Shane

When using `api-stream-example.py` I get this error printed to log: ``` File "/home/shane/Documents/LLM-UI/modules/text_generation.py", line 172, in generate_reply found_stop_string = next((s for s in stopping_strings + evaluated_stopping_strings if s in original_reply),...

I probably should've noted how I got it to work properly, you can put it in this kind of format: `'"token","\n","###","\\n###","Alice:"'` If you're familiar with developer tools, you can also...

Excellent work! I'm consistently getting a substantial boost in inference speed after the initial inference. ``` Output generated in 4.49 seconds (15.60 tokens/s, 70 tokens, context 33, seed 871616523) Output...

Just thought I'd jot this down here since it's a jab at making a Steam Controller OSD for Linux. https://github.com/FliiFe/schud It's not feature complete and it's powered by Electron, but...

I can recreate this issue, as well as #3503, consistently by simply filling up my GPU's VRAM before launching CS2. It makes smoke completely invisible from most angles. This also...

Here's the quickstart guide: https://github.com/matpow2/cuwo/wiki/Quickstart You can also build from source: https://github.com/matpow2/cuwo/wiki/WindowsSource I'm not very experienced with Python, but I think you get errors like that if you try to...

This is slightly different from #11, but it's the same concept, so I understand if it's something you're not interested in implementing.

Use the latest version. #21