镜像自地址
https://github.com/SCIR-HI/Huatuo-Llama-Med-Chinese.git
已同步 2025-12-06 14:36:49 +00:00
update readme
这个提交包含在:
@@ -17,6 +17,7 @@ pip install -r requirements.txt
|
|||||||
```
|
```
|
||||||
### 模型下载
|
### 模型下载
|
||||||
LORA权重可以通过[百度网盘](https://pan.baidu.com/s/1jih-pEr6jzEa6n2u6sUMOg?pwd=jjpf)和[HuggingFace](https://huggingface.co/thinksoso/lora-llama-med)下载
|
LORA权重可以通过[百度网盘](https://pan.baidu.com/s/1jih-pEr6jzEa6n2u6sUMOg?pwd=jjpf)和[HuggingFace](https://huggingface.co/thinksoso/lora-llama-med)下载
|
||||||
|
|
||||||
下载LORA权重并解压,解压后的格式如下:
|
下载LORA权重并解压,解压后的格式如下:
|
||||||
|
|
||||||
```
|
```
|
||||||
|
|||||||
19
data/tmp.py
19
data/tmp.py
@@ -1,19 +0,0 @@
|
|||||||
import json
|
|
||||||
|
|
||||||
# 假设数据存储在 data.json 文件中
|
|
||||||
data = []
|
|
||||||
with open('llama_data.json', 'r') as f:
|
|
||||||
lines = f.readlines()
|
|
||||||
for line in lines:
|
|
||||||
line = line.strip()
|
|
||||||
data.append(json.loads(line))
|
|
||||||
|
|
||||||
# 遍历每个对象,找到 output 属性不为字符串类型的对象
|
|
||||||
new_data = []
|
|
||||||
for obj in data:
|
|
||||||
if isinstance(obj['output'], str):
|
|
||||||
new_data.append(obj)
|
|
||||||
with open("llama_data_1.json","w") as f:
|
|
||||||
for n in new_data:
|
|
||||||
f.write(json.dumps(n,ensure_ascii=False))
|
|
||||||
f.write("\n")
|
|
||||||
在新工单中引用
屏蔽一个用户