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 422 forks source link

如何部署本地api化的模型而不是使用gradio 的界面 #203

Closed zhiyixu closed 1 year ago

zhiyixu commented 1 year ago

我找到了gradio给出的gradio_client库,然后借助flask 搭建了一个api, 使用 gunicorn 启动flask app 之后,提问后报错[2023-06-01 13:41:15 +0800] [346981] [WARNING] Worker with pid 346982 was terminated due to signal 9,但是不使用flask 直接用gradio_client来进行请求倒是正确的,之前的那个错误原因找不出来, 请问咱们这边有没有api化部署的方式?

zhiyixu commented 1 year ago

设置gunicorn 超时时间就完事了....