Hugging Face's logo

AlekseyKorshuk
/
vicuna-7b

Text Generation Transformers PyTorch llama Inference Endpoints text-generation-inference
Model card Files Community
11

I made a GPTQ 4bit 128g version of this model

#3
by TheBloke - opened
Discussion
TheBloke

It can be found here: https://huggingface.co/TheBloke/vicuna-AlekseyKorshuk-7B-GPTQ-4bit-128g

AlekseyKorshuk
 Owner

Would you like to make a merge request to this repo?

TheBloke

I think it might be good to keep it separate, so people can clone the model they want without getting files they don't need.

I saw your comment about accepting a PR for a README.md - how about I PR a README which includes a link to the GPTQ version? What do you think?

TheBloke

I PR'd a README.md if you would like to use it

wolfram

Thank you both! This has become my favorite model - the power of Vicuna, finally unfiltered.

Now that there's vicuna-7B-1.1, would an update make sense?

Sign up or log in to comment