handle streaming properly

fix

Stream LLM responses

fix

fix

fix

fix

fixes

fix

fix

fix

fix

port to gradio

fix

add clear history functionality

use 4 bit quantized models for faster inference

fix

fix

fix

Add model config sliders

Update README.md

Update README.md

fix

fix

Update _model.py

remove unnecessary requirements

bug fix

bug fix

fix

use llama.cpp

increase cache limit -> fewer recompilations by pytorch

update sdk_version

change sdk to streamlit

update README

Update README.md

Update README.md

fix

remove torch.compile

fix

fix

Merge branch 'main' of https://huggingface.co/spaces/aadya1761/GemmaDemoSt2

fix

Update requirements.txt

add req

changes

shift port to 8501

add server port 7860

add README

initial commit