Update Model Files

README.md

@@ -1,59 +0,0 @@
----
-license: apache-2.0
----
-
-# 项目说明
-
-## 📋 项目概述
-
-SDPMed模型基于山东省疾控中心提供的公共卫生领域材料和网络开源的医疗数据集，由山东浪潮智慧医疗科技有限公司提供技术支持，专门对Qwen3-8B模型进行微调优化。通过精心设计的数据集和训练策略，显著提升了模型在医疗/公卫知识问答方面的性能。
-
-## 🚀 主要特性
-
-- **高性能**: 在 [Medbench评估中] 取得8B级模型sota
-- **专业化**: 专门针对 [公共卫生领域] 优化
-- **易部署**: 支持通用的部署方案
-- **可扩展**: 支持进一步微调和定制
-
-## 📊 模型信息
-
-| 属性 | 值 |
-|------|-----|
-| 基础模型 | [Qwen3系列] |
-| 模型大小 | [8B参数] |
-| 训练数据量 | [约177万条] |
-| 垂直领域 | [公共卫生领域] |
-| 显存要求 | [至少24GB] |
-
-## 🔧 环境要求
-
-### 硬件要求
-- GPU: 建议使用 NVIDIA RTX 4090 或更高配置
-- 显存: 至少 24GB
-- 内存: 至少 32GB RAM
-- 存储: 至少 30GB 可用空间
-
-## 🤝 贡献指南
-
-欢迎提交 Issue 和 Pull Request！
-
-1. Fork 本仓库
-2. 创建特性分支 (`git checkout -b feature/AmazingFeature`)
-3. 提交更改 (`git commit -m 'Add some AmazingFeature'`)
-4. 推送到分支 (`git push origin feature/AmazingFeature`)
-5. 创建 Pull Request
-
-## 🙏 致谢
-
-- 感谢 [通义千问] 提供的预训练模型
-- 感谢开源社区的贡献
-- 特别感谢 [山东省疾控中心/浪潮智慧医疗]提供[数据/技术]支持
-
-## 🔄 更新日志
-
-### v1.0.0 (2025-06-20)
-- 初始版本发布
-
----
-
-⭐ 如果这个项目对您有帮助，请给我们一个星标！

added_tokens.json

@@ -1,28 +1,3 @@
-{
-  "</think>": 151668,
-  "</tool_call>": 151658,
-  "</tool_response>": 151666,
-  "<think>": 151667,
-  "<tool_call>": 151657,
-  "<tool_response>": 151665,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
+size 707

config.json

@@ -1,30 +1,3 @@
-{
-  "architectures": [
-    "Qwen3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 12288,
-  "max_position_embeddings": 40960,
-  "max_window_layers": 36,
-  "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab2048ff4d232a0c632c4eea2b61a75e65a820a5841ca48dd1050a40af42567
+size 729

generation_config.json

@@ -1,13 +1,3 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 0.6,
-  "top_k": 20,
-  "top_p": 0.95,
-  "transformers_version": "4.51.3"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:81051cd3f6e77013827148d0b8a6ead93f8ac390d5ab805f849199f0af6a08db
+size 214

model-00001-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9290ab44c8388aa4af18364aa647849fed65b61bdb5d057642c3db2a355f8e72
+oid sha256:06ff30bf108c0a1eeec5370569c5cd6578b84819ae3d977e4bcefcec863b6bb5
 size 1915768080

model-00002-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e26cdfe509a540361e0f9ab60194777e5cfd87d07cbf2e7c1691e195b2b7f2
+oid sha256:e7ae7d7d1dd872fa59c195b89b547245d660f35f559ab344436d0756be94a7fd
 size 1929470608

model-00003-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28291834d85626198d6cbb3e8816a2f27a8aeeb1731b4aa8db210349f450c41c
+oid sha256:a4cedac0a9938dca407dab70c1bf57b3aa087ff58a4b85d0f4389dc5a3c83712
 size 1929470632

model-00004-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c4794c5f5cb44538dfa648744d32170f85d9fcbb28543c8715640dff81f4d1
+oid sha256:1a49c778d6068b9c3d58f804b209baab435a69b0919b7d124a907cd02636bc37
 size 1929470664

model-00005-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f885d465764fc1e0440ff8056303f348b1abc82ef0c8b8eeb8984fcb10912c6
+oid sha256:8437dd62d0f74928cbbc0f35a7f558fc2e99ce41dc8db961c95654faaa460a08
 size 1929470664

model-00006-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039ae6a442e35066a8ba823249a1f84399658fa1e6a42e1e4ae04337b9a69c57
+oid sha256:e09f4fdc713de04f821ae2fda2ea771c95ecc648f3236dff16f53f7db43a7d8d
 size 1929470664

model-00007-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71447fc8c16b9fc7f74aacd3630719b2814904dbf93ffc97aaf3b64dcdcea8e
+oid sha256:a347b1ab0cc637317cd14d94ef574eca744bb22d996d5b24b517cee4613cdd56
 size 1929470664

model-00008-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1c9e7e29b6724ce689685ba4a67b82bb0b3a245cb07f9a1f351bbd9164b263
+oid sha256:8c1e21b5211622ec260e97d6f5c827c5450d6ffd488f48f65fd0290a6ba6c90a
 size 1644264840

model.safetensors.index.json

@@ -1,406 +1,3 @@
-{
-  "metadata": {
-    "total_size": 16381470720
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00009-of-00009.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-    "model.norm.weight": "model-00008-of-00009.safetensors"
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40f6e397075acc1d522f55940630ba43c5d3d6dcc98ad4184ba87fd65317194
+size 32878

special_tokens_map.json

@@ -1,31 +1,3 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

tokenizer_config.json

@@ -1,241 +1,3 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f33cbb21bae9b2ed4a7396d68f9f10d6280d75332d04911cd6c5a0967bd10c9
+size 9732