初始化项目，由ModelHub XC社区提供模型

Model: zjydiary/Medical-Qwen3-14B-1218-GGUF Source: Original Platform
2026-06-17 19:15:12 +08:00
commit bd7ef939ce
21 changed files with 241 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,67 @@
+*.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
+ 
+*.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
+
+Medical-Qwen3-14B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/Medical-Qwen3-14B-Q8_0-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/Medical-Qwen3-14B-BF16-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/Medical-Qwen3-14B-Q8_0-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/Medical-Qwen3-14B-BF16-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/Medical-Qwen3-14B-BF16-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/Medical-Qwen3-14B-Q8_0-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/Medical-Qwen3-14B-Q8_0-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+BF16/Medical-Qwen3-14B-BF16-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Medical-Qwen3-14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/BF16/Medical-Qwen3-14B-BF16-00001-of-00004.gguf
+++ b/BF16/Medical-Qwen3-14B-BF16-00001-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15b94f0fb85e46f93adbbae61cd655ce0cad9dd407833ccf893a985d8b9fee8
+size 9720168896
--- a/BF16/Medical-Qwen3-14B-BF16-00002-of-00004.gguf
+++ b/BF16/Medical-Qwen3-14B-BF16-00002-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204a5f73188c261bfe3608fa240ae60fa0a88bfc97ad0536d0ac60704d722ce7
+size 7214714368
--- a/BF16/Medical-Qwen3-14B-BF16-00003-of-00004.gguf
+++ b/BF16/Medical-Qwen3-14B-BF16-00003-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859c0f5883f98902b76c6a1fb4b350ff090d1e1e50429b61d4b2f163885cc78b
+size 7686553120
--- a/BF16/Medical-Qwen3-14B-BF16-00004-of-00004.gguf
+++ b/BF16/Medical-Qwen3-14B-BF16-00004-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73158147b1ba419122b0c3c6903cd0c9d4b0c54597cffee609b262cafa07d1a
+size 4921987616
--- a/Medical-Qwen3-14B-Q2_K.gguf
+++ b/Medical-Qwen3-14B-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4c518e4216467b7716e51920cba687994d426910f31d6efd0f0d5987ded1b3
+size 5753983520
--- a/Medical-Qwen3-14B-Q3_K_L.gguf
+++ b/Medical-Qwen3-14B-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdbe7b5eb9a9fbf4cae50b5381d93f9660091d1ed40c895a5ca26c82063a192
+size 7900651040
--- a/Medical-Qwen3-14B-Q3_K_M.gguf
+++ b/Medical-Qwen3-14B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5936a6bd67c7e85b94fe88150893c6ddb19448bd06bdf8a96094802dd24aea00
+size 7321312800
--- a/Medical-Qwen3-14B-Q3_K_S.gguf
+++ b/Medical-Qwen3-14B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0395d290ab4baa28860f3a791c6c84f614801277e80f301c6eed232c709c80
+size 6657105440
--- a/Medical-Qwen3-14B-Q4_0.gguf
+++ b/Medical-Qwen3-14B-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c157fb72169fbf9ddfbca79f8b3d4ee68784a064c2d5fbcd2a75dbeb0db08c
+size 8515148320
--- a/Medical-Qwen3-14B-Q4_1.gguf
+++ b/Medical-Qwen3-14B-Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23833c50b32f1275377d47f90345ac44ba4c2c9ccd35c93671162f1114528718
+size 9389521440
--- a/Medical-Qwen3-14B-Q4_K_M.gguf
+++ b/Medical-Qwen3-14B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ed5682b6aa987d42e537133c3e44419232002ae85255edc10af1174d8c7fdc
+size 9001753120
--- a/Medical-Qwen3-14B-Q4_K_S.gguf
+++ b/Medical-Qwen3-14B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071c828d1c4cb34912df0e56ccd7e812fc3ea8b7b0b72369b71a20ab9ea1e5c2
+size 8573475360
--- a/Medical-Qwen3-14B-Q5_K_M.gguf
+++ b/Medical-Qwen3-14B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07fa5c2f649bafeed0072a6368c5671f140f5a11a9bd9b8395696f39ac07181e
+size 10514569760
--- a/Medical-Qwen3-14B-Q5_K_S.gguf
+++ b/Medical-Qwen3-14B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a91ece9dd24530ee9e640207fe8a0d03384de7b17d2c77a2c240a63ac5f16eb
+size 10263894560
--- a/Medical-Qwen3-14B-Q6_K.gguf
+++ b/Medical-Qwen3-14B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189da1f46787bee4f23dcfeb3661ed41bfe1e64dbeba04b5639778adb4f3215c
+size 12121937440
--- a/Q8_0/Medical-Qwen3-14B-Q8_0-00001-of-00004.gguf
+++ b/Q8_0/Medical-Qwen3-14B-Q8_0-00001-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10072f131aaa36b3bbe0b8cf0a9b1b65d52783807a2f9bc493ebca1fb328df7
+size 5553329056
--- a/Q8_0/Medical-Qwen3-14B-Q8_0-00002-of-00004.gguf
+++ b/Q8_0/Medical-Qwen3-14B-Q8_0-00002-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3a1b8774708e93cd15523cd148295e7f94736df836343c2432a96ee0325e93
+size 4178410528
--- a/Q8_0/Medical-Qwen3-14B-Q8_0-00003-of-00004.gguf
+++ b/Q8_0/Medical-Qwen3-14B-Q8_0-00003-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5d0bdd71d7dda242e75a733f4ce9eb3771805cf5e84a69289c955fccdf4d20
+size 3927735840
--- a/Q8_0/Medical-Qwen3-14B-Q8_0-00004-of-00004.gguf
+++ b/Q8_0/Medical-Qwen3-14B-Q8_0-00004-of-00004.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db8350227ea43d3417623a42f68bd4cac7e60802634df674b4e56f3be67eb16
+size 2039058976
--- a/README.md
+++ b/README.md
@@ -0,0 +1,117 @@
+---
+base_model_relation: quantized
+license: Apache License 2.0
+language:
+- zh
+- en
+tags:
+- medical
+- qwen
+- sft
+- lora
+- reinforcement-learning
+base_model: zjydiary/Medical-Qwen3-14B-1218
+pipeline_tag: text-generation
+library_name: peft
+datasets:
+  - zjydiary/Medical
+---
+
+# Medical-Qwen3-14B-1218
+
+## 模型简介 (Model Description)
+
+**Medical-Qwen3-14B-1218** 是基于 [Qwen3-14B](https://modelscope.cn/Qwen/Qwen3-14B) 的医疗领域专用大语言模型。该模型通过两阶段微调（Pre-training + SFT）并采用加权合并策略（Weighted Merging）构建，旨在提升医疗问答的准确性、术语规范性及指令遵循能力。
+
+本版本为 **2025-12-18** 发布的稳定版，融合了 GPT-OSS 风格的训练参数与 Qwen3 的架构优势，在医疗长文本理解与生成上表现出优异的鲁棒性。
+
+## 训练细节 (Training Details)
+
+### 训练流程
+1.  **基座模型**: Qwen/Qwen3-14B (bf16)
+2.  **阶段一：医疗增量预训练 (LoRA PT)**
+    -   数据：混合医疗语料 (Medical Corpus)
+    -   策略：Qwen3 No-Think 模板，全参 LoRA (Target All)
+    -   目标：注入领域知识，适应医疗文风
+3.  **阶段二：指令微调 (LoRA SFT)**
+    -   数据：高质量医疗问答对 (Medical QA Pairs)
+    -   参数：Rank 8, Alpha 16, Dropout 0.07
+    -   策略：Cosine 调度, 强正则 (Weight Decay 0.03), 梯度累积优化
+4.  **模型合并 (Weighted Merging)**
+    -   方法：线性加权合并 (Linear Weighted Merging)
+    -   权重：`SFT (0.7) + PT (0.3)`
+    -   目的：平衡指令遵循能力（SFT）与领域知识广度（PT）
+
+### 训练环境
+-   **Framework**: LLaMA-Factory
+-   **Hardware**: NVIDIA GPU Cluster (FlashAttention-2 Enabled)
+-   **Quantization**: BNB 4-bit NF4 (Training), BFloat16 (Merge/Inference)
+
+## 评估结果 (Evaluation Results)
+
+评估时间：2025-12-18 12:24:46
+评估集：Medical Validation Set (F5/F6)
+解码参数：`temperature=0.6`, `top_p=0.8` (折中推荐配置)
+
+| Metric | Score | Description |
+| :--- | :--- | :--- |
+| **BLEU-4** | **16.38** | 高分表明生成的短语与专家回答高度一致 |
+| **ROUGE-1** | **20.42** | 优秀的词汇覆盖率，关键信息点召回准确 |
+| **ROUGE-2** | **4.60** | 相比早期版本 (+0.1)，二元术语搭配更加精准 |
+| **ROUGE-L** | **11.54** | 良好的长句结构相似度，逻辑连贯性强 |
+
+*注：相比纯 SFT 版本，合并模型在保持 ROUGE 分数的同时，显著降低了过拟合风险，提升了对不同解码参数的鲁棒性。*
+
+## 使用方法 (Usage)
+
+### 推荐推理参数
+为了获得最佳的医疗问答效果，建议使用以下参数：
+-   `temperature`: 0.5 - 0.7 (平衡准确性与流畅度)
+-   `top_p`: 0.8 - 0.9
+-   `repetition_penalty`: 1.05 - 1.1
+-   `max_new_tokens`: 2048 (支持长文回答)
+
+### 代码示例 (Transformers)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_path = "/workspace/model/zjydiary/Medical-Qwen3-14B-1218"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True
+)
+
+prompt = "患者，男，45岁，主诉持续性上腹痛3天，伴恶心呕吐。请给出初步诊断建议及检查方案。"
+messages = [
+    {"role": "system", "content": "你是一名专业的医疗助手，请用严谨、客观的语气回答。"},
+    {"role": "user", "content": prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=2048,
+    temperature=0.6,
+    top_p=0.9
+)
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+
+## 声明 (Disclaimer)
+
+本模型仅供学术研究与技术验证使用。生成的医疗建议仅供参考，不能替代执业医师的诊断。在实际临床应用前，请务必进行严格的专业评估与人工审核。