model quantization request :)

#2
by snakeying - opened

bartowski, my man~

can you quantizate shareAI/llama3.1-8b-instruct-dpo-zh plz~?

or should i wait for this PR https://github.com/ggerganov/llama.cpp/pull/8676 to be finalized?

I'm waiting for that to be finalized and then I'm gonna start making all the llama 3.1s haha

thx man, i will wait then.

it has been merged~~

yup :D started with 70b, gonna make 8b, then go through all these fine tunes :)

thx~bartowski, u rock!

snakeying changed discussion status to closed

Ah nvm i guess I can't make that one because they didn't post the full model, only a q4 GGUF :(

It seems the full model version is posted on ModelScope instead, the model card contains git link for safetensors files.

Sign up or log in to comment