search

Facico / Chinese-Vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca
https://github.com/Facico/Chinese-Vicuna
Apache License 2.0
4.14k stars 425 forks source link

运行chat_7B.sh聊两句话out of memory #244

Closed hdjghjb closed 1 year ago

hdjghjb commented 1 year ago

两张2080ti 运行zsh chat_7B.sh脚本后成功启动gradio，可以正常聊天，但聊几句后报cuda out of memory，不知道有没有方法改善？如果只聊两三句话就无法运行，有不便利的地方。