Bhavya Patel

Results 9 comments of Bhavya Patel

feat(upload): add support on upload to topic

@XMLHexagram this works great thank you for this.

Not using the GPU

> Comment out bitsandbytes and bitsandbytes-windows > > transformers=4.35.0 sentence-transformers==2.2.2 datasets==2.14.6 qdrant_client psycopg2 pgvector > > bitsandbytes @ https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.40.1.post1-py3-none-win_amd64.whl auto-gptq @ https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.3.0/auto_gptq-0.3.0+cu118-cp310-cp310-win_amd64.whl torch @ https://download.pytorch.org/whl/cu117/torch-2.0.1%2Bcu117-cp310-cp310-win_amd64.whl torchvision @ https://download.pytorch.org/whl/cu117/torchvision-0.15.2%2Bcu117-cp310-cp310-win_amd64.whl torchaudio @...

auto-gptq and auto awq is breaking in requiremetns.txt

you should make a pr about this.

Mistral not supported

if you are using cuda use GPTQ model or you are on mac use GGUF https://youtu.be/ASpageg8nPw?t=74

very slow GPU compared with CPU

I don't know if anyone has tried it, but if you use GPTQ, there was a warning that says to remove the temperature. So I tried removing it, and everything...

Support passing/overriding arguments to `requests` calls

@1vn are you taking about api calls?

Better markdown rendering needed

@Dhravya I am confused because I used the chat, and everything seems to be working fine.

Not able to add paths to latest Docker Desktop File Sharing on MacOS Monterey

same issue

Fix unchecked types warnings.

@cbosdo I don’t think this is closed. There are still 707 warnings left, and I might open some smaller PRs to update the code