onusai

I've seen a pretty big drop in aesthetic over the last few days. I narrowed it down to this commit [e59c66c0088422b27f64b401ef42c242f836725a](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/e59c66c0088422b27f64b401ef42c242f836725a) Example images before and after that commit: Prompt if...

After further testing, it appears that issue occurs when max_new_tokens is >= 1992. This issue does not occur when max_new_tokens is less than 1992, but it does duplicate the last...

Yep that seems to fix it. Is there a reason this isnt automatically calculated? something like `max_new_tokens = contex_size - len(prompt)`?

I converted a 30b 4bit ggml model https://huggingface.co/Pi3141/alpaca-30B-ggml/tree/main back to pytorch (hf), but the resulting file was 65gb instead of about 20gb Is it possible for 4bit ggml model to...

> I don't think pytorch or HF have the ability to run using 4bit (float). ah, your right there are 4bit models (https://huggingface.co/decapoda-research/llama-13b-hf-int4) in hf format i think, and you...

Fourthed. Just saw this mentioned in https://www.youtube.com/watch?v=r8wiBA3ZaQE hope it gets an a1111 extention

Im having the same issue, were you able to find any solutions?

hey, thanks a lot for sharing! I was able to run your code and it made the post request successfully, but for the life of me I can't get it...

@lybce This library seems to only work with HTTPS and not HTTP requests. You can try using my fork which fixed the endless "......" on HTTP requests (however HTTPS may...