zpeng1989/Medical_DeepSeek_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_DeepSeek_Large_Language_Model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-05 14:47:14 +08:00
commit e97762b62a
18 changed files with 1253933 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

430
README.md Normal file
View File

@@ -0,0 +1,430 @@
# 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`DeepSeek`蒸馏的LLAMA-8B模型作为基座模型[deepseek-ai/DeepSeek-R1-Distill-Llama-8B]，使用LoRA（Low-Rank Adaptation）技术进行微调。继承DeepSeek模型增加"深度思考模式(think)"。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DeepSeek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**:[`deepseek-ai/DeepSeek-R1-Distill-Llama-8B`]<https://modelscope.cn/models/deepseek-ai/DeepSeek-R1-Distill-Llama-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`deepseek-R1`蒸馏模型进行微调。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`deepseek-R1`蒸馏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
from modelscope import snapshot_download
model_dir = snapshot_download('zpeng1989/Medical_DeepSeek_Large_Language_Model')
```
Git下载
```
#Git模型下载
git clone https://oauth2:eDTzbKYiKrNCswNiDx1s@www.modelscope.cn/zpeng1989/Medical_DeepSeek_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。
```
模型返回结果：
```
<think>患者是一位49岁的男性，3小时前解大便后开始右下腹疼痛，并且能够触到一个包块，这让我觉得有点不妙。哦，他以前身体挺健康的。现在右下腹疼痛已经有3小时，并且能摸到一个约4cm×4cm的肿块，这听起来像是有什么东西在那里耍鬼。
他的实验室检查显示白细胞计数偏高，N 78％，这通常意味着可能有感染。多普勒超声显示在腹股沟纵切线上有一个多层分布的混合回声区，看起来不太规则，远端膨大而且边界很整齐，这可能暗示有一个实性肿瘤或者积液。
再看看他的腹部X线，显示有阶梯状的液气平，这进一步支持我的猜测，很可能是腹腔内有某种积液或者肿瘤。
结合这些信息，我觉得最有可能的诊断是腹腔癌症。特别是考虑到他在腹股沟韧带上能摸到一个肿块，这很典型地指向了盆腔的病变。哦，等等，阶梯状液气平也可能是因为腹腔内有液体的存在，这让我得再想想。
不过，结合他的症状、体格检查和影像学结果，特别是腹部X线的阶梯状液气平，我觉得更可能是腹腔内有一个膨大的肿块，像是肿瘤。
所以，综合考虑下来，我觉得他可能是腹腔内膨大的病变，比如说肿瘤。这个结论看起来更合理，也符合他的所有表现。/n</think>
根据提供的患者信息，这位49岁的男性患者主要表现为右下腹疼痛和可触及的肿块，结合实验室检查中的白细胞计数升高、多普勒超声的特征表现以及腹部X线的特殊征象，最有可能的诊断是腹腔内的膨大病变，尤其是可能的肿瘤。
具体诊断依据如下：
1. **体格检查**：患者在右侧腹股沟区可触及一个圆形肿块，界限不清，压痛点存在，提示可能存在实性肿块。
2. **实验室检查**：血常规中白细胞计数升高（N 78％），提示可能存在感染或炎症过程。此白细胞计数结合其他症状的出现，需警惕感染性或恶性病变的可能性。
3. **影像学检查**：
- 多普勒超声显示腹股沟纵切线上多层分布的混合回声区，宽窄不等、远端膨大且边界整齐，符合腹腔内实性肿瘤或积液的特征。
- 腹部X线显示阶梯状液气平，提示腹腔内可能存在膨大的液体或肿块，常见于腹腔癌症或腹膜后肿瘤。
综合以上信息，考虑该患者最可能的诊断为腹腔内膨大的病变，尤其是盆腔的肿瘤，需进一步进行必要的影像学检查和组织病理学活检以明确诊断。建议尽快就医，接受进一步的诊断和治疗。
患者是一位49岁的男性，3小时前解大便后开始右下腹疼痛，并且能够触到一个包块，这让我觉得有点不妙。哦，他以前身体挺健康的。现在右下腹疼痛已经有3小时，并且能摸到一个约4cm×4cm的肿块，这听起来像是有什么东西在那里耍鬼。
他的实验室检查显示白细胞计数偏高，N 78％，这通常意味着可能有感染。多普勒超声显示在腹股沟纵切线上有一个多层分布的混合回声区，看起来不太规则，远端膨大而且边界很整齐，这可能暗示有一个实性肿瘤或者积液。
再看看他的腹部X线，显示有阶梯状的液气平，这进一步支持我的猜测，很可能是腹腔内有某种积液或者肿瘤。
结合这些信息，我觉得最有可能的诊断是腹腔癌症。特别是考虑到他在腹股沟韧带上能摸到一个肿块，这很典型地指向了盆腔的病变。哦，等等，阶梯状液气平也可能是因为腹腔内有液体的存在，这让我得再想想。
不过，结合他的症状、体格检查和影像学结果，特别是腹部X线的阶梯状液气平，我觉得更可能是腹腔内有一个膨大的肿块，像是肿瘤。
所以，综合考虑下来，我觉得他可能是腹腔内膨大的病变，比如说肿瘤。这个结论看起来更合理，也符合他的所有表现。/n
根据提供的患者信息，这位49岁的男性患者主要表现为右下腹疼痛和可触及的肿块，结合实验室检查中的白细胞计数升高、多普勒超声的特征表现以及腹部X线的特殊征象，最有可能的诊断是腹腔内的膨大病变，尤其是可能的肿瘤。
具体诊断依据如下：
1. **体格检查**：患者在右侧腹股沟区可触及一个圆形肿块，界限不清，压痛点存在，提示可能存在实性肿块。
2. **实验室检查**：血常规中白细胞计数升高（N 78％），提示可能存在感染或炎症过程。此白细胞计数结合其他症状的出现，需警惕感染性或恶性病变的可能性。
3. **影像学检查**：
- 多普勒超声显示腹股沟纵切线上多层分布的混合回声区，宽窄不等、远端膨大且边界整齐，符合腹腔内实性肿瘤或积液的特征。
- 腹部X线显示阶梯状液气平，提示腹腔内可能存在膨大的液体或肿块，常见于腹腔癌症或腹膜后肿瘤。
综合以上信息，考虑该患者最可能的诊断为腹腔内膨大的病变，尤其是盆腔的肿瘤，需进一步进行必要的影像学检查和组织病理学活检以明确诊断。建议尽快就医，接受进一步的诊断和治疗。
```
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。
```
模型结果
```
<think>患者的病史显示她有长期的反酸、烧心症状，这已经持续了30年。这些症状在弯腰后加重，并且一些药物能缓解症状，但停药容易复发。最近几年她还开始出现咳嗽、咳痰和喘息，尤其是在饭后一个小时和早晨发作。她的生活质量受到这些症状的显著影响。
体格检查显示她的体温正常，但呼吸频率偏高，有散在的哮鸣音，这可能提示气道有问题。血液检查是正常的，没有黄染，淋巴结也没有肿大。通过胃镜和上消化道造影确认了反流性食管炎以及食管裂孔疝，这似乎解释了她反复的反酸和呼吸问题。
食管高分辨率测压结果显示食管的吞咽功能不太好，频繁无效，尤其是在吞咽的时候有50%的无效情况。这种无效吞咽进一步表明食管的功能受损严重。
通过食管pH-阻抗监测，发现她有酸反流，但卧位酸反流时间比例高于正常，并且卧位酸清除时间延长。食团反流的次数也较多，尤其是酸反流。这些结果表明酸反流对她的咳嗽和喘息有显著影响。
胃镜结果显示齿状线上有糜烂，并伴有充血、水肿和糜烂，贲门口也松弛，这进一步证实了反流性食管炎和食管裂孔疝的诊断。
患者的DeMeester积分和AET在正常范围内，但卧位反流时间的百分比高于正常。BET也在正常范围，但立位食团反流时间延长，说明反流问题主要在立位。症状相关性分析显示咳嗽和喘息与弱酸反流密切相关，这进一步支持反流对症状的影响。
综合来看，这位患者的症状与反流性食管炎和食管裂孔疝高度相关。她的食管功能有显著损害，需要综合治疗来缓解反流和呼吸问题。/n</think>
根据您提供的病例描述，这位59岁的女性患者有一个复杂的胃肠道问题。我们从她的病史中可以看到，她长期面对反酸、烧心等消化道症状，这些症状在某些药物的使用下可以暂时缓解，但容易复发。近年来，她还出现了咳嗽、咳痰和喘息的问题，这些症状与她的食管情况密切相关。
体格检查提示她有呼吸系统的问题，呼吸频率略高，并且在肺部听诊中发现了散在的哮鸣音，这可能是由于食管裂孔疝导致的气道异常。
胃镜和上消化道造影结果确认了反流性食管炎（LA-C）和食管裂孔疝，这解释了她的反复性反酸和呼吸道症状。食管高分辨率测压结果显示食管吞咽功能下降，频繁无效，尤其是在吞咽时有50%的无效情况，这进一步表明食管功能受损严重。
通过食管pH-阻抗监测，患者有酸反流，但卧位酸反流时间比例高于正常，并且卧位的酸清除时间延长。食团反流的次数较多，尤其是酸反流，对她的咳嗽和喘息有显著影响。胃镜结果显示齿状线上的糜烂以及贲门松弛进一步支持诊断。
总的来说，这位患者的症状与反流性食管炎和食管裂孔疝高度相关。她的食管功能受损明显，需要综合治疗来缓解反流和呼吸问题。根据目前的诊断，调整和维持药物治疗，包括质子泵抑制剂，可能是治疗的关键。同时，生活方式的改变，如姿势管理和食物选择，也有助于改善症状。建议她定期随访，监测治疗效果，并根据症状变化及时调整治疗方案。
患者的病史显示她有长期的反酸、烧心症状，这已经持续了30年。这些症状在弯腰后加重，并且一些药物能缓解症状，但停药容易复发。最近几年她还开始出现咳嗽、咳痰和喘息，尤其是在饭后一个小时和早晨发作。她的生活质量受到这些症状的显著影响。
体格检查显示她的体温正常，但呼吸频率偏高，有散在的哮鸣音，这可能提示气道有问题。血液检查是正常的，没有黄染，淋巴结也没有肿大。通过胃镜和上消化道造影确认了反流性食管炎以及食管裂孔疝，这似乎解释了她反复的反酸和呼吸问题。
食管高分辨率测压结果显示食管的吞咽功能不太好，频繁无效，尤其是在吞咽的时候有50%的无效情况。这种无效吞咽进一步表明食管的功能受损严重。
通过食管pH-阻抗监测，发现她有酸反流，但卧位酸反流时间比例高于正常，并且卧位酸清除时间延长。食团反流的次数也较多，尤其是酸反流。这些结果表明酸反流对她的咳嗽和喘息有显著影响。
胃镜结果显示齿状线上有糜烂，并伴有充血、水肿和糜烂，贲门口也松弛，这进一步证实了反流性食管炎和食管裂孔疝的诊断。
患者的DeMeester积分和AET在正常范围内，但卧位反流时间的百分比高于正常。BET也在正常范围，但立位食团反流时间延长，说明反流问题主要在立位。症状相关性分析显示咳嗽和喘息与弱酸反流密切相关，这进一步支持反流对症状的影响。
综合来看，这位患者的症状与反流性食管炎和食管裂孔疝高度相关。她的食管功能有显著损害，需要综合治疗来缓解反流和呼吸问题。/n
根据您提供的病例描述，这位59岁的女性患者有一个复杂的胃肠道问题。我们从她的病史中可以看到，她长期面对反酸、烧心等消化道症状，这些症状在某些药物的使用下可以暂时缓解，但容易复发。近年来，她还出现了咳嗽、咳痰和喘息的问题，这些症状与她的食管情况密切相关。
体格检查提示她有呼吸系统的问题，呼吸频率略高，并且在肺部听诊中发现了散在的哮鸣音，这可能是由于食管裂孔疝导致的气道异常。
胃镜和上消化道造影结果确认了反流性食管炎（LA-C）和食管裂孔疝，这解释了她的反复性反酸和呼吸道症状。食管高分辨率测压结果显示食管吞咽功能下降，频繁无效，尤其是在吞咽时有50%的无效情况，这进一步表明食管功能受损严重。
通过食管pH-阻抗监测，患者有酸反流，但卧位酸反流时间比例高于正常，并且卧位的酸清除时间延长。食团反流的次数较多，尤其是酸反流，对她的咳嗽和喘息有显著影响。胃镜结果显示齿状线上的糜烂以及贲门松弛进一步支持诊断。
总的来说，这位患者的症状与反流性食管炎和食管裂孔疝高度相关。她的食管功能受损明显，需要综合治疗来缓解反流和呼吸问题。根据目前的诊断，调整和维持药物治疗，包括质子泵抑制剂，可能是治疗的关键。同时，生活方式的改变，如姿势管理和食物选择，也有助于改善症状。建议她定期随访，监测治疗效果，并根据症状变化及时调整治疗方案。
```
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。
```
## 思考
其实做这个项目同时对于DeepSeek蒸馏的Qwen模型也做了微调，但相同参数下，Qwen的返回就会中英文混杂，具体问题还在排查。如果有人有经验欢迎讨论；
但在llama的模型上训练的结果感觉不如直接在原模型上训练来的好，后续修改参数和配置会持续更新模型；
## 许可证
本项目采用 [MIT 许可证](LICENSE)。
## 致谢
- 感谢 `DeepSeek` 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。

36
config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_name_or_path": "DeepSeek_R1_llama_8B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"use_cache": true,
"vocab_size": 128256
}

1
configuration.json Normal file
View File

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

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": 128001,
"temperature": 0.6,
"top_p": 0.95,
"transformers_version": "4.48.3"
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad935310cbea59dd4e8ec183b3a67d8f685de32c33deb761143ee879d83b5e9e
size 1973455376

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:390964da3228dadead92a2f42ebe541b11376a67870384f8070be3f5da084f75
size 1895895336

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:70380eac5129d3a67dddcbc4e1439569eaef5808eedce137318f0cf6a5c4af49
size 1979798040

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05eddf8ac6689f6c5a435e77df802a77adff63ff489d337b9159ae98c0766236
size 1946227368

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38d826638b3d51bf2eb6a9bd19b5a738e7dfa401f3e5bd4a63b9a63b0ae8cbbd
size 1979798064

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb43378b2b5c3b1004b0667fd51374f71b734c02aa63b06a17e956a62348d7da
size 1946227368

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9292a4089b6994d2d0d2ea01dc3374c1f203be049bb70172359d11cedf4074b9
size 1979798064

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cbb75af5b3027158403c0fe7a23145046cdfa2f61fcac9812dae14ee0c780e7a
size 1308683424

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d617c29ce19434a764165114c4e7825cf927f90b3bb45fd181732a0dd13b0a57
size 1050673280

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 16060522496
},
"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_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_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-00001-of-00009.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-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-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_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_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_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-00004-of-00009.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00004-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_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_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_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_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_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_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-00005-of-00009.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00005-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_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-00005-of-00009.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00005-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_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_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_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_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_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_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_proj.weight": "model-00001-of-00009.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
"model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00006-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-00006-of-00009.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00006-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_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_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_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_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-00007-of-00009.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00007-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_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-00007-of-00009.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00007-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-00007-of-00009.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00007-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_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_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_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_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-00008-of-00009.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00008-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_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_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-00008-of-00009.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00008-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-00008-of-00009.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
"model.layers.31.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_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_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_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_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-00003-of-00009.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00003-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_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_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_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_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_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_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_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"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<｜begin▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

1250993
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

2069
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff