初始化项目，由ModelHub XC社区提供模型

Model: mlx-community/Devstral-Small-2505-bf16
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm 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 +1,64 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+- ja
+- ko
+- ru
+- zh
+- ar
+- fa
+- id
+- ms
+- ne
+- pl
+- ro
+- sr
+- sv
+- tr
+- uk
+- vi
+- hi
+- bn
+license: apache-2.0
+library_name: mlx
+inference: false
+base_model: mistralai/Devstral-Small-2505
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+pipeline_tag: text-generation
+tags:
+- mlx
+---
+
+# mlx-community/Devstral-Small-2505-bf16
+
+This model [mlx-community/Devstral-Small-2505-bf16](https://huggingface.co/mlx-community/Devstral-Small-2505-bf16) was
+converted to MLX format from [mistralai/Devstral-Small-2505](https://huggingface.co/mistralai/Devstral-Small-2505)
+using mlx-lm version **0.24.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Devstral-Small-2505-bf16")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

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": 131072,
+    "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": "4.51.3",
+    "use_cache": true,
+    "vocab_size": 131072
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661c5e2fcb28c0b42b1329b705f3a9fa0995a6bf5502bcd47b34b3a5b7970fb6
+size 5117116151

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a828c2948279a7899b15fc49ccfa388285182132395b624366f973e0348094
+size 5222015985

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc70971b20b271bc571237c92f2a7e5a36ba59b7409b5bc3f011a47f22bc90a
+size 5117137242

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3a879004f13dba75c77b0ffb4dc63a85d61ddd69e06ab49736fb020a42ea85
+size 5222016041

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d805f2347f4cf3512ea2e010cdb11a1b8a3f717ba09c8d5e3e4375a23d812324
+size 5222016011

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112a69c8856134651af285041a3085ac563102fc70c3a5fa3ef0dbcb106d54e6
+size 5117137258

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef873ae87cd1212355f0af56eb6afe85f0457b64d7de32a22f0652615b20bb34
+size 5222016033

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1939f7e39ab30814f875362e8ddc74bb65a180ad71ec8b1099dd5b3dbb6715
+size 5222016019

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ca15ba00572920fdb6cb5a83b371392214c54befedd7bec54100d1e21c3cc6
+size 4341200625

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893e21d83adf9def5b5cef68d33d4f3611ee66e0881fafffa5e41b7894d78675
+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