Apollo199999999/zenith-llm-zhi-xuan

Update app.py

remove gpu

Update app.py

Add GPU support

Update app.py

Update app.py

add the type component in chatbot

Update app.py

Update app.py

leave placeholder first

change to tuple?

add avatar images

just modify textbox first

whoops syntax error

Update app.py

UI tweaks

Upload avatar images

change to llama base model

Update app.py

try mistral 7b

Update app.py

Update app.py

qwen 2.5 0.5b?

try tinyllama

i think i need to try changing base models

Update app.py

Update app.py

Update app.py

try some optimizations

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update requirements.txt

try use ollama

Update app.py

Update requirements.txt

GO BACK GO BACK

Update app.py

Update app.py

Update requirements.txt

try use vllm

try lower param model

try using base model first to check inference speed

dont use quantization nvm

try quantization