初始化项目，由ModelHub XC社区提供模型

Model: lmstudio-community/magistral-small-2506-mlx-bf16
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,27 @@
+---
+license: apache-2.0
+library_name: mlx
+base_model: mistralai/Magistral-Small-2506
+tags:
+- mlx
+pipeline_tag: text-generation
+---
+## 💫 Community Model> magistral-small by mistral-ai
+
+*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
+
+**Model creator:** [mistral-ai](https://huggingface.co/mistral-ai)<br>
+**Original model**: [magistral-small](https://huggingface.co/mistral-ai/magistral-small)<br>
+**MLX quantization:** provided by [LM Studio team](https://x.com/lmstudio) using [mlx_lm](https://github.com/ml-explore/mlx-lm)<br>
+
+## Technical Details
+
+Original bfloat16 version of magistral-small using MLX, optimized for Apple Silicon.
+
+## Special thanks
+
+🙏 Special thanks to the [Apple Machine Learning Research](https://github.com/ml-explore) team for creating [MLX](https://github.com/ml-explore/mlx).
+
+## Disclaimers
+
+LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model.  You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models.  LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

config.json

@@ -0,0 +1,26 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 32768,
+    "max_position_embeddings": 49152,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.52.4",
+    "use_cache": true,
+    "vocab_size": 131072
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af7acaa3d1d8c058b0c37c6b0dfb02f58c594384ba6dd4361611e95cdca5ed2
+size 5117116159

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f3185dd065a108677c172d9ae9b5f036d1f1adbbe0393bf8122130899e4e41
+size 5222015985

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b17fa795b6b72b10c9a9075ce201262260ce82e2a9a07dd6f38f989ed190ce
+size 5117137230

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f3946b38aaa80c0d6dad9b0895290ee7e345661df6ea9d0305da4b3d3a8f9f
+size 5222016045

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06a3d3b5987f3cdaccd1d66cef64af3be345663b0147b8cc307e83fc798d8c4
+size 5222016025

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f5210dde387f21801497cd1e59d306b366f8d8fae5e918e32797512f5f53fc
+size 5117137260

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad192320080b3cc219bc272aa0561fae3016a54316b70d664a3672a61b396064
+size 5222016027

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1641972893a5826676d162bb7d8ab8ee1593ef8717ea359507a1610ca91de223
+size 5222016039

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb42f70cb0054803ef09a9f589f4b4b0453003f3ce1ebf335585708203fcb67
+size 4341200611

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453696a5507f49d789318017a93b98f183ba3f19d15d1415f712640b080e0ca5
+size 1342177407

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+    "metadata": {
+        "total_size": 47144806400
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00010-of-00010.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+        "model.norm.weight": "model-00009-of-00010.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037