CPU, TOKEN, env variables (#4)

Update app.py

Update src/submission/check_validity.py

removed last restart

simplified calls

made token a requirement

test

Update requirements.txt

fix

removed quantization to simplify

now with a functionning backend

update read

fixs

fix

updated leaderboard

Simplified leaderboard v0

adding pull back

simplified some parts of the code + updated requirements

Added check on tokenizer to prevent submissions which won't run

Update benchmark count and fix typo (`inetuning->finetuning`) (#395)

Update README.md

make faster thanks to no concurrency limit

fix order of request file vs request file list, to avoid resubmitting issues

cache

update for caching

simplify launcher + remove dataframe warning on boolean columns

add model architecture as column

Simplify About

Try concurrency management

up sdk

fix

Refactor 2 - added plotting back

fix value error in param size

Fix requirements for mistral models - to change once transformers gets updated.

Update app.py

req

fix

req

fix col width

refacto style + rate limit

Fix TruthfulQA NaN scores to 0

adding collections back

refacto part 1

add new evals to the leaderboard

add safefail for when we cannot download datasets, will simply restart the space

token for checking gated base models

simplify deps for pip

update requirements - to rollback once tokenizers deps is patched

adds script to create a request file for any model

Fix BibTex author ordering (#342)