Commit 4d445880 authored by zhouxiang's avatar zhouxiang
Browse files

更新readme

parent 0ff1156e
......@@ -59,6 +59,9 @@ python setup install
# 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baichuan2flm.py文件中创建tokenizer, model时的模型存放路径
# 执行:
python3 baichuan2flm.py baichuan-13b-fp16.bin float16 # 导出fp16模型,参数为导出的模型路径
# 如果使用的dcu显存为16G,则需要用int8精度模型:
python3 baichuan2flm.py baichuan-13b-int8.bin int8 # 导出fp16模型,参数为导出的模型路径
```
......@@ -90,7 +93,7 @@ chmod +x benchmark
## 运行效果展示
![baochuan推理](baichuan推理.gif)
![baochuan推理](baichuan13b-chat.png)
## 应用场景
......
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