zpeng1989/Medical_Qwen3_8B_Large_Language_Model
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: zpeng1989/Medical_Qwen3_8B_Large_Language_Model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 18:30:16 +08:00
commit 33c3b00622
22 changed files with 910111 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

14
Modelfile Normal file
View File

@@ -0,0 +1,14 @@
# ollama modelfile auto-generated by llamafactory
FROM .
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
{{ .Content }}<|im_end|>
<|im_start|>assistant
{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
{{ end }}{{ end }}"""
PARAMETER stop "<|im_end|>"
PARAMETER num_ctx 4096

404
README.md Normal file
View File

@@ -0,0 +1,404 @@
# 医疗思考链问答大模型
## 项目概述
本项目旨在构建一个针对医疗知识的思考链条的问答大模型，基于Qwen3-8B模型作为基座模型[Qwen/Qwen3-8B]，使用LoRA（Low-Rank Adaptation）技术进行微调。模型训练数据涵盖了医疗问诊、咨询等权威医学领域知识信息，并通过问答题目进行微调，以提升模型在医学领域的问答能力。这种数据预处理的策略，充分挖掘了Qwen3模型强大的推理能力，使其能够模拟在医疗场景中，如何发现患者记录描述信息中获取到关联性的过程。
## 模型架构
- **基座模型**:[`Qwen/Qwen3-8B`]<https://modelscope.cn/models/Qwen/Qwen3-8B>
- **微调方法**: LoRA（Low-Rank Adaptation）
- **训练数据**: 问答数据集
## 数据集
### 数据来源
参考链接：<https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/tree/main>
### 数据预处理
训练数据格式：
```
{
"Question": "女性，34岁，双下肢麻木无力1年半，感觉障碍自下而上发展。体检：右侧胸8以下痛、温觉消失，左侧胸以下痛、温觉减退。右下肢肌力Ⅳ级，左下肢肌力Ⅲ级。左侧巴氏征阳性。病变的定性诊断应首先考虑为\nA. 脊膜瘤\nB. 神经纤维瘤\nC. 脑胶质瘤\nD. 椎管内转移瘤\nE. 脊髓髓内室管膜瘤",
"output": "<think>患者是一名34岁的女性，哎，她已经忍受了双下肢麻木无力有一年半了。她的症状是从脚下开始向上蔓延的。这听起来像是典型的神经问题，特别是脊髓的事情。\n\n在体检中，发现她的右侧胸8以下痛、温觉已经完全消失，奇怪的是，左侧则只是减退。这些提示我去考虑下，可能是脊髓的问题，尤其是可能在胸8这个区域出毛病了。\n\n她的巴氏征左侧是阳性的，这表明脊髓半侧损害，这就是所谓的Brown-Séquard综合征呀。嗯，右下肢的肌力相较左侧还稍微好一点，但情况都不妙。\n\n想到病变性质，感觉病程发展这么缓慢，说明是一种慢性病。可以是肿瘤，那肿瘤的话，髓内的或髓外的都有可能。这个就看到底是涉及到脊髓内还是外了。\n\n室管膜瘤这种病镇的可能存在脊髓内部，而且病程缓慢符合这类症状的特点。哦，不过要是脊髓外的问题，那脊膜瘤这种可能会导致脊髓半侧损害，这样就很吻合了。\n\n啊，神经纤维瘤有时候也出现类似的症状，不过更常见多发性问题和皮肤上的表现，她没有这些其他症状。这有点排除掉。\n\n脑胶质瘤或者椎管内转移瘤不太可能造成这样的表现，这个在脊髓半侧这样单纯的损害上，不是那么直接。\n\n所以，考虑到这些症状，还有病变的特性，我觉得首先还是脊膜瘤可能性最大，特别是与这种Brown-Séquard综合征这样的一侧症状损害表现最吻合。</think>\n结合患者的症状和体检结果，考虑到病变的性质以及脊髓半侧损害的特点，这些特征非常符合脊膜瘤的表现。因此，病变的定性诊断首先应考虑为脊膜瘤。\n\nA. 脊膜瘤"
}
```
## 模型训练
### 微调方法
使用LoRA技术对`Qwen3`模型进行微调。LoRA通过在预训练模型的权重矩阵中引入低秩矩阵来减少参数量，从而在保持模型性能的同时降低计算成本。
### 训练步骤
1. **加载预训练模型**: 加载`Qwen3`8B模型。
2. **应用LoRA**: 在模型的关键层应用LoRA技术。
3. **训练模型**: 使用准备好的肿瘤知识问答数据集进行微调。
4. **验证与测试**: 在验证集和测试集上评估模型性能，调整超参数以优化结果。
## 模型评估
### 评估指标
- **准确率**: 模型在问答任务中的准确率。
- **召回率**: 模型能够正确回答的问题比例。
- **F1分数**: 准确率和召回率的调和平均数。
### 评估结果
在测试集上的评估结果如下：
待更新
## 使用指南
### 环境配置
1. **Python版本**: 3.10+
2. **依赖库**:
- `transformers`
- `torch`
### 模型下载
SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
#模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('zpeng1989/Medical_Qwen3_8B_Large_Language_Model')
```
Git下载
```
#Git模型下载
git clone https://oauth2:eDTzbKYiKrNCswNiDx1s@www.modelscope.cn/zpeng1989/Medical_Qwen3_8B_Large_Language_Model.git
```
### 模型推理
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
# 加载微调后的模型
model = AutoModelForCausalLM.from_pretrained("path_to_your_model")
tokenizer = AutoTokenizer.from_pretrained("path_to_your_model")
# 输入问题
question = "请列出所有与葡萄胎相关的症状和体征?"
inputs = tokenizer(question, return_tensors="pt")
# 生成答案
outputs = model.generate(**inputs)
answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(answer)
```
### WEB部署
代码参考：
```
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import streamlit as st
import re
# 在侧边栏中创建一个标题和一个链接
with st.sidebar:
st.markdown("## 7B LLM")
max_length = st.slider("max_length", 0, 8192, 8192, step=1)
temperature = st.slider("temperature", 0.0, 1.0, 0.1, step=0.1)
# 创建一个标题和一个副标题
st.title("Model Chatbot")
st.caption("🚀 A streamlit chatbot powered by Self-LLM")
# 定义模型路径
mode_name_or_path = ''
# 文本分割函数
def split_text(text):
pattern = re.compile(r'<think>(.*?)</think>(.*)', re.DOTALL) # 定义正则表达式模式
match = pattern.search(text) # 匹配 <think>思考过程</think>回答
if match: # 如果匹配到思考过程
think_content = match.group(1).strip() # 获取思考过程
answer_content = match.group(2).strip() # 获取回答
else:
think_content = "" # 如果没有匹配到思考过程，则设置为空字符串
answer_content = text.strip() # 直接返回回答
return think_content, answer_content
# 定义一个函数，用于获取模型和 tokenizer
@st.cache_resource
def get_model():
# 从预训练的模型中获取 tokenizer
tokenizer = AutoTokenizer.from_pretrained(mode_name_or_path, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
# 从预训练的模型中获取模型，并设置模型参数
model = AutoModelForCausalLM.from_pretrained(mode_name_or_path, torch_dtype=torch.bfloat16, device_map="auto")
return tokenizer, model
# 加载 model 和 tokenizer
tokenizer, model = get_model()
# 如果 session_state 中没有 "messages"，则创建一个包含默认消息的列表
if "messages" not in st.session_state:
st.session_state["messages"] = [{"role": "assistant", "content": "有什么可以帮您的？"}]
# 遍历 session_state 中的所有消息，并显示在聊天界面上
for msg in st.session_state.messages:
st.chat_message(msg["role"]).write(msg["content"])
# 如果用户在聊天输入框中输入了内容，则执行以下操作
if prompt := st.chat_input():
# 在聊天界面上显示用户的输入
st.chat_message("user").write(prompt)
# 将用户输入添加到 session_state 中的 messages 列表中
st.session_state.messages.append({"role": "user", "content": prompt})
# 将对话输入模型，获得返回
input_ids = tokenizer.apply_chat_template(st.session_state.messages,tokenize=False,add_generation_prompt=True)
model_inputs = tokenizer([input_ids], return_tensors="pt").to('cuda')
generated_ids = model.generate(model_inputs.input_ids,max_new_tokens=max_length, temperature=temperature)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
think_content, answer_content = split_text(response) # 调用split_text函数，分割思考过程和回答
# 将模型的输出添加到 session_state 中的 messages 列表中
st.session_state.messages.append({"role": "assistant", "content": response})
# 在聊天界面上显示模型的输出
with st.expander("模型思考过程"):
st.write(think_content) # 展示模型思考过程
st.chat_message("assistant").write(answer_content) # 输出模型回答
# print(st.session_state) # 打印 session_state 调试
```
运行命令:
```
# nohup streamlit run Run_Test_v1.py --server.address 0.0.0.0 --server.port 6006 &
```
### 生成结果案例
#### Case 01
输入问题:
```
患者信息如下："""现病史
（1）病史摘要
病人，男，49岁，3小时前解大便后出现右下腹疼痛，右下腹可触及一包块，既往体健。
（2）主诉
右下腹痛并自扪及包块3小时。
体格检查
体温： T 37.8℃，P 101次／分，呼吸22次/分，BP 100/60mmHg，腹软，未见胃肠型蠕动波，肝脾肋下未及，于右侧腹股沟区可扪及一圆形肿块，约4cm×4cm大小，有压痛、界欠清，且肿块位于腹股沟韧带上内方。
辅助检查
（1）实验室检查
血常规：WBC 5.0×109／L，N 78％。
尿常规正常。
（2）多普勒超声检查
沿腹股沟纵切可见一多层分布的混合回声区，宽窄不等，远端膨大，边界整齐，长约4～5cm。
（3）腹部X线检查
可见阶梯状液气平。"""具体工作：简述该病人的诊断及诊断依据。
```
模型增加<think>返回结果：
```
<think>这个患者啊，49岁的男性，3小时前开始右下腹疼痛，还摸到一个包块。现在可麻烦了，得仔细看看。
首先，他的体温是37.8℃，有点发烧，虽然不很高，但总觉得不对劲儿。多普勒超声显示在腹股沟有个多层分布的肿块，有压痛，而且边界也不是特别清楚。这个看起来有点像感染，或者是 something 肿胀着。
说到感染，考虑到他是右下腹痛，首先会想到阑尾炎，毕竟这个地方容易出状况。不过，这个包块的位置在腹股沟韧带上方，这又好像更偏向直肠末端或者盆腔的问题了。
接着看看实验室检查，血常规显示白细胞计数是5.0×10^9/L，中性粒细胞占78%。嗯，这个中性粒细胞比例确实偏高，说明可能有细菌参与。不过也奇怪，为什么白细胞不高的？
再说说那些古怪的检查结果。多普勒超声描述的多层混合回声区，还有腹部X线的阶梯状液气平，嗯，这些特征总是导引我们去想绞窄性阑尾炎。绞窄性阑尾因为肿胀和缺血，很容易导致肠道梗阻和坏死，这些描述就越来越符合了。
从新理清一下，右下腹疼痛，腹股沟上方的包块，发热，多普勒超声的特征，再加上中性粒细胞增高，所有这些东西放在一起看，确实更像是绞窄性阑尾炎。
不再怀疑了，综合所有信息，这就是绞窄性阑尾炎，基于那些水乳交融的特征的符合，再加上诊断目的很吻合，应该就是它了。</think>
该病人的诊断为绞窄性阑尾炎。诊断依据包括：
1. 临床表现：患者为49岁男性，主要症状为右下腹痛3小时，并可触及包块。伴随轻微发热（37.8℃），提示可能存在感染或炎症。
2. 多普勒超声检查：显示腹股沟区域存在多层分布的混合回声区，边界整齐，长度约为4-5cm，提示可能有肿胀或组织坏死。
3. 腹部X线检查：出现阶梯状液气平，这一特征通常与肠道梗阻相关，可能进一步支持绞窄性变化的判断。
4. 实验室检查：血常规显示中性粒细胞比例高达78%，支持细菌感染的诊断，典型与阑尾炎相符。
综合上述信息中的炎症迹象、症状位置、影像学特征以及实验室检验结果，绞窄性阑尾炎是最符合的诊断。考虑到及时治疗的必要性，建议患者尽快进行进一步诊治。
```
模型去除<think>返回结果：
```
根据提供的患者信息，可以做出以下诊断：
诊断：急性腹股沟淋巴结炎，结合少量阶梯状液气平，需高度考虑并发肠梗阻的可能。
诊断依据：
1. **临床表现**：患者，男，49岁，3小时前解大便后出现右下腹疼痛，并自扪及包块。提示急性疼痛过程，且与肠道活动可能存在关联。
2. **体格检查**：体温升高至37.8℃，提示低热，可能存在轻度感染或炎症反应。右侧腹股沟区可扪及圆形肿块，约4cm×4cm大小，有压痛，界欠清，且肿块位于腹股沟韧带上内方。此与腹股沟淋巴结肿大一致，提示淋巴系统炎症。
3. **实验室检查**：血常规显示中性粒细胞比例为78%，提示存在明显炎症反应。结合体温略高，支持急性炎症的诊断。
4. **影像学检查**：
- 多普勒超声检查显示沿腹股沟纵切可见一多层分布的混合回声区，边界整齐，长约4～5cm。此为典型的淋巴结肿大的超声表现。
- 腹部X线检查显示阶梯状液气平，可能与肠道梗阻有关，需进一步评估以排除肠穿孔或严重的并发症。
综上，结合临床表现、体格检查及影像学检查结果，诊断为急性腹股沟淋巴结炎，并需警惕并发肠梗阻的可能，建议密切监测病情变化。
```
参考答案
```
诊断：嵌顿性腹股沟斜疝合并肠梗阻。
诊断依据：
①右下腹痛并自扪及包块3小时；
②有腹胀、呕吐，类似肠梗阻表现；腹部平片可见阶梯状液平，考虑肠梗阻可能；腹部B超考虑，
腹部包块内可能为肠管可能；
③有轻度毒性反应或是中毒反应，如 T 37.8℃，P 101次／分，白细胞中性分类78％；
④腹股沟区包块位于腹股沟韧带上内方。
```
#### Case 02
输入问题
```
患者信息如下："""现病史
（1）病史摘要
杨XX，女，59岁，30年前无明显诱因开始出现反酸、反食、烧心，胸骨后烧灼感，伴胃胀、嗳气，弯腰后反酸加重，不规律服用“奥美拉唑、吗丁啉、莫沙必利”症状可缓解，停药反复发作。5年前开始出现咳嗽、咳痰，咳嗽严重时伴胸闷、喘息症状，无明显季节性，常于进食后1小时及凌晨发作，止咳平喘效果不佳，生活质量明显下降。2年前外院诊为“反流性食管炎LA-B、食管裂孔疝，睡眠时床头抬高及、服用“耐信 20mg BID”反流症状明显缓解，咳喘症状亦明显缓解。近10个月咳喘症状加重，伴有听力下降，调整耐信 40mg BID，咳喘症状再次改善，但仍时有发作。
（2）主诉
反酸、烧心30年，咳嗽、咳痰、喘息5年，加重10个月。
体格检查
结果 T36.8℃，P70次/分，R20次/分，Bp136/80mmHg。
自主体位，神志清楚，全身皮肤及巩膜无黄染，全身浅表淋巴结无肿大。双肺听诊呼吸音粗及散在哮鸣音。心率70次/分，律齐，未闻及病理性杂音，腹部平软，肝脏、脾脏未触及，未触及腹部包块，肠鸣音正常。
辅助检查
（1）实验室检查
出凝血功能：正常；血生化：正常;血常规：正常。
（2）胃镜
反流性食管炎：LA-C；食管裂孔疝（混合型）。
（3）上消化道造影
反流性食管炎；食管裂孔疝。
（4）食管高分辨率测压
LES压力低于正常，食管体部频繁无效，食管裂孔疝。
（5）食管高分辨率测压
1.食管pH监测：未达到胃食管病理性酸反流；卧位酸廓清能力下降。
2.食管阻抗监测：反流总次数正常，以酸反流为主；
3.症状相关性分析：监测期间咳嗽、喘息症状与弱酸反流相关。
辅助检查
胃镜：
所见：齿状线上移约4cm，可见多条纵行糜烂，底部有融合，齿状线不规整，周围可见充血、水肿、糜烂。 贲门口松弛。反转胃镜可见食管裂孔疝疝囊。
结论：反流性食管炎：LA-C；食管裂孔疝（混合型）。
辅助检查
食管pH-阻抗监测（口服PPI期间）
食管pH监测显示： DeMeester积分为8.0（正常值<14.7）；酸反流时间百分比（AET）为2.1%（正常值<4.2%），卧位酸反流时间所占百分比大于正常。卧位酸清除时间延长。
食管阻抗监测显示：食团反流总时间百分比（BET）为1.2%（正常值<1.4%），立位食团反流时间百分比大于正常；反流总次数为48次（正常值<73次），其中酸反流32次，弱酸反流5次，弱碱反流3次，酸性气体反流2次，弱酸性气体反流4次，弱碱性气体反流2次。立位食团清除时间延长。
症状相关性分析：
1、患者监测期间共记录咳嗽症状17次，与弱酸反流相关4次，弱酸反流的SI为24%、SAP为99%。
2、患者监测期间共记录喘息症状5次，与弱酸反流相关2次。弱酸反流的SI为40%，SAP为 96%。
注：SI为反流/症状指数 ，参考值>50%；SAP：反流/症状相关概率，参考值>95%。
辅助检查
上消化道造影：可见巨大食管裂孔疝，贲门及胃底均疝入胸腔。
辅助检查
食管高分辨率测压：
LES压力低于正常，吞咽时松弛正常。
UES压力低于正常，松弛功能欠佳。
食管体部频繁无效蠕动 (无效吞咽百分比50%) 。
食管裂孔疝。"""具体工作：分析本例病人的病史、体格检查和辅助检查。
```
模型增加<think>返回结果：
```
<think>哦，这位女士的反酸和烧心症状看起来真的很让人头疼啊，从30年前就开始了。说起来，这些症状听起来就像典型的反流性食管炎，还伴有食管裂孔疝，这让情况变得更复杂了。经过几次检查，像胃镜和上消化道造影，结果一致指向了这些结论，看来这些是相当可能的诊断。
而且更有趣的是，她的咳喘症状也很有特点。咳嗽和喘息竟然在她5年开始了，而且常在吃饭后一小时和凌晨的时候发作。这跟胃食管反流的联系真是剪不断理还乱了。万万没想到，她的呼吸问题竟然和反流有着这么明显的关联。
哦，最近的检测确实揭露了不少关键信息——食管pH-阻抗监测在她服用PPI期间显示酸反流的时间还比较长，尤其是晚上，酸清除能力似乎不太好。这解释了她需要调整药物剂量从耐信20mg BID到40mg BID，而这样做对症状又有了一定的改善。
体格检查方面，嗯，看似简单的结果其实也给出了不少提示：体温正常，心跳呼吸都还算平稳。不过，肺部那些散布的哮鸣音还真让人担心。好在腹部检查是平的，没有奇怪的发现，不过这贲门口有些松弛，就足以结合她的食管问题做出诊断了。
通过这些信息综合来看，反流性食管炎和食管裂孔疝的诊断似乎说得通。说到底，她的症状、检查结果以及与反流的联系都指向了这个方向。这一结论看起来是成立的，也不令人意外。</think>
对该病人的病史、体格检查和辅助检查结果进行分析，可以得出以下结论：
1. **疾病摘要**：病人，杨女士，59岁，长期受反酸、烧心、胸骨后烧灼感等典型的反流性食管炎症状困扰。此外，她还经历了咳嗽、咳痰、喘息等与呼吸系统相关的问题，这些症状在进食后及凌晨时分更明显，严重影响其生活质量。
2. **体格检查结果**：生命体征基本正常，但双肺听诊时可发现呼吸音粗，散在的哮鸣音提示存在肺部问题。这与她长期的反流现象可能有一定关联。
3. **辅助检查**：
- **胃镜检查**显示杨女士患有反流性食管炎LA-C级和食管裂孔疝（混合型）。
- **食管高分辨率测压**揭示LES（下食管环) 压力不足，食管体部蠕动无力，并证实食管裂孔疝的存在。
- **食管pH-阻抗监测**（口服PPI期间) 显示卧位时酸反流时间较长，表明尽管药物效果总体尚可，某些时段酸反流仍需关注。
- **症状相关性分析**指出，她的咳嗽和喘息症状与弱酸反流显著相关。
综合以上信息，杨女士的诊断为反流性食管炎合并食管裂孔疝是相当明确的。她的咳喘症状与胃食管反流密切相关，这在同类患者中也不罕见。体格检查及各项检查结果相互支持，诊断具有说服力。根据现有资料，调整PPI剂量至40mg BID已对她当前的症状提供了较好的控制，但未来仍需监测调整治疗方案，防止其他并发症的进展。
```
模型去除<think>返回结果：
```
根据提供的信息，对该病人的病史、体格检查和辅助检查可以进行如下分析：
1. **病史分析**
- 杨女士，59岁，女性，长期（已有30年）遭受胃食管反流的困扰，主要表现为反酸、烧心、胸骨后烧灼感等。这些症状在服用PPI（如耐信）和促胃肠动力药后能够暂时缓解，但停药后又会反复发作。
- 此外，她还经历了5年的咳嗽、咳痰和喘息症状，这些呼吸道症状与胃食管反流明显相关。症状常在胸骨后反酸或嗳气时加重，尤其是站立或弯腰时。
- 2年前，通过抬高睡眠时的床头和调整用药（使用耐信 20mg BID），反流及相关咳喘症状有所改善。然而，近1年咳喘症状加重，并伴随听力下降。
- 调整用药为耐信 40mg BID后，反流和咳喘症状再次改善，但仍未完全控制，时有发作。这表明胃食管反流问题仍然严重，对呼吸道有持续影响。
2. **体格检查结果**
- 病人生命体征基本正常，体温 36.8 ℃，心率 70 次/分，呼吸频率 20 次/分，血压 136/80 mmHg。
- 双肺听诊时可闻及呼吸音粗糙及散在的哮鸣音，提示存在明显的呼吸道分泌增加或支气管痉挛。
- 腹部检查显示平坦柔软，未触及异常。
3. **辅助检查结果**
- **胃镜检查**显示：反流性食管炎 LA-C 级和食管裂孔疝（混合型）。这解释了她长期的胃食管反流症状，同时也为呼吸道症状提供了一个可能的机制，即反流物质上移刺激迷走神经所致。
- **上消化道造影**结果与胃镜一致，进一步确诊了食管裂孔疝和反流性食管炎。
- **食管高分辨率测压**指出 LES（食管下括约肌）和 UES（上食管括约肌）压力均低于正常，且食管体部存在无效蠕动频率增加，这为胃食管反流提供了解剖学基础。
- **食管 pH-阻抗监测**（口服 PPI 期间）结果显示酸反流时间百分比略低于正常，但卧位酸反流时间增加，酸清除时间延长，提示夜间反流严重。
- 阻抗监测进一步显示立位食团反流时间增加，证实食物团块的反流也是重要因素。
- **症状相关性分析**表明，患者的咳嗽和喘息症状主要与弱酸反流相关。根据标准，反流/症状指数（SI）大于 50% 和症状/反流相关概率（SAP）大于 95% 即表明症状与反流具有统计学显著的相关性。
综合以上分析，杨女士的主要问题为严重的胃食管反流合并食管裂孔疝，且已对呼吸道造成显著影响。改善反流控制，可能对呼吸道症状产生积极效果。同时，还需考虑多学科治疗方案，结合消化系统和呼吸系统的问题进行综合管理。
```
参考结果
```
（1）病史分析：该病例的早期症状为反酸、反食、烧心，胸骨后烧灼感、嗳气等典型胃食管反流症状为主，抗反流用药治疗可缓解症状，即可诊断为胃食管反流病。之后患者逐渐出现咳嗽、咳痰和喘息等哮喘样症状，该症状呼吸内科治疗效果不佳，再进行抗反流治疗后不但反酸、烧心得到明显缓解，而且哮喘样症状也得到明显缓解。
本病例特点为：①先出现典型胃食管反流病症状，后出现咳嗽、喘息等食管外症状；②抗反流药物治疗可同时缓解反酸、烧心以及咳喘症状。
（2）体格检查分析：体格检查方面此病例在咳喘发作间期无过多的阳性体征，肺部听诊可闻及哮鸣音。
（3）辅助检查分析：本例病人实验室检查无明显异常。通过胃镜、上消化道造影、食管高分辨率测压检查明确患者存在食管裂孔疝和反流性食管炎，食管pH-阻抗检查（口服PPI期间）进一步证实患者的咳嗽和喘息症状均与反流有显著相关性。上述客观检查确诊患者为胃食管反流病，反流性哮喘可能性大。
```
## 许可证
本项目采用 [MIT 许可证](LICENSE)。
## 致谢
- 感谢 `Qwen` 模型的开发者。
- 感谢所有为医疗知识问答数据集做出贡献的研究人员。
## 联系方式
如有任何问题，请联系 [592392714@qq.com]。
---
**注意**: 本项目仅供学术研究使用，不构成医疗建议。

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</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
}

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"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
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"task":"text-generation"}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"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"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12e7e697bde62f769afeafca438609824c2e7c25257862bbffc552d60e8bed2d
size 1915768080

3
model-00002-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e5f9d3964dc209e2222c915cf1ee3020658925c8de020d24bb22c9e632c0b3f6
size 1929470608

3
model-00003-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:adea910db94f5aca6f89cbe230bcbce4f56b62eb63cdeaa6dd65c31bc9e20bff
size 1929470632

3
model-00004-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:397249c8c91a766aebb7ab90b4d1b8cfce231376fdfd41c7b9bf8051993e8130
size 1929470664

3
model-00005-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38c43d82cd88cb075dd035ad7414042ccf0e7327736c29a6c607189874c376f8
size 1929470664

3
model-00006-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb65c8584f61a433d5ea01d1c66bca70ba3fa3700c656b31564be5042a85ca87
size 1929470664

3
model-00007-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:761cc3aab45decfa4ba16451c695506941e5211350c1dde2c954c0375f5a9c8d
size 1929470664

3
model-00008-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f991be7f9c8cb2e2641b0f9c51a48b815998e06078665bdf1dd94a6ac300bbdd
size 1644264840

3
model-00009-of-00009.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20c2d6366ab85c90786ccdd829cd2b9e7d30ef3b2ebbb998280e7e4014b542ff
size 1244659840

406
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,406 @@
{
"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"
}
}

31
special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"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
}
}

757480
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

241
tokenizer_config.json Normal file
View File

@@ -0,0 +1,241 @@
{
"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
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long