Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- openchat/openchat-3.5-0106
+- machinists/Mistral-7B-SQL
+---
+
+# jaLLAbi
+
+jaLLAbi is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
+* [machinists/Mistral-7B-SQL](https://huggingface.co/machinists/Mistral-7B-SQL)
+
+## 🧩 Configuration
+
+\```yaml
+slices:
+  - sources:
+      - model: openchat/openchat-3.5-0106
+        layer_range: [0, 32]
+      - model: machinists/Mistral-7B-SQL
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: openchat/openchat-3.5-0106
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+\```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B",
+  "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": 40,
+  "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": "4.37.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+    - model: HanNayeoniee/LHK_DPO_v1
+      layer_range: [0, 32]
+  - sources:
+    - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b6649bc46f0334f5f19a82ee82532e716b545dab7df03a65f0e25a52544949
+size 3993080896

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a7cfbbf28d723b834da447dcd5a8765264ccffaf5f6e9c3d3718947950ed6c
+size 3902903096

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa462464ed6fac360849b52f518b293596a734dce7998d357444106f8773dd45
+size 3993080928

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf6bfe3b43863f73ecf461b674a884f21ce9c7f6e598ba73b5480dd6518e1d3
+size 3993080936

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6d790342acbab30ea9a3220493e8cb81b0ff033f16728d655ca7e113b15e23
+size 3993080936

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0f90b1e64cf5ae4abf66e0a0db426a0481f22c6ee1f6ba79f8630bb262c3fb
+size 3993080936

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e41f1eb6871f9d7692a93429622c40ff7ad52a0fa10dbfc5adf5d9097639429
+size 3902878376

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b87e1e9669804fcd712a6682c0dcfa1e0cc16c2701a3ed998ef126f139c7d5
+size 939525168

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.embed_tokens.weight": "model-00002-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.norm.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors"}}

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_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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,
+  "max_length": null,
+  "model_max_length": 255,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}