text-generation-inference
text-generation-inference copied to clipboard
支持更多的中文模型:Qwen、Baichuan、InternLM、ChatGLM2等多卡部署
Model description
首先,十分感谢您们的开源。
然后。以上都是比较有名的中文开源大模型,基本上都可以使用transformers库加载并进行推理。
最后。在单张卡上使用TGI进行推理是没有问题的,但是在多张卡上会报错shard is not supported for AutoModel。在受限的资源下,比如两张12G的显卡,使用多卡部署还是很有必要的,希望能够支持更多的中文模型。
Open source status
- [X] The model implementation is available
- [X] The model weights are available
Provide useful links for the implementation
https://github.com/InternLM/InternLM
https://github.com/QwenLM/Qwen-7B
https://github.com/baichuan-inc/Baichuan-7B https://github.com/baichuan-inc/Baichuan-13B
https://github.com/THUDM/ChatGLM2-6B
千问-chat对话没法结束是啥情况?
千问-chat对话没法结束是啥情况?
Do you add stop words when decoding ?
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.
这是来自QQ邮箱的自动回复邮件。您好~您发送的邮件我已收到。谢谢您的邮件~
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.