Quant pls

#1
by Yhyu13 - opened

@TheBloke

HI, I've create a sft version of Phi2 with alpca gpt4 en dataset, and it surpass GPT3.5 davinci on the AlpcaEval benchmark from my local run with Chatgpt as annotator, would you like to quant this model?

Thanks!

Many thanks for the finetune, output from initial testing looks good.
Have a set of quants up here: https://huggingface.co./afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF

Sign up or log in to comment