current queue

Current evals

Upload folder using huggingface_hub (#3)

Merge branch 'main' of https://huggingface.co/spaces/Yeyito/llm_contamination_detector

Current eval and queue

current evals

Current queue

Unloading models + current evals

merge changes

Current evals and queue

reverted again

nvm text doesn't work like that

winogrande warnings

fixed issue with bagel model

new evals

new evals

Current queue

current evals

current evals

Error with Yi fix

current eval and queue

current queue

current eval

Added How does this work? To the about

Fixing lack of ref_model

reverted tokenizer fix, will be solved manually upon testing, current evals

current eval

forgot to remove an imort

Load tokenizer from parent model & app.py fixes

Mistral cache

ref model and tuple error fix

Current queue

Reference model full implementation

Reference model selection box

mistralai default ref, queue hotfix

small python fix

gsm8k fix, queue, ref_model column

current evals num_z=50

re0commented evaluations

new evals num_z=50

fixed tuple oversight

current evals with num_z=50

current eval

We use the same code in here to test the models outside of this space

Current evaluations (num_z = 50)

num_z=50 saves and current evaluations

No more restarting space, fixed format

num_z = 50 for all

It was and not or 🙂

More aggressive OOM prevention, num_z reduced to 50 for gsm8k and mmlu