Hugging Face's logo

TheBloke
/
guanaco-7B-HF

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
4

TGI unwanted chinese output

#2
by SinanAkkoyun - opened
Discussion
SinanAkkoyun

Hello! When running with HF's text-generation-inference code, the model almost always outputs chinese. The exact prompts return normal responses with other inference solutions.

Could anyone please help?

SinanAkkoyun

https://github.com/huggingface/text-generation-inference/issues/397

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment