"vscode:/vscode.git/clone" did not exist on "180ab8c8464d1c2a22556df9923696bbc2c92076"
Commit 9869dc3e authored by zhouxiang's avatar zhouxiang
Browse files

修改readme

parent 597fe8a4
......@@ -76,7 +76,7 @@ python setup.py install
# 如果有现成的原版qwen-7b的运行环境中,可以将模型转换脚本qwen2flm.py移动到原版qwen-7b的运行环境中,
# 也可以通过执行pip install -r requirements.txt安装模型转换所需依赖;
# 如果使用已经下载完成的模型或者自己finetune的模型需要修改qwen2flm.py文件中创建tokenizer, model时的模型存放路径
# 执行:
# 在本工程目录下执行:
python3 qwen2flm.py qwen-7b-fp16.bin float16 # 导出fp16模型,参数为导出的模型路径
python3 qwen2flm.py qwen-7b-int8.bin int8 # 导出int8模型,参数为导出的模型路径
```
......
......@@ -13,7 +13,7 @@ if __name__ == "__main__":
model_path = args.path
prompts = ["深圳有什么好玩的", "上海有什么好玩的", "晚上睡不着怎么办", "南京有什么好吃的"]
prompts = ["深圳有什么好玩的", "上海有什么好玩的", "晚上睡不着怎么办", "南京有什么好吃的"] * 2
print(prompts)
responses, historys = [], []
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment