初始化项目，由ModelHub XC社区提供模型

Model: hkust-nlp/qwen2.5-7b-coder_codeio
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+model-00001-of-000002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-000002.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+# For reference on dataset card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
+# Doc / guide: https://huggingface.co/docs/hub/datasets-cards
+{}
+---
+
+# CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
+
+<p align="left">
+    📑 <a href="https://huggingface.co/papers/2502.07316" target="_blank">Paper</a> &nbsp&nbsp | &nbsp&nbsp 🌐 <a href="https://codei-o.github.io/" target="_blank">Project Page</a> &nbsp&nbsp | &nbsp&nbsp 💾 <a href="https://huggingface.co/collections/hkust-nlp/codei-o-67a978e28fd926b56a4f55a2" target="_blank">Released Resources</a> &nbsp&nbsp | &nbsp&nbsp 📦 <a href="https://github.com/hkust-nlp/CodeIO" target="_blank">Repo</a>  
+
+This is the resource page of the CodeI/O collection on Huggingface, we highlight your currect position with a blue block.
+
+**Dataset**
+<table>
+      <tr>
+        <th>Dataset</th>
+        <th>Link</th>
+    </tr>
+      <tr>
+        <td>CodeI/O-PythonEdu-Reasoning</td>
+        <td style="text-align: center; vertical-align: middle;">
+          <a href="https://huggingface.co/datasets/hkust-nlp/CodeIO-PyEdu-Reasoning">🤗</a>
+        </td>
+    </tr>
+</table>
+
+**Models**
+<table>
+    <tr>
+        <th rowspan="2">Base Model / Training</th>
+        <th colspan="2">CodeI/O</th>
+        <th colspan="2">CodeI/O++</th>
+    </tr>
+    <tr>
+        <th>Stage 1</th>
+        <th>Stage 2</th>
+        <th>Stage 1</th>
+        <th>Stage 2</th>
+    </tr>
+    <tr>
+        <td>Qwen 2.5 7B Coder</td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio_stage1">🤗</a></td>
+        <td style="background-color: #e6f3ff; text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio_pp_stage1">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio_pp">🤗</a></td>
+    </tr>
+    <tr>
+        <td>LLaMA 3.1 8B</td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio_stage1">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio_pp_stage1">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio_pp">🤗</a></td>
+    </tr>
+    <tr>
+        <td>DeepSeek v2 Lite Coder</td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio_stage1">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio_pp_stage1">🤗</a></td>
+        <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio_pp">🤗</a></td>
+    </tr>
+</table>
+
+## Citation
+If you find these resources helpful, please kindly cite as:
+```
+@article{li2025codeio,
+  title={CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction},
+  author={Li, Junlong and Guo, Daya and Yang, Dejian and Xu, Runxin and Wu, Yu and He, Junxian},
+  journal={arXiv preprint arXiv:2502.07316},
+  year={2025}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

configuration.json

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

model-00001-of-000002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef6cf4bdb44ebb0d0bd97f28213f3e64277e960d3a7daa4245ded56519ece56
+size 8606596466

model-00002-of-000002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11b6028937b82596b2555928804884d4494e7176145f12bc4a1617bcdf57768
+size 6624675384

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+    "model.norm.weight": "model-00002-of-000002.safetensors",
+    "lm_head.weight": "model-00002-of-000002.safetensors"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}"
+}