Add flash attention to llama-cpp init

added minor fix for running model(2)

added minor fix for running model(1)

added minor fix for running model

added fix number2 for running model

added prebuilt wheel for llama_cpp

fix for llama_cpp function inside

fixes

Added preload_from_hub for my models weights in readme, addition of packages for smoothly running the models in requirements.txt and finally updated the app.py to run llm in ui

Fix Space dependency conflict

added local development how to

Updated .gitignore and added requirements.txt

Adding .gitignore

initial setup of the space and minor space configs

initial commit