niansa/tuxifan
niansa/tuxifan
Seeing this as a "no".
Closing, because new editor doesn't have icons.
> Yes, the weights are fp16. You can convert and run 4-bit using https://github.com/ggerganov/llama.cpp. I think 30B with full precision might be at least on par to 65B 4-bit in...
There's the OpenAPI integrated into the chat client now.
Should be solved by now
Stale, please open a new issue if this is still relevant.
Stale, please open a new issue if this still occurs
Stale, please open a new issue if this still occurs
This model was suggested: https://github.com/ymcui/Chinese-LLaMA-Alpaca