如何微调Chinese-Vicuna-7b模型

环境建议:使用谷歌云GCP,国内的云环境实在是太慢了哦。github慢,pip 慢,下载模型也慢。

1.下载环境

!git clone https://github.com/Facico/Chinese-Vicuna
!pip install -r ./Chinese-Vicuna/requirements.txt

2. 准备数据 json/jsonl格式

3. 微调

!python ./Chinese-Vicuna/finetune.py --data_path /content/Chinese-Vicuna/sample/instruct/data_sample.jsonl --test_size 5

4.生成web界面

!python ./Chinese-Vicuna/generate.py --model_path decapoda-research/llama-7b-hf --lora_path /content/lora-Vicuna --use_local 0

5.运行界面

猜你喜欢

转载自blog.csdn.net/wxl781227/article/details/130771263
今日推荐