llm icon indicating copy to clipboard operation
llm copied to clipboard

Support for `GPTBigCode`

Open ekolawole opened this issue 1 year ago • 1 comments

What we need is local cpp for llm "HuggingFaceH4/starchat-alpha A". It is much better than any other open source chat models at coding. And it does very well at chatting too. This is better than Vicuna.

ekolawole avatar May 14 '23 00:05 ekolawole

https://huggingface.co/docs/transformers/model_doc/gpt_bigcode

https://huggingface.co/HuggingFaceH4/starchat-alpha/blob/main/config.json

Looks to be a GPT-2 variant.

philpax avatar May 15 '23 17:05 philpax

This should be solved with the last GPT-2 changes.

LLukas22 avatar Jul 02 '23 13:07 LLukas22