Update README.md

Merge branch 'main' of https://huggingface.co/spaces/Tonic/Petite-LLM-3

small mods on the title and description

Update README.md

test commit powershell

Remove test_download.py

Remove test_app.py

testing singing

testing signing on hf

adds minor changes to the README

adds special tokens strip with fallback

adds debug

removes int4 subfolder

removes cache implementation static

removes subdirectory and chat template loading

removes flash attention from app

removes flash attention from requirements

makes modifications for zerogpu spaces

adds flash attention 2 to attention implementation or eager to cpu

adds flash attention 2 to attention implementation

adds subdirectory back

adds flash attention

tries to improve the generation paramaters

adds torchao

add french description

adds float32 defaults for quantized model tensors

fix local model typo

fix requests import error

attempts to add chat template

use the subfolder param

last trt to download the model at build time using the scripts

last try download int4 model from subfolder using hffilesystem

tries to download the model at build time using the scripts

tries to download the model at build time

initial commit