Fix space by upgrading to latest `gradio` (#41)

Update default model to google-bert/bert-base-cased (#40)

fix typo

unpin acc req and update huggingface hub

fix access token

Only do model name translation for Llama-2 and CodeLlama (#37)

Try again

Pin accelerate

Fully rm results page

Update README.md

Merge branch 'main' of https://huggingface.co/spaces/hf-accelerate/model-memory-usage

Fixup visible + spammign

Update requirements.txt (#29)

Some more fixes

Update src/model_utils.py

peek -> peak (#24)

Right column name

Update for more explained training methods

Fix Space URL in Discussion Report (#23)

Use huggingface_hub==0.19.4 (#22)

Update src/app.py

New version

Update src/app.py

Try removing global var

Check for if discussion is disabled

Ensure you can't spam/double click

Refactor code (#11)

Allow URLs

better err for detr

else

Translate llama

Togethercompute

Add link to the access token (#5)

Fix issue with PR

Support bfloat16 (#3)

Update requirements.txt

Update requirements.txt

Update requirements.txt

Try with no build isolation

Create pre-requirements.txt

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update requirements.txt

Default bert-base-cased

Nit

Clearer message

float16

User token