Upload folder using huggingface_hub

README.md

@@ -0,0 +1,126 @@
+---
+license: apache-2.0
+tags:
+- moe
+model-index:
+- name: MixTAO-7Bx2-MoE-v8.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 73.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 89.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 78.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 87.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 71.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+---
+
+# MixTAO-7Bx2-MoE
+
+MixTAO-7Bx2-MoE is a Mixure of Experts (MoE).
+This model is mainly used for large model technology experiments, and increasingly perfect iterations will eventually create high-level large language models.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_zhengr__MixTAO-7Bx2-MoE-v8.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |77.50|
+|AI2 Reasoning Challenge (25-Shot)|73.81|
+|HellaSwag (10-Shot)              |89.22|
+|MMLU (5-Shot)                    |64.92|
+|TruthfulQA (0-shot)              |78.57|
+|Winogrande (5-shot)              |87.37|
+|GSM8k (5-shot)                   |71.11|
+

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "zhengr/MixTAO-7Bx2-MoE-v8.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "unsloth_version": "2024.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "lm_head.weight": "model-00005-of-00013.safetensors", "model.norm.weight": "model-00005-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00013-of-00013.safetensors"}}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37309915bfe5de1fbf8ed26ec7f49791d6a24e469893d6ff0d0082b1fa441c18
+size 8563534616

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994fd39f25ff2edeac845aa5c90944ed29c4b855a906c4a54d2604b6159d74da
+size 4444857496

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 255,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}