0, "Available on the hub": true, "Model sha": "39ca914ceb82f7f14a38484023bc04f0cd5d0a8d", "Flagged": false, @@ -86767,7 +109629,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 710.0, + "Hub \u2764\ufe0f": 755.0, "Available on the hub": true, "Model sha": "949f61e203f91b412efe8f679c798f09f0ff4b0c", "Flagged": false, @@ -86790,7 +109652,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 107.0, + "Hub \u2764\ufe0f": 120.0, "Available on the hub": true, "Model sha": "ec4dd26f30674fdee00ef161b55f464ce28f9c20", "Flagged": false, @@ -86859,7 +109721,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.7, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "b4131723cfff1fa42f6cbab546c5b4bb0d19fd83", "Flagged": false, @@ -86888,6 +109750,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "lqtrung1998\/galactica-6.7b-ReFT-Rerank-GSM8k", + "Average \u2b06\ufe0f": 36.86, + "ARC": 41.13, + "HellaSwag": 48.78, + "MMLU": 32.86, + "TruthfulQA": 41.2, + "Winogrande": 56.91, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForSequenceClassification", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.66, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "13f88bef7068492879a32eeee42597cc37fc727e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Josephgflowers\/Tinyllama-1.3B-Cinder-Reason-Test-2", @@ -86951,7 +109836,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 5.0, - "Hub \u2764\ufe0f": 108.0, + "Hub \u2764\ufe0f": 110.0, "Available on the hub": true, "Model sha": "d1438e22a33b9115af0e47ab3a0fe844cbf588a6", "Flagged": false, @@ -86995,10 +109880,10 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 2.8, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, "Model sha": "40e84b6d38aac92a0302c2a682498794ef0fd901", "Flagged": false, "MoE": false @@ -87066,12 +109951,35 @@ "Merged": false, "Hub License": "other", "#Params (B)": 2.7, - "Hub \u2764\ufe0f": 65.0, + "Hub \u2764\ufe0f": 73.0, "Available on the hub": true, "Model sha": "397f71a473a150c00f0fe3fc4a2f78ff3ccaf82d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "jan-hq\/LlamaCorn-1.1B-Chat", + "Average \u2b06\ufe0f": 36.73, + "ARC": 33.79, + "HellaSwag": 59.24, + "MMLU": 29.01, + "TruthfulQA": 36.86, + "Winogrande": 61.48, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c2b9512df2001f9ead2ebd3d0286cf47be73ad68", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "L-R\/LLmRa-2.7B", @@ -87164,6 +110072,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udfe9", + "Model": "M4-ai\/tau-0.5B", + "Average \u2b06\ufe0f": 36.68, + "ARC": 29.27, + "HellaSwag": 47.43, + "MMLU": 37.53, + "TruthfulQA": 39.39, + "Winogrande": 56.83, + "GSM8K": 9.63, + "Type": "continuously pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.5, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "dee82e4f55c393354b33ed3f1d448aa520ba8e26", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/K2S3-SOLAR-11b-v1.0", + "Average \u2b06\ufe0f": 36.67, + "ARC": 33.7, + "HellaSwag": 51.39, + "MMLU": 30.05, + "TruthfulQA": 45.99, + "Winogrande": 57.54, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3c5ff9c8a00dfb6cf8619ce08c2f06a22e650e0c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "alnrg2arg\/blockchainlabs_tinyllama_fusion_LHK_yunkong_v2", @@ -87187,6 +110141,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "M4-ai\/tau-0.5B", + "Average \u2b06\ufe0f": 36.65, + "ARC": 29.01, + "HellaSwag": 47.45, + "MMLU": 37.44, + "TruthfulQA": 39.39, + "Winogrande": 56.83, + "GSM8K": 9.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.5, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "dee82e4f55c393354b33ed3f1d448aa520ba8e26", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "danielhanchen\/open_llama_3b_600bt_preview", @@ -87210,6 +110187,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Code-290k-6.7B-Instruct", + "Average \u2b06\ufe0f": 36.64, + "ARC": 34.9, + "HellaSwag": 51.99, + "MMLU": 34.89, + "TruthfulQA": 41.95, + "Winogrande": 52.64, + "GSM8K": 3.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "4ef569814773fac1700bfb8c563118d497af7b76", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "42dot\/42dot_LLM-SFT-1.3B", @@ -87227,12 +110227,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 1.44, - "Hub \u2764\ufe0f": 27.0, + "Hub \u2764\ufe0f": 30.0, "Available on the hub": true, "Model sha": "7474cafe5dc60549c19f89f7c49392a8a32b9199", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Chickaboo\/ChickaQ", + "Average \u2b06\ufe0f": 36.6, + "ARC": 29.44, + "HellaSwag": 49.15, + "MMLU": 37.05, + "TruthfulQA": 47.22, + "Winogrande": 56.12, + "GSM8K": 0.61, + "Type": "base merges and moerges", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2f6bc46231a35c15a0343ef9f09899381116091b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83e\udd1d", "Model": "alnrg2arg\/blockchainlabs_tinyllama_fusion_LHK_yunkong", @@ -87296,12 +110319,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.74, - "Hub \u2764\ufe0f": 82.0, + "Hub \u2764\ufe0f": 104.0, "Available on the hub": true, "Model sha": "ffb89c545ae24f7f164e121cf68723a18f5b28c9", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "sail\/Sailor-1.8B", + "Average \u2b06\ufe0f": 36.59, + "ARC": 33.11, + "HellaSwag": 57.06, + "MMLU": 30.44, + "TruthfulQA": 37.81, + "Winogrande": 58.41, + "GSM8K": 2.73, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "c2d5776ce22949330793ddcc4f5b19f61f0dcf8d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "PSanni\/Deer-3b", @@ -87325,6 +110371,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/smolphin-test-bottomheavy", + "Average \u2b06\ufe0f": 36.54, + "ARC": 32.68, + "HellaSwag": 59.17, + "MMLU": 25.84, + "TruthfulQA": 38.49, + "Winogrande": 61.8, + "GSM8K": 1.29, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c8226313c06f0d749be5a29db75a4e9467921d87", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "alexredna\/Tukan-1.1B-Chat-reasoning-sft-COLA", @@ -87365,12 +110434,58 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.74, - "Hub \u2764\ufe0f": 82.0, + "Hub \u2764\ufe0f": 104.0, "Available on the hub": true, "Model sha": "ffb89c545ae24f7f164e121cf68723a18f5b28c9", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/TinyWombat-1.8b-Chat-v.1", + "Average \u2b06\ufe0f": 36.48, + "ARC": 32.94, + "HellaSwag": 58.88, + "MMLU": 25.12, + "TruthfulQA": 39.74, + "Winogrande": 60.22, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.89, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "149003fdf86efe3d8d28145ef31f2baeb01b019a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "invalid-coder\/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo", + "Average \u2b06\ufe0f": 36.46, + "ARC": 33.02, + "HellaSwag": 60.0, + "MMLU": 26.88, + "TruthfulQA": 38.08, + "Winogrande": 59.59, + "GSM8K": 1.21, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5781cace9e0c56c090f981375000d5f33512acaa", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BEE-spoke-data\/TinyLlama-3T-1.1bee", @@ -87394,6 +110509,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Abhaykoul\/Qwen1.5-0.5B-vortex-v2", + "Average \u2b06\ufe0f": 36.45, + "ARC": 30.63, + "HellaSwag": 45.54, + "MMLU": 36.29, + "TruthfulQA": 44.29, + "Winogrande": 56.04, + "GSM8K": 5.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "029222d7fbad83a11b2b721aae4dbed6c8f848d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/smolphin-test-stack-sorted", + "Average \u2b06\ufe0f": 36.42, + "ARC": 32.34, + "HellaSwag": 59.07, + "MMLU": 26.44, + "TruthfulQA": 37.48, + "Winogrande": 61.25, + "GSM8K": 1.97, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "41c13b6301a2e03272c5a2ebaa57a0a4d048d1cd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "codellama\/CodeLlama-7b-Python-hf", @@ -87411,7 +110572,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 6.74, - "Hub \u2764\ufe0f": 107.0, + "Hub \u2764\ufe0f": 120.0, "Available on the hub": true, "Model sha": "ec4dd26f30674fdee00ef161b55f464ce28f9c20", "Flagged": false, @@ -87434,7 +110595,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 111.0, + "Hub \u2764\ufe0f": 126.0, "Available on the hub": true, "Model sha": "df4c1907f152969ce2850c097e414d79c3a1665a", "Flagged": false, @@ -87463,6 +110624,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "h4rz3rk4s3\/TinyNewsLlama-1.1B", + "Average \u2b06\ufe0f": 36.41, + "ARC": 32.94, + "HellaSwag": 59.43, + "MMLU": 25.18, + "TruthfulQA": 40.95, + "Winogrande": 59.75, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a4e7c60302a70746c6bfc4a79d85f040c27c675d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/SmolPlatypus-1.5B-Sorted", + "Average \u2b06\ufe0f": 36.4, + "ARC": 33.62, + "HellaSwag": 59.06, + "MMLU": 25.61, + "TruthfulQA": 37.88, + "Winogrande": 61.17, + "GSM8K": 1.06, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "508179f70e68b6213c5f2f02ff76cfc2796441b4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "facebook\/xglm-7.5B", @@ -87480,7 +110687,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 7.5, - "Hub \u2764\ufe0f": 53.0, + "Hub \u2764\ufe0f": 54.0, "Available on the hub": true, "Model sha": "732d59308a844004bd9a4def972cc7c3896a38e0", "Flagged": false, @@ -87501,13 +110708,13 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "cf2c67039648176ffe45e3ffb9892557a95d3405", - "Flagged": true, - "MoE": true + "Flagged": false, + "MoE": false }, { "T": "\ud83d\udcac", @@ -87526,7 +110733,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 24.0, + "Hub \u2764\ufe0f": 28.0, "Available on the hub": true, "Model sha": "fc3e646d484cf1e48d210b69d7f142f104b996da", "Flagged": false, @@ -87549,7 +110756,7 @@ "Merged": false, "Hub License": "llama2", "#Params (B)": 34.0, - "Hub \u2764\ufe0f": 245.0, + "Hub \u2764\ufe0f": 249.0, "Available on the hub": true, "Model sha": "3aabef8c9bc1b3ec2fffed053645bc1e2d829b6c", "Flagged": false, @@ -87595,7 +110802,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 6.7, - "Hub \u2764\ufe0f": 63.0, + "Hub \u2764\ufe0f": 65.0, "Available on the hub": true, "Model sha": "4f56c6e28f9a2a1c470626f1a064238806f19f09", "Flagged": false, @@ -87624,6 +110831,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/SmolPlatypus-1.5B", + "Average \u2b06\ufe0f": 36.23, + "ARC": 33.96, + "HellaSwag": 60.05, + "MMLU": 24.73, + "TruthfulQA": 36.82, + "Winogrande": 60.85, + "GSM8K": 0.99, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "98d850be9b5536120bb4591381854c1acfa20b12", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "cognitivecomputations\/TinyDolphin-2.8.1-1.1b", @@ -87647,6 +110877,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/smolphin-test-stack", + "Average \u2b06\ufe0f": 36.2, + "ARC": 32.68, + "HellaSwag": 59.94, + "MMLU": 25.16, + "TruthfulQA": 36.64, + "Winogrande": 62.04, + "GSM8K": 0.76, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ac7c8b73ca8a9602c777481367fca2c4528c17e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "EleutherAI\/gpt-neo-2.7B", @@ -87664,7 +110917,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 2.72, - "Hub \u2764\ufe0f": 381.0, + "Hub \u2764\ufe0f": 384.0, "Available on the hub": true, "Model sha": "e24fa291132763e59f4a5422741b424fb5d59056", "Flagged": false, @@ -87779,7 +111032,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 80.0, + "Hub \u2764\ufe0f": 83.0, "Available on the hub": true, "Model sha": "52bc5b43010b4844513826b8be3f78c7344c37d7", "Flagged": false, @@ -87802,7 +111055,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 16.22, - "Hub \u2764\ufe0f": 282.0, + "Hub \u2764\ufe0f": 289.0, "Available on the hub": true, "Model sha": "d9b00ec47ae3546398432f0693fe2d5d92bf143b", "Flagged": false, @@ -87918,7 +111171,7 @@ "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "670b3f3be7ee5fd09922c033d0fa2d539f98344a", "Flagged": false, "MoE": false @@ -87940,7 +111193,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.3, - "Hub \u2764\ufe0f": 79.0, + "Hub \u2764\ufe0f": 81.0, "Available on the hub": true, "Model sha": "b1c3f74c8495e27b3963d64af0781d4a611794f3", "Flagged": false, @@ -87986,7 +111239,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 16.0, "Available on the hub": true, "Model sha": "471c1ff16a8a78afa702a69f16df98dc14464bf6", "Flagged": false, @@ -88010,11 +111263,34 @@ "Hub License": "?", "#Params (B)": 33.48, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "45f38e53a579a2b39298cc57ab04078722bebec0", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Deathsquad10\/TinyMix", + "Average \u2b06\ufe0f": 35.91, + "ARC": 32.0, + "HellaSwag": 53.69, + "MMLU": 24.27, + "TruthfulQA": 39.42, + "Winogrande": 64.09, + "GSM8K": 1.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "be8089b91dc36c42ffac1101d8a386bf4e5e765d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "ewqr2130\/TinyLamma-SFT", @@ -88038,6 +111314,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/smolphin-test1", + "Average \u2b06\ufe0f": 35.85, + "ARC": 32.25, + "HellaSwag": 59.73, + "MMLU": 24.61, + "TruthfulQA": 35.81, + "Winogrande": 61.72, + "GSM8K": 0.99, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e83efe15c074ba19df21f64d6aa989b096dab01", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "MayaPH\/opt-flan-iml-6.7b", @@ -88130,6 +111429,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "VAIBHAV22334455\/JARVIS", + "Average \u2b06\ufe0f": 35.78, + "ARC": 32.08, + "HellaSwag": 56.86, + "MMLU": 27.15, + "TruthfulQA": 37.33, + "Winogrande": 60.14, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "28091aa912d17a231f59a18a286f289928c098fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OEvortex\/vortex-3b", + "Average \u2b06\ufe0f": 35.76, + "ARC": 31.91, + "HellaSwag": 56.89, + "MMLU": 27.32, + "TruthfulQA": 37.39, + "Winogrande": 60.14, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "033a96fd948b6375247465c72be51a6cb6b46c50", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "bigcode\/starcoder", @@ -88147,7 +111492,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 2632.0, + "Hub \u2764\ufe0f": 2684.0, "Available on the hub": true, "Model sha": "e117ab3b3d0769fd962bd48b099de711757a3d60", "Flagged": false, @@ -88216,12 +111561,58 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 1.44, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 21.0, "Available on the hub": true, "Model sha": "a72bf57eb02cd4ea4388a344b4a5893aa95698da", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/SmolLlama-1.5B-Bottomheavy", + "Average \u2b06\ufe0f": 35.68, + "ARC": 34.22, + "HellaSwag": 59.54, + "MMLU": 24.96, + "TruthfulQA": 35.0, + "Winogrande": 59.75, + "GSM8K": 0.61, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b383556d08f411258991be602297b00208753c87", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kalisai\/Nusantara-2.7b-Indo-Chat", + "Average \u2b06\ufe0f": 35.68, + "ARC": 34.22, + "HellaSwag": 56.1, + "MMLU": 24.83, + "TruthfulQA": 37.41, + "Winogrande": 58.17, + "GSM8K": 3.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "452bc6935b408166abe65a7966afa03cbd78ce02", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "sartmis1\/starcoder-finetune-selfinstruct", @@ -88240,11 +111631,57 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b21bd307ea7417185e7dc59557c399a3e4e0092b", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Qwen\/Qwen1.5-0.5B-Chat", + "Average \u2b06\ufe0f": 35.61, + "ARC": 30.55, + "HellaSwag": 44.07, + "MMLU": 33.82, + "TruthfulQA": 42.95, + "Winogrande": 54.62, + "GSM8K": 7.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 38.0, + "Available on the hub": true, + "Model sha": "6c705984bb8b5591dd4e1a9e66e1a127965fd08d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Minami-su\/Qwen1.5-0.5B-Chat_llamafy", + "Average \u2b06\ufe0f": 35.61, + "ARC": 30.63, + "HellaSwag": 44.11, + "MMLU": 33.82, + "TruthfulQA": 42.97, + "Winogrande": 54.7, + "GSM8K": 7.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.5, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "23d87e6b371b3bb929600b690ec4f8160a387eaa", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "freecs\/Tiny-Llama-3-7b", @@ -88260,7 +111697,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 6.91, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -88283,7 +111720,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 6.91, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -88401,7 +111838,7 @@ "Hub License": "?", "#Params (B)": 1.03, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "20dd44d78aa09480bf15ca0ecc0c0780951d49a9", "Flagged": false, "MoE": false @@ -88423,7 +111860,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 376.0, + "Hub \u2764\ufe0f": 379.0, "Available on the hub": true, "Model sha": "88ec5781ad071a9d9e925cd28f327dea22eb5188", "Flagged": false, @@ -88452,6 +111889,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "M4-ai\/tau-0.5B-instruct-DPOP", + "Average \u2b06\ufe0f": 35.54, + "ARC": 28.92, + "HellaSwag": 43.63, + "MMLU": 33.92, + "TruthfulQA": 42.73, + "Winogrande": 57.06, + "GSM8K": 6.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "30cbeff9365d6141ddebab7562b26e31409c5e51", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "22h\/open-cabrita3b", @@ -88516,7 +111976,7 @@ "Hub License": "apache-2.0", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "effd86f3284e6472f1a865a208ee68900e9f7318", "Flagged": false, "MoE": false @@ -88538,12 +111998,35 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 15.52, - "Hub \u2764\ufe0f": 226.0, + "Hub \u2764\ufe0f": 228.0, "Available on the hub": true, "Model sha": "b693a7a7d52bed1cd7cc0fe00399db838b09c74f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "h4rz3rk4s3\/TinyPoliticaLlama-1.1B", + "Average \u2b06\ufe0f": 35.47, + "ARC": 33.79, + "HellaSwag": 57.83, + "MMLU": 25.45, + "TruthfulQA": 38.06, + "Winogrande": 57.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8838d8f094dee1078572cf127f835cdb32117d6f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "bhenrym14\/airoboros-33b-gpt4-1.4.1-PI-8192-fp16", @@ -88585,7 +112068,7 @@ "Hub License": "?", "#Params (B)": 1.42, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "6cd9b5bc13ee15b5e7e7cfb46477bc6a7c0b5d47", "Flagged": false, "MoE": false @@ -88654,7 +112137,7 @@ "Hub License": "?", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "eb5f39bac15ccab9463001aa203e33d49f4ff7cb", "Flagged": false, "MoE": false @@ -88682,6 +112165,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/SmolLlama-1.5B", + "Average \u2b06\ufe0f": 35.42, + "ARC": 32.76, + "HellaSwag": 56.74, + "MMLU": 24.53, + "TruthfulQA": 38.08, + "Winogrande": 59.27, + "GSM8K": 1.14, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1fdc734ee4063929f4b79aeea78fb849904a83ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jeff31415\/TinyLlama-1.1B-1.5T-OpenOrca-Alpha", + "Average \u2b06\ufe0f": 35.39, + "ARC": 32.76, + "HellaSwag": 53.77, + "MMLU": 25.73, + "TruthfulQA": 40.52, + "Winogrande": 58.96, + "GSM8K": 0.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c337449718ad228fcf205e9c963ad31043e027ad", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "TheBloke\/openchat_v2_openorca_preview-GPTQ", @@ -88728,6 +112257,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-3-2", + "Average \u2b06\ufe0f": 35.31, + "ARC": 33.28, + "HellaSwag": 49.24, + "MMLU": 27.86, + "TruthfulQA": 40.99, + "Winogrande": 60.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e66bf986384a611f1316b660e1b0a6072d77866", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "KnutJaegersberg\/Walter-Llama-1B", @@ -88929,7 +112481,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.3, - "Hub \u2764\ufe0f": 40.0, + "Hub \u2764\ufe0f": 42.0, "Available on the hub": true, "Model sha": "d60fa58f50def19751da2075791da359ca19d273", "Flagged": false, @@ -88975,7 +112527,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 16.22, - "Hub \u2764\ufe0f": 105.0, + "Hub \u2764\ufe0f": 107.0, "Available on the hub": true, "Model sha": "848bf2514f804799dd28c188e5428d497dc983fb", "Flagged": false, @@ -88998,7 +112550,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 1.41, - "Hub \u2764\ufe0f": 5.0, + "Hub \u2764\ufe0f": 6.0, "Available on the hub": false, "Model sha": "20bf1732212ea81adb45b782a25ce69e65a01ad2", "Flagged": false, @@ -89027,6 +112579,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Corianas\/DPO-miniguanaco-1.5T", + "Average \u2b06\ufe0f": 35.13, + "ARC": 30.63, + "HellaSwag": 54.05, + "MMLU": 24.79, + "TruthfulQA": 42.69, + "Winogrande": 58.64, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9be4cc848fc5c7047b32a42451b1631a14ee00e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "maywell\/TinyWand-DPO", @@ -89205,7 +112780,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.4, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "77f320b24ccae4aa85a5890dbb9514bd11267bb3", "Flagged": false, @@ -89234,6 +112809,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "h4rz3rk4s3\/TinyParlaMintLlama-1.1B", + "Average \u2b06\ufe0f": 34.97, + "ARC": 31.66, + "HellaSwag": 55.87, + "MMLU": 24.84, + "TruthfulQA": 38.81, + "Winogrande": 58.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c9aa196c68732bf1b563dcfb4d9c6f835087e9e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "euclaise\/falcon_1b_stage3", @@ -89257,6 +112855,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/cosmo-3b-test", + "Average \u2b06\ufe0f": 34.94, + "ARC": 35.32, + "HellaSwag": 52.36, + "MMLU": 27.25, + "TruthfulQA": 39.02, + "Winogrande": 54.3, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.95, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bb3e1b70079ea2d17c23171d01189e09fe6712c5", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "TinyLlama\/TinyLlama-1.1B-Chat-v0.6", @@ -89274,7 +112895,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 60.0, + "Hub \u2764\ufe0f": 67.0, "Available on the hub": true, "Model sha": "bf9ae1c8bf026667e6f810768de259bb4a7f4777", "Flagged": false, @@ -89343,7 +112964,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.1, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 13.0, "Available on the hub": true, "Model sha": "175336a0000f36b508575ef1a2da05755faf48c3", "Flagged": false, @@ -89413,11 +113034,80 @@ "Hub License": "?", "#Params (B)": 1.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a5c7ecc4d908e7a9469d080308af64ae775c733d", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "frankenmerger\/cosmo-3b-test-v0.2", + "Average \u2b06\ufe0f": 34.7, + "ARC": 35.32, + "HellaSwag": 51.7, + "MMLU": 27.33, + "TruthfulQA": 38.82, + "Winogrande": 53.51, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.95, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "544e8b53e20aa379415ba12ecd1616d2a894672d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OEvortex\/HelpingAI-Lite-1.5T", + "Average \u2b06\ufe0f": 34.68, + "ARC": 31.23, + "HellaSwag": 52.39, + "MMLU": 25.93, + "TruthfulQA": 38.61, + "Winogrande": 58.33, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "25333435dd8d5605ac4f3d6bc9cd1cb886f15b77", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nnheui\/pythia-1.4b-sft-full", + "Average \u2b06\ufe0f": 34.68, + "ARC": 32.68, + "HellaSwag": 52.08, + "MMLU": 25.44, + "TruthfulQA": 38.42, + "Winogrande": 57.46, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a15673e313e80a70f5d71396e612a8088bde650", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "MBZUAI\/LaMini-GPT-1.5B", @@ -89481,7 +113171,7 @@ "Merged": false, "Hub License": "bigscience-openrail-m", "#Params (B)": 15.0, - "Hub \u2764\ufe0f": 717.0, + "Hub \u2764\ufe0f": 726.0, "Available on the hub": true, "Model sha": "926ca1b215c4631bc5f8c3e47173381452c23e5c", "Flagged": false, @@ -89550,7 +113240,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.3, - "Hub \u2764\ufe0f": 134.0, + "Hub \u2764\ufe0f": 137.0, "Available on the hub": true, "Model sha": "8c7b10754972749675d22364c25c428b29face51", "Flagged": false, @@ -89579,6 +113269,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "jeff31415\/TinyLlama-1.1B-1T-OpenOrca", + "Average \u2b06\ufe0f": 34.58, + "ARC": 31.31, + "HellaSwag": 52.34, + "MMLU": 25.31, + "TruthfulQA": 38.58, + "Winogrande": 58.25, + "GSM8K": 1.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "605c2a8b2324a25ca0513c4c862bfa9c937b3514", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "PY007\/TinyLlama-1.1B-Chat-v0.1", @@ -89597,7 +113310,7 @@ "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7abc14e7779eabc3a028bc695342869d0410dea2", "Flagged": false, "MoE": false @@ -89625,6 +113338,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "jylee420\/gemma-2b-data-std", + "Average \u2b06\ufe0f": 34.55, + "ARC": 37.54, + "HellaSwag": 32.49, + "MMLU": 35.82, + "TruthfulQA": 39.56, + "Winogrande": 61.72, + "GSM8K": 0.15, + "Type": "continuously pretrained", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8514b865649969a5e1acdbff5d098694269c69ab", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "AI-Sweden-Models\/gpt-sw3-1.3b-instruct", @@ -89735,7 +113471,7 @@ "Hub License": "?", "#Params (B)": 1.31, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "34b668ff0acfe56f2d541aa46b385557ee39eb3f", "Flagged": false, "MoE": false @@ -89757,12 +113493,35 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 10.0, "Available on the hub": true, "Model sha": "c85efce322a0f6d93d64f7b9096525753da6913e", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "ToastyPigeon\/SmolLlama-1.5B-Sorted", + "Average \u2b06\ufe0f": 34.39, + "ARC": 31.91, + "HellaSwag": 56.39, + "MMLU": 24.48, + "TruthfulQA": 32.11, + "Winogrande": 60.85, + "GSM8K": 0.61, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6e3ee804d739faa38cb008f5cbdc94670e5f3191", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "gpt2-xl", @@ -89804,7 +113563,7 @@ "Hub License": "?", "#Params (B)": 1.03, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "098830e58452a0a08f90eb0189ec5925803fd48b", "Flagged": false, "MoE": false @@ -89895,7 +113654,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 5.08, - "Hub \u2764\ufe0f": 18.0, + "Hub \u2764\ufe0f": 20.0, "Available on the hub": true, "Model sha": "dc6a67fac06c8bca7860b84656a0cb736293a7a8", "Flagged": false, @@ -90110,6 +113869,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "FINGU-AI\/FinguAI-Chat-v1", + "Average \u2b06\ufe0f": 34.09, + "ARC": 29.18, + "HellaSwag": 44.08, + "MMLU": 30.39, + "TruthfulQA": 42.79, + "Winogrande": 56.59, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "3557829049749742bdb0bfaf23de2d07ecf928f2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "KnutJaegersberg\/Walter-Falcon-1B", @@ -90173,7 +113955,7 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 357.0, + "Hub \u2764\ufe0f": 358.0, "Available on the hub": true, "Model sha": "25071b093c15c0d1cb2b2876c6deb621b764fcf5", "Flagged": false, @@ -90194,7 +113976,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -90225,6 +114007,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "croissantllm\/CroissantLLMBase", + "Average \u2b06\ufe0f": 33.99, + "ARC": 30.63, + "HellaSwag": 54.18, + "MMLU": 25.72, + "TruthfulQA": 37.39, + "Winogrande": 55.41, + "GSM8K": 0.61, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "b22c20207a5a1b2b4bb3f2b511096c1f0cc95b81", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "jzjiao\/opt-1.3b-rlhf", @@ -90265,7 +114070,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 1.72, - "Hub \u2764\ufe0f": 105.0, + "Hub \u2764\ufe0f": 106.0, "Available on the hub": true, "Model sha": "cc72a88036c2fb937d65efeacc57a0c2ef5d6fe5", "Flagged": false, @@ -90288,7 +114093,7 @@ "Merged": false, "Hub License": "creativeml-openrail-m", "#Params (B)": 2.7, - "Hub \u2764\ufe0f": 50.0, + "Hub \u2764\ufe0f": 52.0, "Available on the hub": true, "Model sha": "9533805293bc48e8ddfe9dc1940d8cbc5662113e", "Flagged": false, @@ -90405,7 +114210,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 35.58, - "Hub \u2764\ufe0f": 78.0, + "Hub \u2764\ufe0f": 80.0, "Available on the hub": true, "Model sha": "cd07cc7c55b46524f61214012653c25226d24c0d", "Flagged": false, @@ -90428,7 +114233,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 28.0, + "Hub \u2764\ufe0f": 30.0, "Available on the hub": true, "Model sha": "4ab631381edb607557cbb04b6e9a225bad16807c", "Flagged": false, @@ -90452,7 +114257,7 @@ "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "213ebf60d7fdd3258fa5574840b06c97a7e8cf5d", "Flagged": false, "MoE": false @@ -90474,7 +114279,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 1.37, - "Hub \u2764\ufe0f": 227.0, + "Hub \u2764\ufe0f": 231.0, "Available on the hub": true, "Model sha": "8282180b53cba30a1575e49de1530019e5931739", "Flagged": false, @@ -90595,6 +114400,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "sail\/Sailor-0.5B-Chat", + "Average \u2b06\ufe0f": 33.47, + "ARC": 30.38, + "HellaSwag": 45.51, + "MMLU": 26.73, + "TruthfulQA": 39.85, + "Winogrande": 56.51, + "GSM8K": 1.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "3d72ea8def9a4aa40d7536f5d568fcc4a16218b2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BEE-spoke-data\/TinyLlama-1.1bee", @@ -90636,7 +114464,7 @@ "Hub License": "?", "#Params (B)": 3.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a1ba0a65e5262bc134dbc562a9faf80865b0a72f", "Flagged": false, "MoE": false @@ -90681,7 +114509,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.06, - "Hub \u2764\ufe0f": 73.0, + "Hub \u2764\ufe0f": 77.0, "Available on the hub": true, "Model sha": "09dfc839067bf44e7f52976eca8adbc17f04e1b0", "Flagged": false, @@ -90779,6 +114607,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "RaoFoundation\/774M-03_09_2024", + "Average \u2b06\ufe0f": 33.22, + "ARC": 30.29, + "HellaSwag": 53.88, + "MMLU": 25.33, + "TruthfulQA": 34.44, + "Winogrande": 55.09, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "27d2412db12d6bedf3b3f26ffa4045a6ba7d0e48", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "shaohang\/Sparse0.5_OPT-1.3", @@ -90820,11 +114671,103 @@ "Hub License": "?", "#Params (B)": 1.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "06249d582b0cfefac537dd6bee2e578002ffff00", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/Qwenchana-0.5B-restart", + "Average \u2b06\ufe0f": 33.15, + "ARC": 30.03, + "HellaSwag": 45.95, + "MMLU": 25.61, + "TruthfulQA": 40.48, + "Winogrande": 54.85, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4793a45028bdf35b26438799eb8090a3077beba6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/Qwenchana-0.5B-restart", + "Average \u2b06\ufe0f": 33.1, + "ARC": 30.46, + "HellaSwag": 45.89, + "MMLU": 25.39, + "TruthfulQA": 40.48, + "Winogrande": 54.62, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4793a45028bdf35b26438799eb8090a3077beba6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "sail\/Sailor-0.5B", + "Average \u2b06\ufe0f": 33.05, + "ARC": 29.69, + "HellaSwag": 45.82, + "MMLU": 25.62, + "TruthfulQA": 40.76, + "Winogrande": 55.33, + "GSM8K": 1.06, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "69e509f56254ae8bba6fdb9d2e35b9df03b96b7b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sail\/Sailor-0.5B", + "Average \u2b06\ufe0f": 33.03, + "ARC": 29.69, + "HellaSwag": 45.82, + "MMLU": 25.13, + "TruthfulQA": 40.74, + "Winogrande": 55.56, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "69e509f56254ae8bba6fdb9d2e35b9df03b96b7b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "health360\/Healix-1.1B-V1-Chat-dDPO", @@ -90840,7 +114783,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -90848,6 +114791,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/TinyllamaMix-1.1B", + "Average \u2b06\ufe0f": 32.99, + "ARC": 31.48, + "HellaSwag": 48.39, + "MMLU": 25.05, + "TruthfulQA": 33.45, + "Winogrande": 58.48, + "GSM8K": 1.06, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0a00b7bb4f046e98cc833f5303522afc057e1058", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "TurkuNLP\/gpt3-finnish-13B", @@ -90871,6 +114837,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "kalisai\/Nusantara-0.8b-Indo-Chat", + "Average \u2b06\ufe0f": 32.93, + "ARC": 30.38, + "HellaSwag": 44.61, + "MMLU": 26.89, + "TruthfulQA": 39.54, + "Winogrande": 54.7, + "GSM8K": 1.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.82, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0d5d402467e6d72883bc1d64695a450497d5925c", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "aisquared\/dlite-v2-774m", @@ -90940,6 +114929,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/Mistral-4B-FT-2", + "Average \u2b06\ufe0f": 32.81, + "ARC": 25.94, + "HellaSwag": 39.63, + "MMLU": 25.46, + "TruthfulQA": 46.33, + "Winogrande": 56.59, + "GSM8K": 2.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.75, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8784a1ae1bd0f5f986ab0dd2cd27b514c7698251", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "EleutherAI\/pythia-1b-deduped", @@ -90986,6 +114998,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "wandb\/pruned_mistral", + "Average \u2b06\ufe0f": 32.74, + "ARC": 28.33, + "HellaSwag": 46.35, + "MMLU": 26.62, + "TruthfulQA": 41.09, + "Winogrande": 53.91, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.88, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "dc597f8e6661e96ed0c50056c38eefb857315112", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "KnutJaegersberg\/RWKV-4-PilePlus-1B5-20230520-2942-486Gtokens-ctx4096", @@ -91001,7 +115036,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 1.41, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -91070,10 +115105,10 @@ "Weight type": "Adapter", "Precision": "4bit", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 1.3, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, "Model sha": "137d483d1dc757c81c59bd190016f7c5df01f978", "Flagged": false, "MoE": false @@ -91147,6 +115182,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "DatPySci\/pythia-1b-self-kto-iter0", + "Average \u2b06\ufe0f": 32.5, + "ARC": 30.2, + "HellaSwag": 49.06, + "MMLU": 24.11, + "TruthfulQA": 36.35, + "Winogrande": 53.43, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "47f394e1df169f2264859757f6a092de4172c15e", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "bigscience\/bloom-1b1", @@ -91164,7 +115222,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 1.06, - "Hub \u2764\ufe0f": 50.0, + "Hub \u2764\ufe0f": 53.0, "Available on the hub": true, "Model sha": "6f4195539db0eef1c9d010289f32e0645d9a2354", "Flagged": false, @@ -91187,7 +115245,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 3.8, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "c20e42bd49a3b1b0d0a07151899a322c4760e871", "Flagged": false, @@ -91285,6 +115343,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "DatPySci\/pythia-1b-kto-iter0", + "Average \u2b06\ufe0f": 32.43, + "ARC": 30.12, + "HellaSwag": 48.95, + "MMLU": 24.39, + "TruthfulQA": 36.4, + "Winogrande": 53.12, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a188b55a7680083715f5adde3994cf5620e0a978", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "FabbriSimo01\/Bloom_1b_Quantized", @@ -91325,7 +115406,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 1.3, - "Hub \u2764\ufe0f": 56.0, + "Hub \u2764\ufe0f": 73.0, "Available on the hub": true, "Model sha": "e04e04028d6345ab3225644cd615e2573ffb9b8c", "Flagged": false, @@ -91515,6 +115596,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "daekeun-ml\/phi-2-ko-v0.1", + "Average \u2b06\ufe0f": 32.16, + "ARC": 30.72, + "HellaSwag": 37.26, + "MMLU": 27.34, + "TruthfulQA": 43.64, + "Winogrande": 52.72, + "GSM8K": 1.29, + "Type": "continuously pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-3.0", + "#Params (B)": 2.86, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "5c366413d429ce7c72ca34fac94db6651d9e8b80", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "rinna\/bilingual-gpt-neox-4b", @@ -91580,12 +115684,35 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "9e2d5d7a6189762164690a2fe714b00ce497b253", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "openai-community\/gpt2-large", + "Average \u2b06\ufe0f": 32.07, + "ARC": 25.77, + "HellaSwag": 45.62, + "MMLU": 26.07, + "TruthfulQA": 38.72, + "Winogrande": 55.41, + "GSM8K": 0.83, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.81, + "Hub \u2764\ufe0f": 213.0, + "Available on the hub": true, + "Model sha": "32b71b12589c2f8d625668d2335a01cac3249519", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "LordNoah\/Alpaca_refine_gpt2_e1_se0", @@ -91649,7 +115776,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "9e2d5d7a6189762164690a2fe714b00ce497b253", "Flagged": false, @@ -91695,7 +115822,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 7.0, "Available on the hub": true, "Model sha": "9e2d5d7a6189762164690a2fe714b00ce497b253", "Flagged": false, @@ -91742,7 +115869,7 @@ "Hub License": "?", "#Params (B)": 1.1, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c1f1ef67c12e4bb85fe0bdf1747c645a202cc118", "Flagged": false, "MoE": false @@ -91856,7 +115983,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 7.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "68282fe744c69ea2e4420a4a6833c0b9168215eb", "Flagged": false, @@ -92109,7 +116236,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": false, "Model sha": "6f2924e354c3ab035aa2ff7c7e28d0e5327e2667", "Flagged": false, @@ -92249,7 +116376,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 13.02, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": false, "Model sha": "6f2924e354c3ab035aa2ff7c7e28d0e5327e2667", "Flagged": false, @@ -92318,7 +116445,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "e1c5ef4ebb97afa0db09ec3e520f0487ca350bbe", "Flagged": false, @@ -92548,7 +116675,7 @@ "Merged": false, "Hub License": "agpl-3.0", "#Params (B)": 1.52, - "Hub \u2764\ufe0f": 59.0, + "Hub \u2764\ufe0f": 61.0, "Available on the hub": true, "Model sha": "bef2c90128c00ff6f16c0f397463423b7d988e17", "Flagged": false, @@ -92577,6 +116704,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "nnheui\/pythia-410m-sft-full", + "Average \u2b06\ufe0f": 31.12, + "ARC": 26.54, + "HellaSwag": 40.0, + "MMLU": 25.49, + "TruthfulQA": 40.21, + "Winogrande": 53.43, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.35, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4fd9c56aba82a5a7e93369d3a9e894e277d24841", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nnheui\/pythia-410m-sft-full", + "Average \u2b06\ufe0f": 31.06, + "ARC": 26.11, + "HellaSwag": 39.92, + "MMLU": 25.28, + "TruthfulQA": 40.11, + "Winogrande": 53.67, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4fd9c56aba82a5a7e93369d3a9e894e277d24841", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Mikivis\/gpt2-large-lora-sft1", @@ -92694,7 +116867,7 @@ }, { "T": "\ud83d\udd36", - "Model": "KaeriJenti\/Kaori-34b-v2", + "Model": "KaeriJenti\/kaori-34b-v4", "Average \u2b06\ufe0f": 30.97, "ARC": 23.89, "HellaSwag": 28.97, @@ -92711,13 +116884,13 @@ "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "e28a7b27201045a0ca9b1504c5bae53428f2c0ba", + "Model sha": "94628cc31b1acac36a464edbfea09949bca139b7", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "KaeriJenti\/kaori-34b-v4", + "Model": "KaeriJenti\/Kaori-34b-v2", "Average \u2b06\ufe0f": 30.97, "ARC": 23.89, "HellaSwag": 28.97, @@ -92734,7 +116907,7 @@ "#Params (B)": 34.39, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "94628cc31b1acac36a464edbfea09949bca139b7", + "Model sha": "e28a7b27201045a0ca9b1504c5bae53428f2c0ba", "Flagged": false, "MoE": false }, @@ -92784,6 +116957,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/GPT2-774M-CINDER-SHOW-MULTI-CHAT", + "Average \u2b06\ufe0f": 30.87, + "ARC": 26.54, + "HellaSwag": 39.69, + "MMLU": 25.8, + "TruthfulQA": 37.15, + "Winogrande": 52.17, + "GSM8K": 3.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4262c2b9647c19a2b1dbf876f9e93e57643eb7d2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Corianas\/Quokka_1.3b", @@ -92853,6 +117049,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Tinyllama-616M-Cinder", + "Average \u2b06\ufe0f": 30.73, + "ARC": 26.45, + "HellaSwag": 36.4, + "MMLU": 24.86, + "TruthfulQA": 43.41, + "Winogrande": 53.28, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9556943a1a039272f052231e1626ba606994f43e", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "cmarkea\/bloomz-560m-sft-chat", @@ -92894,7 +117113,7 @@ "Hub License": "?", "#Params (B)": 0.56, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "20529d47b0a82343014727edd1639a9a6a6b09e6", "Flagged": false, "MoE": false @@ -92916,7 +117135,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 0.56, - "Hub \u2764\ufe0f": 90.0, + "Hub \u2764\ufe0f": 93.0, "Available on the hub": true, "Model sha": "a2845d7e13dd12efae154a9f1c63fcc2e0cc4b05", "Flagged": false, @@ -92940,7 +117159,7 @@ "Hub License": "?", "#Params (B)": 16.22, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "12190f743a19e91dfe1f5c77abc0c1bf486073dd", "Flagged": false, "MoE": false @@ -92968,6 +117187,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Minami-su\/Qwen1.5-7B-Chat_mistral", + "Average \u2b06\ufe0f": 30.49, + "ARC": 24.49, + "HellaSwag": 26.69, + "MMLU": 25.78, + "TruthfulQA": 52.33, + "Winogrande": 53.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "b159c4dc7f9d9fa6c5b799325df6964b653e30cc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "xhyi\/PT_GPTNEO350_ATG", @@ -93198,6 +117440,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Llama-160M-Chat-v1", + "Average \u2b06\ufe0f": 30.28, + "ARC": 24.74, + "HellaSwag": 35.32, + "MMLU": 26.14, + "TruthfulQA": 44.16, + "Winogrande": 51.3, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "06b255f112080b26c62e72404331421ffcb95293", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "vicgalle\/Miqu-6B-truthy", @@ -93221,28 +117486,51 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral-7b-v2-selfplay-v1", + "Average \u2b06\ufe0f": 30.25, + "ARC": 31.91, + "HellaSwag": 30.89, + "MMLU": 53.02, + "TruthfulQA": 0.0, + "Winogrande": 65.67, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf53e3ac89cff2709d85c3657204208e277518f3", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "Felladrin\/Llama-160M-Chat-v1", - "Average \u2b06\ufe0f": 30.27, - "ARC": 24.74, - "HellaSwag": 35.29, - "MMLU": 26.13, - "TruthfulQA": 44.16, - "Winogrande": 51.3, + "Model": "chlee10\/T3Q-MSlerp-7Bx2", + "Average \u2b06\ufe0f": 30.24, + "ARC": 28.41, + "HellaSwag": 25.46, + "MMLU": 25.91, + "TruthfulQA": 47.28, + "Winogrande": 54.38, "GSM8K": 0.0, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 0.16, - "Hub \u2764\ufe0f": 4.0, + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "06b255f112080b26c62e72404331421ffcb95293", + "Model sha": "aa3ac6b1f0739b40674cb32d30e8b1d196dfdbdc", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udfe2", @@ -93282,10 +117570,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "06253ee259e6b205c4734ab6ec3fa850737b2110", "Flagged": false, "MoE": false @@ -93353,12 +117641,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.46, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "a1c0d260967efd02b197d525ce2802d42a3fb694", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "lqtrung1998\/Codellama-7b-hf-ReFT-Rerank-GSM8k", + "Average \u2b06\ufe0f": 30.18, + "ARC": 29.27, + "HellaSwag": 26.13, + "MMLU": 24.64, + "TruthfulQA": 49.97, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForSequenceClassification", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b863eff60d154ed4d68349f75550377f9ff7fefc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "KnutJaegersberg\/RWKV-4-PilePlus-430M-20230520-6162-1018Gtokens-ctx4098", @@ -93374,7 +117685,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 0.38, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -93422,7 +117733,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.46, - "Hub \u2764\ufe0f": 145.0, + "Hub \u2764\ufe0f": 152.0, "Available on the hub": true, "Model sha": "77b8a976440e7d1ea5a890eaf1e0175b1cac0078", "Flagged": false, @@ -93491,7 +117802,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.33, - "Hub \u2764\ufe0f": 12.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "83ce2f4e78d308968cf7ecd03d86a1f64aea8336", "Flagged": false, @@ -93512,10 +117823,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "", "#Params (B)": 0.02, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "65bd72580520a1d4a0c19fcb23f68c1f28464e1b", "Flagged": false, "MoE": false @@ -93537,7 +117848,7 @@ "Merged": false, "Hub License": "bigscience-bloom-rail-1.0", "#Params (B)": 0.56, - "Hub \u2764\ufe0f": 312.0, + "Hub \u2764\ufe0f": 317.0, "Available on the hub": true, "Model sha": "4f42c91d806a19ae1a46af6c3fb5f4990d884cd6", "Flagged": false, @@ -93584,7 +117895,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "06253ee259e6b205c4734ab6ec3fa850737b2110", "Flagged": false, "MoE": false @@ -93630,7 +117941,7 @@ "Hub License": "?", "#Params (B)": 0.33, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9351bd3b7ded60bcf170d81fd3a6040ea431a8de", "Flagged": false, "MoE": false @@ -93672,7 +117983,7 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.7, "Hub \u2764\ufe0f": 0.0, @@ -93696,10 +118007,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b0dae937b7137790d8946794375e1affd51c760a", "Flagged": false, "MoE": false @@ -93721,7 +118032,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 1.14, - "Hub \u2764\ufe0f": 47.0, + "Hub \u2764\ufe0f": 49.0, "Available on the hub": true, "Model sha": "182f0165fdf8da9c9935901eec65c94337f01c11", "Flagged": false, @@ -93745,7 +118056,7 @@ "Hub License": "?", "#Params (B)": 1.32, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "502e70081df53edc8a9156acf5a26a11a9dad8fb", "Flagged": false, "MoE": false @@ -93790,7 +118101,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.35, - "Hub \u2764\ufe0f": 104.0, + "Hub \u2764\ufe0f": 108.0, "Available on the hub": true, "Model sha": "cb32f77e905cccbca1d970436fb0f5e6b58ee3c5", "Flagged": false, @@ -93860,7 +118171,7 @@ "Hub License": "?", "#Params (B)": 1.31, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9fd01ce09da870fc66af88616d43e53db642ef46", "Flagged": false, "MoE": false @@ -93928,7 +118239,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 0.35, - "Hub \u2764\ufe0f": 52.0, + "Hub \u2764\ufe0f": 53.0, "Available on the hub": false, "Model sha": "d65832d913f6b396e2ffb64c373d9383c9da9303", "Flagged": false, @@ -93997,8 +118308,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.03, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, "Model sha": "8bf7ba0c5552fd7377c75e0ad8e6030a16234f86", "Flagged": false, "MoE": false @@ -94115,7 +118426,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "eab22794d6cf39c945f7dc326c9785a5abf88ddd", "Flagged": false, "MoE": false @@ -94138,7 +118449,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f08d224deae510ebf1408ce38bc2610b1e4c77eb", "Flagged": false, "MoE": false @@ -94183,7 +118494,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 9.04, - "Hub \u2764\ufe0f": 177.0, + "Hub \u2764\ufe0f": 179.0, "Available on the hub": true, "Model sha": "cc30c031fd795ee3d3a50312ab4549415bfbdb46", "Flagged": false, @@ -94298,12 +118609,35 @@ "Merged": false, "Hub License": "gpl-3.0", "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 262.0, + "Hub \u2764\ufe0f": 267.0, "Available on the hub": true, "Model sha": "fccf34387d2c9f2f95ff59ae380e6de3718e41ff", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "monology\/mixtral-soup", + "Average \u2b06\ufe0f": 29.82, + "ARC": 23.98, + "HellaSwag": 27.08, + "MMLU": 26.25, + "TruthfulQA": 49.94, + "Winogrande": 51.7, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9d8a942dace21a8104f0e8ff6b3d85aee82e4cd2", + "Flagged": false, + "MoE": true + }, { "T": "?", "Model": "Panchovix\/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k", @@ -94327,6 +118661,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Minami-su\/roleplay_alpaca_llama_lora", + "Average \u2b06\ufe0f": 29.8, + "ARC": 27.65, + "HellaSwag": 25.99, + "MMLU": 27.04, + "TruthfulQA": 48.63, + "Winogrande": 49.49, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bc79883dd53a993dbe1c100ae6f40811179a382d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "vihangd\/neuralfalcon-1b-v1", @@ -94459,7 +118816,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 238.09, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "323a18e2bc3c2fada3daefe71befe616354fd6eb", "Flagged": false, @@ -94529,7 +118886,7 @@ "Hub License": "?", "#Params (B)": 0.33, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d1cba6a82e52f551953e1d47bdaca262a2989f9d", "Flagged": false, "MoE": false @@ -94557,6 +118914,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "0x7o\/BulgakovLM-3B", + "Average \u2b06\ufe0f": 29.72, + "ARC": 28.33, + "HellaSwag": 26.57, + "MMLU": 24.99, + "TruthfulQA": 47.93, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e0c6683dd5d2aa9bb306d2292c2a0f91f36e636", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Felladrin\/Llama-68M-Chat-v1", @@ -94574,7 +118954,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.07, - "Hub \u2764\ufe0f": 3.0, + "Hub \u2764\ufe0f": 4.0, "Available on the hub": true, "Model sha": "f60895b5cf4e4f2c9387c6c851a4f6691c40ce95", "Flagged": false, @@ -94603,6 +118983,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "team-lucid\/mptk-1b", + "Average \u2b06\ufe0f": 29.7, + "ARC": 24.06, + "HellaSwag": 35.61, + "MMLU": 26.95, + "TruthfulQA": 39.71, + "Winogrande": 51.07, + "GSM8K": 0.83, + "Type": "pretrained", + "Architecture": "MptForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "382a746dfb0745bab2b2e63a1e6a28ba1aa3f306", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Tinyllama-320M-Cinder-v1", + "Average \u2b06\ufe0f": 29.69, + "ARC": 27.73, + "HellaSwag": 29.68, + "MMLU": 24.52, + "TruthfulQA": 44.3, + "Winogrande": 51.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.34, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "89290f10ce5b9fcc2a27d2e297eb244cc866da2b", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "danielpark\/gorani-100k-llama2-13b-instruct", @@ -94667,7 +119093,7 @@ "Hub License": "?", "#Params (B)": 0.14, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4807e7df1dfb9d60c6d98e3cfeff62cb6b9a1579", "Flagged": false, "MoE": false @@ -94687,10 +119113,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "cc-by-nc-4.0", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "ee9b0cf26f521b5cb2322d743880e8b6bfadb0b7", "Flagged": false, "MoE": false @@ -94732,7 +119158,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 11.6, "Hub \u2764\ufe0f": 0.0, @@ -94764,6 +119190,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "MatthieuJ\/ING_Triomphant_M2_SLERP", + "Average \u2b06\ufe0f": 29.62, + "ARC": 27.22, + "HellaSwag": 26.45, + "MMLU": 24.21, + "TruthfulQA": 48.79, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4962111e068a187dfe8ba76f4b612281c6496f87", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BFauber\/opt125m_10e5", @@ -94810,6 +119259,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "chihoonlee10\/T3Q-MSlerp-13B", + "Average \u2b06\ufe0f": 29.61, + "ARC": 27.65, + "HellaSwag": 25.85, + "MMLU": 26.26, + "TruthfulQA": 48.01, + "Winogrande": 49.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e0e967ea95b34436f54dd00340b5fd4da51e7d10", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "openbmb\/UltraRM-13b", @@ -94825,9 +119297,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 12.85, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 46.0, "Available on the hub": true, "Model sha": "4b231ae58c15244e6e15f0d2f4e26ec37b846229", "Flagged": false, @@ -94919,7 +119391,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.56, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "82bd8b88b95068eee614a35b790388c5d2415705", "Flagged": false, @@ -94948,6 +119420,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "G-reen\/EXPERIMENT-DPO-m7b2-3-merged", + "Average \u2b06\ufe0f": 29.55, + "ARC": 29.52, + "HellaSwag": 25.9, + "MMLU": 23.12, + "TruthfulQA": 48.27, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1f34fad9a39b6b3e5dfad6898c8654a99ea8e8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "JackFram\/llama-160m", + "Average \u2b06\ufe0f": 29.55, + "ARC": 24.83, + "HellaSwag": 35.23, + "MMLU": 24.26, + "TruthfulQA": 42.08, + "Winogrande": 50.83, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "aca9b687d1425f863dcf5de9a4c96e3fe36266dd", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "facebook\/xglm-564M", @@ -94965,7 +119483,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.56, - "Hub \u2764\ufe0f": 38.0, + "Hub \u2764\ufe0f": 41.0, "Available on the hub": true, "Model sha": "f3059f01b98ccc877c673149e0178c0e957660f9", "Flagged": false, @@ -94986,7 +119504,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 0.75, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -94994,6 +119512,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-2-3", + "Average \u2b06\ufe0f": 29.55, + "ARC": 25.6, + "HellaSwag": 25.66, + "MMLU": 27.07, + "TruthfulQA": 47.99, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0e6c655f2ab8185961d7babc0dbf79f6091e89e8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Abe13\/juniper-certificate-Llama-2-7b-chat-hf", @@ -95126,7 +119667,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 64.0, + "Hub \u2764\ufe0f": 65.0, "Available on the hub": false, "Model sha": "8201db0de8deb68f25e7309db04d163b71970494", "Flagged": false, @@ -95149,7 +119690,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 319.0, + "Hub \u2764\ufe0f": 321.0, "Available on the hub": true, "Model sha": "132eb6b6cedaf579c2f333f1ecd78a16d7e45978", "Flagged": false, @@ -95170,7 +119711,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", + "Hub License": "?", "#Params (B)": 10.73, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -95219,7 +119760,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "22a88e62529dc2cc95991478cd87e6c588237258", "Flagged": false, "MoE": false @@ -95265,7 +119806,7 @@ "Hub License": "?", "#Params (B)": 7.58, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "52d285a1d9bdd52e50a4cd10b9de43f2f4332517", "Flagged": false, "MoE": false @@ -95311,7 +119852,7 @@ "Hub License": "?", "#Params (B)": 6.61, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "7444355ad764584ef05805f58ccf174bb03e0f46", "Flagged": false, "MoE": false @@ -95333,7 +119874,7 @@ "Merged": false, "Hub License": null, "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 94.0, + "Hub \u2764\ufe0f": 96.0, "Available on the hub": false, "Model sha": "065248a99f051da363b1c2cbf05da943c8b6211b", "Flagged": false, @@ -95379,7 +119920,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.15, - "Hub \u2764\ufe0f": 151.0, + "Hub \u2764\ufe0f": 159.0, "Available on the hub": true, "Model sha": "6cb0d322a3a484e99667e7cb240e22f1ac036b99", "Flagged": false, @@ -95454,6 +119995,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "zelus82\/JuliusCesar-72B-BeyonderV.0", + "Average \u2b06\ufe0f": 29.46, + "ARC": 26.02, + "HellaSwag": 26.24, + "MMLU": 23.12, + "TruthfulQA": 49.89, + "Winogrande": 51.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 37.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "07854414580231d4048de6cd7e1723425c1961db", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "porkorbeef\/Llama-2-13b-public", @@ -95469,10 +120033,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e1b32a8fcfc0f37fd5f50cf765151897574c73c7", "Flagged": false, "MoE": false @@ -95500,6 +120064,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "abideen\/Mistral-v0.2-orpo", + "Average \u2b06\ufe0f": 29.45, + "ARC": 27.99, + "HellaSwag": 26.41, + "MMLU": 23.12, + "TruthfulQA": 49.85, + "Winogrande": 49.33, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1dbaad225a1568e48abf33dad4365dd9a51ca27f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "BEE-spoke-data\/smol_llama-220M-GQA", @@ -95517,7 +120104,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.22, - "Hub \u2764\ufe0f": 8.0, + "Hub \u2764\ufe0f": 9.0, "Available on the hub": true, "Model sha": "2d144b9a69b3620110e8a14790d383076ac87925", "Flagged": false, @@ -95541,11 +120128,34 @@ "Hub License": "?", "#Params (B)": 0.12, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "f01e73ba67da96f6645be3067158cc493b0cbbcb", "Flagged": false, "MoE": false }, + { + "T": "\ud83e\udd1d", + "Model": "monology\/mixtral-ties", + "Average \u2b06\ufe0f": 29.43, + "ARC": 26.45, + "HellaSwag": 26.19, + "MMLU": 24.05, + "TruthfulQA": 48.75, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "921017cf0f80cdaf03434dc90be294d05d1ad7cd", + "Flagged": false, + "MoE": true + }, { "T": "\ud83d\udd36", "Model": "KoboldAI\/fairseq-dense-125M", @@ -95569,6 +120179,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "princeton-nlp\/Sheared-Pythia-160m", + "Average \u2b06\ufe0f": 29.41, + "ARC": 22.44, + "HellaSwag": 32.07, + "MMLU": 26.65, + "TruthfulQA": 43.22, + "Winogrande": 51.7, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c8889f496254bae7b6196dfd64521e1581eb5567", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "bigcode\/tiny_starcoder_py", @@ -95586,7 +120219,7 @@ "Merged": false, "Hub License": "bigcode-openrail-m", "#Params (B)": 0.16, - "Hub \u2764\ufe0f": 67.0, + "Hub \u2764\ufe0f": 66.0, "Available on the hub": true, "Model sha": "8547527bef0bc927268c1653cce6948c5c242dd1", "Flagged": false, @@ -95639,8 +120272,8 @@ "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "breadlicker45\/dough-instruct-base-001", + "T": "\ud83d\udd36", + "Model": "breadlicker45\/dough-base-001", "Average \u2b06\ufe0f": 29.37, "ARC": 23.89, "HellaSwag": 24.76, @@ -95648,22 +120281,22 @@ "TruthfulQA": 53.4, "Winogrande": 51.07, "GSM8K": 0.0, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": null, - "#Params (B)": 0.19, + "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "3e1b0bf0a887feeb342982eee4f6d8041772a7dd", + "Model sha": "e42b65191f97d786eadaba450f1d34baea470734", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "breadlicker45\/dough-base-001", + "T": "\ud83d\udcac", + "Model": "breadlicker45\/dough-instruct-base-001", "Average \u2b06\ufe0f": 29.37, "ARC": 23.89, "HellaSwag": 24.76, @@ -95671,16 +120304,39 @@ "TruthfulQA": 53.4, "Winogrande": 51.07, "GSM8K": 0.0, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": null, - "#Params (B)": 0.0, + "#Params (B)": 0.19, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "e42b65191f97d786eadaba450f1d34baea470734", + "Model sha": "3e1b0bf0a887feeb342982eee4f6d8041772a7dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zelus82\/Asterix-B7", + "Average \u2b06\ufe0f": 29.37, + "ARC": 28.16, + "HellaSwag": 25.65, + "MMLU": 24.59, + "TruthfulQA": 47.24, + "Winogrande": 50.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Delta", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2885da230c05730dff0501b95aa18c533b63017e", "Flagged": false, "MoE": false }, @@ -95701,7 +120357,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.11, - "Hub \u2764\ufe0f": 243.0, + "Hub \u2764\ufe0f": 244.0, "Available on the hub": true, "Model sha": "af2ef45ef8cbe82eb7eb4074f260412bc14c7b11", "Flagged": false, @@ -95836,14 +120492,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 21.51, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, "Model sha": "3e32f163db0a5d25d00f9d1c8aff0a3666f2b25e", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -95870,7 +120526,7 @@ }, { "T": "\ud83d\udd36", - "Model": "Technoculture\/Mediquad-orca-20B", + "Model": "Technoculture\/Medorca-4x7b", "Average \u2b06\ufe0f": 29.35, "ARC": 29.35, "HellaSwag": 25.72, @@ -95882,18 +120538,18 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": false, + "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 19.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "6a5a811206e5c255dff8128334c06924347ae324", + "Available on the hub": true, + "Model sha": "70fa312cca9f7d966c37ccb52f0ce6a2aa2fd3a0", "Flagged": false, "MoE": true }, { "T": "\ud83d\udd36", - "Model": "Technoculture\/Medorca-4x7b", + "Model": "Technoculture\/Mediquad-orca-20B", "Average \u2b06\ufe0f": 29.35, "ARC": 29.35, "HellaSwag": 25.72, @@ -95905,14 +120561,14 @@ "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "apache-2.0", + "Merged": false, + "Hub License": "?", "#Params (B)": 19.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "70fa312cca9f7d966c37ccb52f0ce6a2aa2fd3a0", + "Available on the hub": false, + "Model sha": "6a5a811206e5c255dff8128334c06924347ae324", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", @@ -95937,6 +120593,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-0-3", + "Average \u2b06\ufe0f": 29.34, + "ARC": 27.3, + "HellaSwag": 27.59, + "MMLU": 24.7, + "TruthfulQA": 43.73, + "Winogrande": 52.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e57e848c73f812b324109ffea29e60443979d4f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "BEE-spoke-data\/smol_llama-220M-openhermes", @@ -96067,7 +120746,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "llama2", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -96098,6 +120777,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-1-3", + "Average \u2b06\ufe0f": 29.31, + "ARC": 25.0, + "HellaSwag": 27.42, + "MMLU": 24.03, + "TruthfulQA": 49.05, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "22010813444e2fe8244ae5e5313489b61a5b12ec", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "Harshvir\/LaMini-Neo-1.3B-Mental-Health_lora", @@ -96182,10 +120884,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "d9f3e490df2134784afc3a86f5c617a9bab8db4d", "Flagged": false, "MoE": false @@ -96207,7 +120909,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 242.0, + "Hub \u2764\ufe0f": 250.0, "Available on the hub": true, "Model sha": "04e3e47b52dadbcf7688aa61a7ed0438ecf9184c", "Flagged": false, @@ -96228,10 +120930,10 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "", "#Params (B)": 0.18, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e3d26f736b8b47d5275421be6133b81bef84db7d", "Flagged": false, "MoE": false @@ -96277,7 +120979,7 @@ "Hub License": "?", "#Params (B)": 12.85, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "2ea86d3c02ca0c2abb086a2145e1e85eaea4a23e", "Flagged": false, "MoE": false @@ -96322,12 +121024,35 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 0.6, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, "Model sha": "5d2a0bcaa25ae455a8111a385c95b3827c972e26", "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udd36", + "Model": "playdev7\/theseed-v0.3", + "Average \u2b06\ufe0f": 29.24, + "ARC": 25.94, + "HellaSwag": 26.05, + "MMLU": 24.55, + "TruthfulQA": 46.33, + "Winogrande": 52.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 24.37, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "545fd9e47d92b243c42b521a64596f114c961b3f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "BEE-spoke-data\/NanoLlama-GQA-L10-A32_KV8-v13-KI", @@ -96443,6 +121168,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "crumb\/nano-mistral", + "Average \u2b06\ufe0f": 29.2, + "ARC": 21.67, + "HellaSwag": 28.52, + "MMLU": 25.16, + "TruthfulQA": 47.42, + "Winogrande": 52.41, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.17, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c988b8c8f84d863f9155e924884169081fbde2b8", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "BEE-spoke-data\/smol_llama-220M-open_instruct", @@ -96483,7 +121231,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.18, - "Hub \u2764\ufe0f": 75.0, + "Hub \u2764\ufe0f": 80.0, "Available on the hub": true, "Model sha": "97d0fec744c2cb4d48f5db51d17e3258e185858e", "Flagged": false, @@ -96621,12 +121369,35 @@ "Merged": false, "Hub License": "", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 21.0, + "Hub \u2764\ufe0f": 23.0, "Available on the hub": false, "Model sha": "e5f31df92bfb7b7a808ea8d1c7557488e1bdff7f", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Hemanth-thunder\/Tamil-Mistral-7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 29.16, + "ARC": 27.13, + "HellaSwag": 27.09, + "MMLU": 24.5, + "TruthfulQA": 47.3, + "Winogrande": 48.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "504c4964130f0696e387e94ee6073aa565b082e9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "Dans-DiscountModels\/TinyMistral-v2.5-MiniPile-Guidelines-E1", @@ -96650,6 +121421,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Hemanth-thunder\/Tamil-Mistral-7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 29.16, + "ARC": 27.39, + "HellaSwag": 27.16, + "MMLU": 24.42, + "TruthfulQA": 47.27, + "Winogrande": 48.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "504c4964130f0696e387e94ee6073aa565b082e9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "Dans-DiscountModels\/TinyMistral-v2.5-MiniPile-Guidelines-E1", @@ -96711,9 +121505,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 43.23, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "7094ef1fc4e032cf2c03a2f43f3db5e814bce318", "Flagged": false, @@ -96736,7 +121530,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.12, - "Hub \u2764\ufe0f": 103.0, + "Hub \u2764\ufe0f": 109.0, "Available on the hub": true, "Model sha": "3d2b5f275bdf882b8775f902e1bfdb790e2cfc32", "Flagged": false, @@ -96851,7 +121645,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 27.0, + "Hub \u2764\ufe0f": 29.0, "Available on the hub": false, "Model sha": "8cd14d5339178f1b285f55baee14a0deff7103ac", "Flagged": false, @@ -96875,7 +121669,7 @@ "Hub License": "?", "#Params (B)": 1.13, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a065961fd627aa3b3e6dde21e77fd5e20f712189", "Flagged": false, "MoE": false @@ -96944,7 +121738,7 @@ "Hub License": "?", "#Params (B)": 6.06, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e680a6b8244e9a4871aa419e2faca079d4f42381", "Flagged": false, "MoE": false @@ -97058,7 +121852,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 50.0, + "Hub \u2764\ufe0f": 51.0, "Available on the hub": false, "Model sha": "242c6469cab41b41d30826e850afa4687e422f24", "Flagged": false, @@ -97079,7 +121873,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", + "Hub License": "?", "#Params (B)": 19.56, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -97087,6 +121881,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe9", + "Model": "Hemanth-thunder\/Tamil-Mistral-7B-v0.1", + "Average \u2b06\ufe0f": 29.08, + "ARC": 28.75, + "HellaSwag": 26.52, + "MMLU": 24.28, + "TruthfulQA": 46.99, + "Winogrande": 47.91, + "GSM8K": 0.0, + "Type": "continuously pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.39, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "35c013932c92b186eeb8597b9a5261304846f029", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "OEvortex\/HelpingAI-110M", + "Average \u2b06\ufe0f": 29.05, + "ARC": 22.78, + "HellaSwag": 28.02, + "MMLU": 23.66, + "TruthfulQA": 48.25, + "Winogrande": 51.62, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.11, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "197c0107aed8e7e14d300ff4d72478b377929323", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BFauber\/opt125m_10e5_1ep", @@ -97196,7 +122036,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.21, - "Hub \u2764\ufe0f": 17.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, "Model sha": "50f5173d932e8e61f858120bcb800b97af589f46", "Flagged": false, @@ -97294,6 +122134,52 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udfe2", + "Model": "crumb\/model-a-48.5m", + "Average \u2b06\ufe0f": 28.98, + "ARC": 22.18, + "HellaSwag": 27.85, + "MMLU": 25.08, + "TruthfulQA": 46.75, + "Winogrande": 51.7, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.05, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "5aba9fe63195029ceddc2c54751be160b635586a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Thytu\/phi-2-audio-super", + "Average \u2b06\ufe0f": 28.97, + "ARC": 23.46, + "HellaSwag": 26.58, + "MMLU": 23.12, + "TruthfulQA": 49.53, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "28fffd749751b67637a5fe22288ffe9cedf5610f", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "huggingtweets\/jerma985", @@ -97357,12 +122243,35 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.1, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "cac68b3377fd0a1eb1aca92a2e661d81f59d8b08", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Minueza-32M-UltraChat", + "Average \u2b06\ufe0f": 28.97, + "ARC": 21.08, + "HellaSwag": 26.95, + "MMLU": 26.08, + "TruthfulQA": 47.7, + "Winogrande": 51.78, + "GSM8K": 0.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "512baa3b64b2a88d1e35bcd6ab4164124ba184d1", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BEE-spoke-data\/smol_llama-101M-GQA", @@ -97380,7 +122289,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.1, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 19.0, "Available on the hub": true, "Model sha": "cac68b3377fd0a1eb1aca92a2e661d81f59d8b08", "Flagged": false, @@ -97403,7 +122312,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 76.0, "Available on the hub": false, "Model sha": "815e2dd7daabe446c429f3c9f70ef01582528f81", "Flagged": false, @@ -97426,7 +122335,7 @@ "Merged": false, "Hub License": "other", "#Params (B)": 0.02, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "3930ca6bf3976e9b603815403cb373398ae509e5", "Flagged": false, @@ -97446,7 +122355,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 30.41, "Hub \u2764\ufe0f": 0.0, @@ -97472,7 +122381,7 @@ "Merged": false, "Hub License": "", "#Params (B)": 30.0, - "Hub \u2764\ufe0f": 74.0, + "Hub \u2764\ufe0f": 76.0, "Available on the hub": false, "Model sha": "815e2dd7daabe446c429f3c9f70ef01582528f81", "Flagged": false, @@ -97516,9 +122425,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 0.1, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 38.0, "Available on the hub": true, "Model sha": "2ab25ed47af79376eed2baaf8bbb7a192a0c73ff", "Flagged": false, @@ -97547,6 +122456,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "Felladrin\/Minueza-32M-Base", + "Average \u2b06\ufe0f": 28.92, + "ARC": 21.33, + "HellaSwag": 26.39, + "MMLU": 24.8, + "TruthfulQA": 47.45, + "Winogrande": 53.2, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "d05607502380476adee68810778b8752846b0bcc", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "vilm\/Mixsmol-4x400M-v0.1-epoch2", @@ -97680,7 +122612,7 @@ "Hub License": "?", "#Params (B)": 0.14, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "906d8a02bdb444159b189a153f1f5589071ed74e", "Flagged": false, "MoE": false @@ -97700,10 +122632,10 @@ "Weight type": "Adapter", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": null, "#Params (B)": 0.14, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "a558223f774bbd315d1a3890d93ab80dc720fbb1", "Flagged": false, "MoE": false @@ -97725,7 +122657,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 283.0, + "Hub \u2764\ufe0f": 288.0, "Available on the hub": true, "Model sha": "9d5c5fadcc072b693fb5a5e29416bbf3f503c26c", "Flagged": false, @@ -97746,9 +122678,9 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 0.41, - "Hub \u2764\ufe0f": 0.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, "Model sha": "8df9f96cc14be8f681c40bd1672b3f3540b70e31", "Flagged": false, @@ -97869,6 +122801,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "wtang06\/mpt-125m-c4", + "Average \u2b06\ufe0f": 28.84, + "ARC": 22.18, + "HellaSwag": 26.41, + "MMLU": 24.68, + "TruthfulQA": 49.08, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f13efec5c8498cb52998eb9ed347207f077b5f9d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "saarvajanik\/facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache", @@ -97938,6 +122893,52 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Minueza-32M-Deita", + "Average \u2b06\ufe0f": 28.8, + "ARC": 20.73, + "HellaSwag": 26.72, + "MMLU": 26.84, + "TruthfulQA": 47.75, + "Winogrande": 50.51, + "GSM8K": 0.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2523b34a5ede2ef8534521080b92380ccaace340", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Minami-su\/Qwen1.5-0.5B-Chat_mistral", + "Average \u2b06\ufe0f": 28.79, + "ARC": 25.51, + "HellaSwag": 26.41, + "MMLU": 23.08, + "TruthfulQA": 49.06, + "Winogrande": 48.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.5, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "09a21a368d0bf4a81b22772948b74f13fa066c26", + "Flagged": false, + "MoE": false + }, { "T": "?", "Model": "ByteWave\/Yi-8B-Llama", @@ -97956,7 +122957,7 @@ "Hub License": "?", "#Params (B)": 8.73, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "4f3f4d73ff3962487d1c51702b02d795bf1f33a4", "Flagged": false, "MoE": false @@ -97979,11 +122980,34 @@ "Hub License": "?", "#Params (B)": 0.07, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b288893319b6cdce499148f4482043c350116560", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/TinyMistral-248M-SFT-v3", + "Average \u2b06\ufe0f": 28.78, + "ARC": 25.68, + "HellaSwag": 25.31, + "MMLU": 24.41, + "TruthfulQA": 48.87, + "Winogrande": 48.38, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7a4787dfed21a432924d24575e6c65a97e1dd98a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "Locutusque\/TinyMistral-248M-v2", @@ -98001,7 +123025,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.25, - "Hub \u2764\ufe0f": 13.0, + "Hub \u2764\ufe0f": 14.0, "Available on the hub": true, "Model sha": "937ed7abdec98b7a9868b95e3b8a0d757b902325", "Flagged": false, @@ -98054,8 +123078,8 @@ "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "binbi\/SF-72B-V1.8.6-V1.2", + "T": "\ud83d\udcac", + "Model": "binbi\/SF-72B-V1", "Average \u2b06\ufe0f": 28.75, "ARC": 26.28, "HellaSwag": 24.87, @@ -98063,22 +123087,22 @@ "TruthfulQA": 48.78, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 72.29, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "f894446c80611e3fc174e4cf3af0e149a316b9bb", + "Model sha": "39e00bb5cbebecb7b62f3b696423127e6ca5283b", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "binbi\/SF-72B-V1", + "T": "\ud83d\udd36", + "Model": "binbi\/SF-72B-V1.8.6-V1.2", "Average \u2b06\ufe0f": 28.75, "ARC": 26.28, "HellaSwag": 24.87, @@ -98086,16 +123110,16 @@ "TruthfulQA": 48.78, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "chat models (RLHF, DPO, IFT, ...)", + "Type": "fine-tuned on domain-specific datasets", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 72.29, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "39e00bb5cbebecb7b62f3b696423127e6ca5283b", + "Model sha": "f894446c80611e3fc174e4cf3af0e149a316b9bb", "Flagged": false, "MoE": false }, @@ -98159,7 +123183,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, + "Merged": false, "Hub License": "other", "#Params (B)": 72.29, "Hub \u2764\ufe0f": 0.0, @@ -98169,23 +123193,23 @@ "MoE": false }, { - "T": "\ud83d\udd36", + "T": "\ud83d\udcac", "Model": "Felladrin\/Smol-Llama-101M-Chat-v1", "Average \u2b06\ufe0f": 28.73, "ARC": 22.87, - "HellaSwag": 28.69, + "HellaSwag": 28.71, "MMLU": 24.93, "TruthfulQA": 45.76, "Winogrande": 50.04, "GSM8K": 0.08, - "Type": "fine-tuned on domain-specific datasets", + "Type": "chat models (RLHF, DPO, IFT, ...)", "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.1, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "b7c10b0e04ef6f9811ac7f57b3a947546d288eea", "Flagged": false, @@ -98209,7 +123233,7 @@ "Hub License": "?", "#Params (B)": 0.07, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "9fce9b8252f7891dbd50299a8c3bd71cd25454db", "Flagged": false, "MoE": false @@ -98297,7 +123321,7 @@ "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 72.29, "Hub \u2764\ufe0f": 0.0, @@ -98392,7 +123416,7 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.12, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "888a0d660e498daed51fdf69da70b075452b4bf9", "Flagged": false, @@ -98513,6 +123537,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Pythia-31M-Chat-v1", + "Average \u2b06\ufe0f": 28.59, + "ARC": 21.84, + "HellaSwag": 26.81, + "MMLU": 24.55, + "TruthfulQA": 48.04, + "Winogrande": 50.28, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "e6a52e4ac98e20c7f9e39aaba9368dd6faacdad9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "saarvajanik\/facebook-opt-6.7b-qcqa-ub-16-best-for-KV-cache", @@ -98597,7 +123644,7 @@ "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 0.13, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -98722,7 +123769,7 @@ }, { "T": "\ud83d\udfe2", - "Model": "openai-community\/gpt2", + "Model": "gpt2", "Average \u2b06\ufe0f": 28.53, "ARC": 22.01, "HellaSwag": 31.53, @@ -98737,15 +123784,15 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.14, - "Hub \u2764\ufe0f": 1695.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "11c5a3d5811f50298f278a704980280950aedb10", "Flagged": false, "MoE": false }, { "T": "\ud83d\udfe2", - "Model": "gpt2", + "Model": "openai-community\/gpt2", "Average \u2b06\ufe0f": 28.53, "ARC": 22.01, "HellaSwag": 31.53, @@ -98760,8 +123807,8 @@ "Merged": false, "Hub License": "mit", "#Params (B)": 0.14, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Hub \u2764\ufe0f": 1785.0, + "Available on the hub": true, "Model sha": "11c5a3d5811f50298f278a704980280950aedb10", "Flagged": false, "MoE": false @@ -98922,11 +123969,34 @@ "Hub License": "?", "#Params (B)": 0.26, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "72df0b6d62d64002575687ea2edbb0df05712678", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Minueza-32M-Chat", + "Average \u2b06\ufe0f": 28.49, + "ARC": 20.39, + "HellaSwag": 26.54, + "MMLU": 25.75, + "TruthfulQA": 47.27, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "9722ba30871f0479ac340b1656ad31c49e330536", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sharathhebbar24\/code_gpt2_mini_model", @@ -98973,6 +124043,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "nisten\/smaugzilla-77b", + "Average \u2b06\ufe0f": 28.49, + "ARC": 24.83, + "HellaSwag": 25.16, + "MMLU": 23.05, + "TruthfulQA": 48.22, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 76.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "12c4d57705c4f7a1a2b9fd94e79ddb1cd357aa9a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "0x7194633\/nanoFialka-v1", @@ -99059,7 +124152,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 4.04, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 3.0, "Available on the hub": true, "Model sha": "7647fcf7c3aa98a04a86a65e2f774ec670994b07", "Flagged": false, @@ -99088,6 +124181,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udfe2", + "Model": "Cheng98\/llama-39m", + "Average \u2b06\ufe0f": 28.45, + "ARC": 24.06, + "HellaSwag": 25.57, + "MMLU": 24.31, + "TruthfulQA": 47.19, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.04, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7add242066017116840350cd1f6415b071faac6d", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "BEE-spoke-data\/Mixtral-GQA-400m-v2", @@ -99197,7 +124313,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.1, - "Hub \u2764\ufe0f": 20.0, + "Hub \u2764\ufe0f": 22.0, "Available on the hub": true, "Model sha": "e93a9faa9c77e5d09219f6c868bfc7a1bd65593c", "Flagged": false, @@ -99274,7 +124390,7 @@ }, { "T": "\ud83d\udcac", - "Model": "lgaalves\/gpt2_camel_physics-platypus", + "Model": "lgaalves\/gpt2_platypus-camel_physics", "Average \u2b06\ufe0f": 28.41, "ARC": 23.04, "HellaSwag": 31.32, @@ -99283,21 +124399,21 @@ "Winogrande": 49.64, "GSM8K": 0.0, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "GPT2LMHeadModel", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "mit", + "Hub License": "?", "#Params (B)": 0.12, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "66165ff32ed8de6c39f3524a810f5e97ba6d3347", "Flagged": false, "MoE": false }, { "T": "\ud83d\udcac", - "Model": "lgaalves\/gpt2_platypus-camel_physics", + "Model": "lgaalves\/gpt2_camel_physics-platypus", "Average \u2b06\ufe0f": 28.41, "ARC": 23.04, "HellaSwag": 31.32, @@ -99306,11 +124422,11 @@ "Winogrande": 49.64, "GSM8K": 0.0, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "Unknown", + "Architecture": "GPT2LMHeadModel", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "mit", "#Params (B)": 0.12, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, @@ -99382,7 +124498,7 @@ "Hub License": "?", "#Params (B)": 0.12, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "cd4d700d13b3bc9371bf45616ef74ac20d165c3d", "Flagged": false, "MoE": false @@ -99405,7 +124521,7 @@ "Hub License": "?", "#Params (B)": 0.59, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "bab37eb7ba63f6ff9f0eb36a85727146b82ae5ed", "Flagged": false, "MoE": false @@ -99425,7 +124541,7 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "cc-by-nc-4.0", + "Hub License": "?", "#Params (B)": 120.61, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, @@ -99589,7 +124705,7 @@ "Hub License": "?", "#Params (B)": 0.12, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e12dbd27ee148ce4af6faf742aa936d38c26536f", "Flagged": false, "MoE": false @@ -99682,7 +124798,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 0.25, - "Hub \u2764\ufe0f": 19.0, + "Hub \u2764\ufe0f": 23.0, "Available on the hub": true, "Model sha": "99c8efd7bc4aba7939e20b7e9e3a46b542cae713", "Flagged": false, @@ -99729,7 +124845,7 @@ "Hub License": "mit", "#Params (B)": 0.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, + "Available on the hub": true, "Model sha": "54f816e4cc09d5e3615da5a0eedb67b2be529cd9", "Flagged": false, "MoE": false @@ -99752,7 +124868,7 @@ "Hub License": "?", "#Params (B)": 0.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "e8e347b02f9305e4bc144eb9be2821c518d43183", "Flagged": false, "MoE": false @@ -99912,8 +125028,8 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.25, - "Hub \u2764\ufe0f": 23.0, - "Available on the hub": true, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, "Model sha": "ec0ff201527cd9b50eb9b4fc754d6c08f1242ea1", "Flagged": false, "MoE": false @@ -100079,6 +125195,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Minueza-32Mx2-Chat", + "Average \u2b06\ufe0f": 28.12, + "ARC": 20.14, + "HellaSwag": 26.36, + "MMLU": 26.07, + "TruthfulQA": 44.56, + "Winogrande": 51.62, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.04, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "79ede1f05e0f7090ca2f002cdaf2b3bbfb1b5ee9", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "Sharathhebbar24\/math_gpt2_sft", @@ -100142,7 +125281,7 @@ "Merged": false, "Hub License": "cc-by-nc-4.0", "#Params (B)": 0.12, - "Hub \u2764\ufe0f": 16.0, + "Hub \u2764\ufe0f": 17.0, "Available on the hub": true, "Model sha": "5c67c8c03c08e82d6138ce2a1eddf5317fac3a6b", "Flagged": false, @@ -100257,7 +125396,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 1.0, - "Hub \u2764\ufe0f": 6.0, + "Hub \u2764\ufe0f": 8.0, "Available on the hub": true, "Model sha": "6004505aa44f0101f69c6e1bf29722c863858c7b", "Flagged": false, @@ -100372,7 +125511,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.11, - "Hub \u2764\ufe0f": 69.0, + "Hub \u2764\ufe0f": 71.0, "Available on the hub": true, "Model sha": "d2b54d7af419055f204690fe0385959616a1723e", "Flagged": false, @@ -100396,7 +125535,7 @@ "Hub License": "?", "#Params (B)": 0.25, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "8f03f72bca0542aa164c29ba41f02cba6f9d7748", "Flagged": false, "MoE": false @@ -100418,7 +125557,7 @@ "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 0.25, - "Hub \u2764\ufe0f": 9.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, "Model sha": "0490a521f39dfdf3e50a500773cd1772322b66a9", "Flagged": false, @@ -100441,7 +125580,7 @@ "Merged": false, "Hub License": "apache-2.0", "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 211.0, + "Hub \u2764\ufe0f": 220.0, "Available on the hub": true, "Model sha": "40897bd7c8b47a76802c411108ca6220438b8b40", "Flagged": false, @@ -100449,7 +125588,7 @@ }, { "T": "\ud83d\udd36", - "Model": "huashiyiqike\/testmodel", + "Model": "Corianas\/111m", "Average \u2b06\ufe0f": 27.6, "ARC": 19.71, "HellaSwag": 26.68, @@ -100464,15 +125603,15 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 0.15, - "Hub \u2764\ufe0f": 1.0, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, - "Model sha": "1ac5d244402e2433b6abfcff1fe65e84af15766b", + "Model sha": "ee58d79e27f8b9e3984aab29235c5851d2be01d4", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "Corianas\/111m", + "Model": "huashiyiqike\/testmodel", "Average \u2b06\ufe0f": 27.6, "ARC": 19.71, "HellaSwag": 26.68, @@ -100487,78 +125626,170 @@ "Merged": false, "Hub License": "cc-by-nc-sa-4.0", "#Params (B)": 0.15, - "Hub \u2764\ufe0f": 2.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "ee58d79e27f8b9e3984aab29235c5851d2be01d4", + "Model sha": "1ac5d244402e2433b6abfcff1fe65e84af15766b", "Flagged": false, "MoE": false }, { "T": "\ud83d\udcac", - "Model": "Felladrin\/TinyMistral-248M-SFT-v3", - "Average \u2b06\ufe0f": 27.45, - "ARC": 21.93, - "HellaSwag": 28.26, - "MMLU": 22.91, - "TruthfulQA": 40.03, - "Winogrande": 51.54, + "Model": "Felladrin\/TinyMistral-248M-Chat-v1", + "Average \u2b06\ufe0f": 27.01, + "ARC": 21.59, + "HellaSwag": 27.45, + "MMLU": 23.08, + "TruthfulQA": 40.91, + "Winogrande": 49.01, "GSM8K": 0.0, "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "Unknown", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "?", + "Hub License": "apache-2.0", "#Params (B)": 0.25, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, - "Model sha": "7a4787dfed21a432924d24575e6c65a97e1dd98a", + "Available on the hub": false, + "Model sha": "0a9bb94974cbc12c049fc16b0a5b3755532df78f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "khyat\/gujju-llama-instruct-v1.0", + "Average \u2b06\ufe0f": 25.41, + "ARC": 24.49, + "HellaSwag": 51.24, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 53.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9aa081f889d966c6364ab524ece82bf194c193ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v17.2-32k", + "Average \u2b06\ufe0f": 23.07, + "ARC": 33.53, + "HellaSwag": 31.36, + "MMLU": 17.8, + "TruthfulQA": 0.0, + "Winogrande": 55.72, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d61589d9e263af809f20f452af68749ff85d0163", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "databricks\/dolly-v2-3b", + "Average \u2b06\ufe0f": 22.83, + "ARC": 25.26, + "HellaSwag": 26.55, + "MMLU": 24.7, + "TruthfulQA": 0.0, + "Winogrande": 59.43, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 275.0, + "Available on the hub": true, + "Model sha": "f6c9be08f16fe4d3a719bee0a4a7c7415b5c65df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral-7b-v2-selfplay-v0", + "Average \u2b06\ufe0f": 22.68, + "ARC": 29.44, + "HellaSwag": 26.17, + "MMLU": 25.38, + "TruthfulQA": 0.0, + "Winogrande": 55.09, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3e491e05f30398f11226cecff0ae1abf3a2fc61d", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v17.2-32k", - "Average \u2b06\ufe0f": 23.07, - "ARC": 33.53, - "HellaSwag": 31.36, - "MMLU": 17.8, + "T": "\ud83d\udd36", + "Model": "Severian\/Nexus-IKM-Hermes-2-Pro-Mistral-7B", + "Average \u2b06\ufe0f": 22.65, + "ARC": 29.27, + "HellaSwag": 29.33, + "MMLU": 25.16, "TruthfulQA": 0.0, - "Winogrande": 55.72, + "Winogrande": 52.17, "GSM8K": 0.0, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "MixtralForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralModel", "Weight type": "Original", - "Precision": "bfloat16", + "Precision": "float16", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 46.74, - "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "d61589d9e263af809f20f452af68749ff85d0163", + "Hub License": "mit", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "77e713b12722e8cc68268618bdc03a1c040131f3", "Flagged": false, - "MoE": true + "MoE": false }, { "T": "\ud83d\udd36", - "Model": "databricks\/dolly-v2-3b", - "Average \u2b06\ufe0f": 22.83, - "ARC": 25.26, - "HellaSwag": 26.55, - "MMLU": 24.7, + "Model": "Severian\/Nexus-IKM-Mistral-7B-v5-instruction", + "Average \u2b06\ufe0f": 22.48, + "ARC": 27.73, + "HellaSwag": 28.93, + "MMLU": 24.69, "TruthfulQA": 0.0, - "Winogrande": 59.43, - "GSM8K": 1.06, + "Winogrande": 53.51, + "GSM8K": 0.0, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "GPTNeoXForCausalLM", + "Architecture": "MistralModel", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "mit", - "#Params (B)": 3.0, - "Hub \u2764\ufe0f": 262.0, + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "f6c9be08f16fe4d3a719bee0a4a7c7415b5c65df", + "Model sha": "522171e1381316dfbbe8f76904728c1607220da1", "Flagged": false, "MoE": false }, @@ -100580,11 +125811,34 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "05868b30f81600b703a1029c4806683f7f5a89fc", "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "Severian\/Mistral-v0.2-Nexus-Internal-Knowledge-Map-7B", + "Average \u2b06\ufe0f": 22.29, + "ARC": 29.27, + "HellaSwag": 28.82, + "MMLU": 24.98, + "TruthfulQA": 0.0, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "81d1652b1a24da0d98b17b0f2faad63c6a9febf2", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udcac", "Model": "v1olet\/v1olet_mistral_7B", @@ -100603,7 +125857,7 @@ "Hub License": "?", "#Params (B)": 7.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "aaf2184ac642ce0171d2703bdb3db8fde855e4c9", "Flagged": false, "MoE": false @@ -100631,6 +125885,29 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/mistral2-sp-lima-test", + "Average \u2b06\ufe0f": 21.78, + "ARC": 29.44, + "HellaSwag": 26.16, + "MMLU": 25.38, + "TruthfulQA": 0.0, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6bc29114b9ac8a2d90c8bebe527468ab648a719a", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udfe2", "Model": "FabbriSimo01\/Facebook_opt_1.3b_Quantized", @@ -100672,7 +125949,7 @@ "Hub License": "?", "#Params (B)": 7.11, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "c0e782c571209e1238e3a3170dcd187f9a436df2", "Flagged": false, "MoE": false @@ -100838,6 +126115,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udd36", + "Model": "juhwanlee\/gemma-7B-alpaca-case-3-3", + "Average \u2b06\ufe0f": 21.06, + "ARC": 25.0, + "HellaSwag": 26.22, + "MMLU": 24.73, + "TruthfulQA": 0.0, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f5a1d0ea3395882367421149757b0e2dcb7b4045", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "BreadAi\/MuseCan", @@ -100864,10 +126164,10 @@ { "T": "\ud83d\udfe2", "Model": "team-lucid\/mptk-1b", - "Average \u2b06\ufe0f": 20.84, + "Average \u2b06\ufe0f": 20.76, "ARC": 22.7, - "HellaSwag": 25.48, - "MMLU": 27.11, + "HellaSwag": 25.11, + "MMLU": 27.02, "TruthfulQA": 0.0, "Winogrande": 49.72, "GSM8K": 0.0, @@ -100884,6 +126184,29 @@ "Flagged": false, "MoE": false }, + { + "T": "\ud83d\udcac", + "Model": "openbmb\/MiniCPM-2B-dpo-bf16-llama-format", + "Average \u2b06\ufe0f": 20.67, + "ARC": 25.6, + "HellaSwag": 22.42, + "MMLU": 24.24, + "TruthfulQA": 0.0, + "Winogrande": 51.78, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.72, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "b38fe792b0a2aa59aec4b38d3a2daf249513b9a4", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", "Model": "mindy-labs\/mindy-7b", @@ -100902,7 +126225,7 @@ "Hub License": "?", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "b859eae30d69b065060e268b4e918601dabcc36c", "Flagged": false, "MoE": false @@ -100977,8 +126300,8 @@ "MoE": false }, { - "T": "\ud83d\udd36", - "Model": "ewqr2130\/mistral-moe-scratch", + "T": "\ud83e\udd1d", + "Model": "rizla\/rizla-11", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -100986,22 +126309,22 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "fine-tuned on domain-specific datasets", - "Architecture": "Unknown", + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", "Weight type": "Original", - "Precision": "float16", - "Merged": false, - "Hub License": "?", - "#Params (B)": 46.7, + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 9.42, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "efda3aed6b33db48bde86d2d3a7200895350e490", + "Model sha": "499b64d8272ea64e1247f9ff1eef33d7138b6c34", "Flagged": false, - "MoE": true + "MoE": false }, { - "T": "\ud83e\udd1d", - "Model": "RatanRohith\/NeuralPizza-Valor-7B-Merge-slerp", + "T": "\ud83d\udd36", + "Model": "shitshow123\/stablelm_sft_dpo", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101009,22 +126332,22 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "base merges and moerges", - "Architecture": "MistralForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": true, + "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 0.92, - "Hub \u2764\ufe0f": 1.0, + "#Params (B)": 7.87, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "fca24d608a5196ee6661e1b293466f95089776ff", + "Model sha": "c8c9b1fb2217a2b659de4f9396feeca5d15f53ee", "Flagged": false, "MoE": false }, { "T": "\ud83e\udd1d", - "Model": "mathurinache\/Odysseas-11B", + "Model": "AbacusResearch\/jaLLAbi", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101033,21 +126356,21 @@ "Winogrande": 49.57, "GSM8K": 0.0, "Type": "base merges and moerges", - "Architecture": "MistralForCausalLM", + "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", "Merged": true, "Hub License": "apache-2.0", - "#Params (B)": 0.48, + "#Params (B)": 14.36, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "c3a5944eb94bb9d2e8fd8b9c8d45791b4e8cf982", + "Model sha": "d5c3d2f5365073d173557ee78764d018d0a0ce86", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "clibrain\/Llama-2-ft-instruct-es", + "Model": "uukuguy\/speechless-mistral-six-in-one-7b-orth-1.0", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101056,21 +126379,21 @@ "Winogrande": 49.57, "GSM8K": 0.0, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "LlamaForCausalLM", + "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "float16", + "Precision": "bfloat16", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 18.0, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "42f07d6a86fac5574febb7b8fa13c3b1e14fcebd", + "Model sha": "e500285ba420cb3865d72aa0cc3b1fb9cc0bfee8", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", - "Model": "APMIC\/caigun-lora-model-33B", + "Model": "aiplanet\/panda-coder-13B", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101081,13 +126404,13 @@ "Type": "fine-tuned on domain-specific datasets", "Architecture": "LlamaForCausalLM", "Weight type": "Original", - "Precision": "8bit", + "Precision": "4bit", "Merged": false, - "Hub License": "cc-by-nc-nd-4.0", - "#Params (B)": 18.25, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, "Available on the hub": true, - "Model sha": "43789c7afafa495cbcb75185c8f48b11488c0408", + "Model sha": "823a8320224cdac88e927aee00338ffa79395faa", "Flagged": false, "MoE": false }, @@ -101114,9 +126437,32 @@ "Flagged": false, "MoE": true }, + { + "T": "\ud83d\udcac", + "Model": "TheTravellingEngineer\/bloom-1b1-RLHF-v2", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "05f7f0fd82fb3a5798d4bb284b6c10dd9d380f22", + "Flagged": false, + "MoE": false + }, { "T": "\ud83d\udd36", - "Model": "shitshow123\/stablelm_sft_dpo", + "Model": "clibrain\/Llama-2-ft-instruct-es", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101125,21 +126471,21 @@ "Winogrande": 49.57, "GSM8K": 0.0, "Type": "fine-tuned on domain-specific datasets", - "Architecture": "GPTNeoXForCausalLM", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 7.87, - "Hub \u2764\ufe0f": 0.0, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 18.0, "Available on the hub": true, - "Model sha": "c8c9b1fb2217a2b659de4f9396feeca5d15f53ee", + "Model sha": "42f07d6a86fac5574febb7b8fa13c3b1e14fcebd", "Flagged": false, "MoE": false }, { "T": "\ud83e\udd1d", - "Model": "rizla\/rizla-11", + "Model": "RatanRohith\/NeuralPizza-Valor-7B-Merge-slerp", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101148,21 +126494,21 @@ "Winogrande": 49.57, "GSM8K": 0.0, "Type": "base merges and moerges", - "Architecture": "MixtralForCausalLM", + "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "bfloat16", + "Precision": "float16", "Merged": true, - "Hub License": "cc-by-nc-2.0", - "#Params (B)": 9.42, - "Hub \u2764\ufe0f": 0.0, + "Hub License": "apache-2.0", + "#Params (B)": 0.92, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "499b64d8272ea64e1247f9ff1eef33d7138b6c34", + "Model sha": "fca24d608a5196ee6661e1b293466f95089776ff", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "TheTravellingEngineer\/bloom-1b1-RLHF-v2", + "T": "\ud83d\udd36", + "Model": "abideen\/phi2-pro", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101170,22 +126516,68 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "BloomForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "e770dbf94ef346a944128314573434f4b018c4d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-moe-scratch", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "", - "#Params (B)": 1.0, + "Hub License": "?", + "#Params (B)": 46.7, "Hub \u2764\ufe0f": 0.0, "Available on the hub": false, - "Model sha": "05f7f0fd82fb3a5798d4bb284b6c10dd9d380f22", + "Model sha": "efda3aed6b33db48bde86d2d3a7200895350e490", + "Flagged": false, + "MoE": true + }, + { + "T": "?", + "Model": "Rardilit\/Panther_v1", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LLaMAForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "mathurinache\/Odysseas-11B", + "Model": "RESMPDEV\/Mistral-7B-v0.2", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101196,19 +126588,19 @@ "Type": "fine-tuned on domain-specific datasets", "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "float16", - "Merged": true, + "Precision": "bfloat16", + "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 0.48, - "Hub \u2764\ufe0f": 0.0, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "c3a5944eb94bb9d2e8fd8b9c8d45791b4e8cf982", + "Model sha": "420a5558193f58ebcb8827dbf22a7a4b5f6d7c86", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udfe2", - "Model": "wtang06\/mpt-125m-c4", + "T": "\ud83d\udd36", + "Model": "xdatasi\/antares-7b-slovenian", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101216,22 +126608,22 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "pretrained", - "Architecture": "MPTForCausalLM", + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 0.12, - "Hub \u2764\ufe0f": 1.0, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 2.0, "Available on the hub": true, - "Model sha": "55f8f1874aa8bf4fc28c0abc92c7fbd1271ff7d7", + "Model sha": "8ca5c1b150d49d41f662bc59403cfed34d03cbcd", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83e\udd1d", - "Model": "RatanRohith\/NeuralPizza-7B-Merge-Slerp", + "Model": "blueRab2it\/Godrick_7Bx2_MoE_13B-v0.1", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101240,21 +126632,44 @@ "Winogrande": 49.57, "GSM8K": 0.0, "Type": "base merges and moerges", - "Architecture": "MistralForCausalLM", + "Architecture": "MixtralForCausalLM", "Weight type": "Original", "Precision": "float16", "Merged": true, "Hub License": "apache-2.0", - "#Params (B)": 0.92, + "#Params (B)": 11.54, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "535fd5f9f28bfbd5a46f5f80a1f0c83633ed142b", + "Model sha": "75b195de13b49044b7dca213f9cc8f265b07d964", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "kihoonlee\/Merge-13B-v1-test", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 11.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2af514940b5c353502ee1e4f918aae5c516c9680", "Flagged": false, "MoE": false }, { - "T": "?", - "Model": "Rardilit\/Panther_v1", + "T": "\ud83d\udcac", + "Model": "kyujinpy\/Sakura-SOLAR-Instruct-DPO-v1", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101262,22 +126677,45 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "", - "Architecture": "LLaMAForCausalLM", - "Weight type": "Delta", + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", "Precision": "float16", "Merged": false, - "Hub License": "other", - "#Params (B)": 0.0, - "Hub \u2764\ufe0f": 1.0, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "56cd9f8992e05fa799b33db83e967d1b5f0d5724", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mathurinache\/Odysseas-11B", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.48, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "", + "Model sha": "c3a5944eb94bb9d2e8fd8b9c8d45791b4e8cf982", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "antiven0m\/brugle-rp", + "Model": "abhishek\/autotrain-c71ux-tngfu", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101289,18 +126727,18 @@ "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "bfloat16", - "Merged": true, - "Hub License": "unknown", + "Merged": false, + "Hub License": "other", "#Params (B)": 7.24, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": false, - "Model sha": "02096a89cfa76a0bb9aa331a771edd703674b0c3", + "Available on the hub": true, + "Model sha": "98a3674f7543a3a0bc51b8655b848ff2f146f8a9", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "aiplanet\/panda-coder-13B", + "Model": "APMIC\/caigun-lora-model-33B", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101311,19 +126749,19 @@ "Type": "fine-tuned on domain-specific datasets", "Architecture": "LlamaForCausalLM", "Weight type": "Original", - "Precision": "4bit", + "Precision": "8bit", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 13.0, - "Hub \u2764\ufe0f": 8.0, - "Available on the hub": false, - "Model sha": "823a8320224cdac88e927aee00338ffa79395faa", + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 18.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43789c7afafa495cbcb75185c8f48b11488c0408", "Flagged": false, "MoE": false }, { "T": "\ud83e\udd1d", - "Model": "kihoonlee\/Merge-13B-v1-test", + "Model": "MatthieuJ\/Forbin_13B_M1_SLERP", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101334,15 +126772,15 @@ "Type": "base merges and moerges", "Architecture": "MixtralForCausalLM", "Weight type": "Original", - "Precision": "float16", + "Precision": "bfloat16", "Merged": true, "Hub License": "apache-2.0", "#Params (B)": 11.54, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "2af514940b5c353502ee1e4f918aae5c516c9680", + "Model sha": "9a87947a0d3ca8538bd088384001afa9f9f83f08", "Flagged": false, - "MoE": false + "MoE": true }, { "T": "\ud83d\udd36", @@ -101362,14 +126800,14 @@ "Hub License": "?", "#Params (B)": 13.0, "Hub \u2764\ufe0f": 0.0, - "Available on the hub": true, + "Available on the hub": false, "Model sha": "5d17f6b5f394f0745bd4377c8a1290c68051e351", "Flagged": false, "MoE": false }, { - "T": "\ud83e\udd1d", - "Model": "AbacusResearch\/jaLLAbi", + "T": "\ud83d\udfe2", + "Model": "wtang06\/mpt-125m-c4", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101377,22 +126815,22 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "base merges and moerges", - "Architecture": "MixtralForCausalLM", + "Type": "pretrained", + "Architecture": "MPTForCausalLM", "Weight type": "Original", - "Precision": "bfloat16", - "Merged": true, + "Precision": "float16", + "Merged": false, "Hub License": "apache-2.0", - "#Params (B)": 14.36, - "Hub \u2764\ufe0f": 0.0, + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 1.0, "Available on the hub": true, - "Model sha": "d5c3d2f5365073d173557ee78764d018d0a0ce86", + "Model sha": "55f8f1874aa8bf4fc28c0abc92c7fbd1271ff7d7", "Flagged": false, "MoE": false }, { "T": "\ud83d\udd36", - "Model": "uukuguy\/speechless-mistral-six-in-one-7b-orth-1.0", + "Model": "antiven0m\/brugle-rp", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101405,17 +126843,17 @@ "Weight type": "Original", "Precision": "bfloat16", "Merged": false, - "Hub License": "apache-2.0", - "#Params (B)": 7.0, - "Hub \u2764\ufe0f": 1.0, - "Available on the hub": true, - "Model sha": "e500285ba420cb3865d72aa0cc3b1fb9cc0bfee8", + "Hub License": "unknown", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "02096a89cfa76a0bb9aa331a771edd703674b0c3", "Flagged": false, - "MoE": true + "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "kyujinpy\/Sakura-SOLAR-Instruct-DPO-v1", + "T": "\ud83e\udd1d", + "Model": "RatanRohith\/NeuralPizza-7B-Merge-Slerp", "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, "HellaSwag": 25.04, @@ -101423,39 +126861,39 @@ "TruthfulQA": 0.0, "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "Unknown", + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", "Weight type": "Original", "Precision": "float16", - "Merged": false, - "Hub License": "?", - "#Params (B)": 10.73, + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.92, "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "56cd9f8992e05fa799b33db83e967d1b5f0d5724", + "Model sha": "535fd5f9f28bfbd5a46f5f80a1f0c83633ed142b", "Flagged": false, "MoE": false }, { - "T": "\ud83d\udcac", - "Model": "Felladrin\/Pythia-31M-Chat-v1", - "Average \u2b06\ufe0f": 19.92, + "T": "\ud83e\udd1d", + "Model": "mathurinache\/Odysseas-11B", + "Average \u2b06\ufe0f": 20.07, "ARC": 22.7, - "HellaSwag": 25.6, - "MMLU": 23.24, + "HellaSwag": 25.04, + "MMLU": 23.12, "TruthfulQA": 0.0, - "Winogrande": 47.99, + "Winogrande": 49.57, "GSM8K": 0.0, - "Type": "chat models (RLHF, DPO, IFT, ...)", - "Architecture": "GPTNeoXForCausalLM", + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", "Weight type": "Original", - "Precision": "float16", - "Merged": false, + "Precision": "bfloat16", + "Merged": true, "Hub License": "apache-2.0", - "#Params (B)": 0.03, - "Hub \u2764\ufe0f": 3.0, + "#Params (B)": 0.48, + "Hub \u2764\ufe0f": 0.0, "Available on the hub": true, - "Model sha": "e6a52e4ac98e20c7f9e39aaba9368dd6faacdad9", + "Model sha": "c3a5944eb94bb9d2e8fd8b9c8d45791b4e8cf982", "Flagged": false, "MoE": false }