Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.7k

Running on CPU Upgrade

Hi! This selector is updated automatically depending on whether your model was accessible at last leaderboard compilation (there could have been a network error for ex) - it should fix itself automatically. If not, feel free to reopen tomorrow and I'll investigate more in depth.

Hi, it's still being shown as deleted.

It could be because I did delete this model previously (due to an error on my part). I have re-created the model on HF now.

If you recreated the model, I'll remove its results and you will have to resubmit, as we have no guarantee that's the same model and the commit hash will not match - could you point me to the results/requests files?

Here it is: https://huggingface.co./datasets/open-llm-leaderboard/details_l3utterfly__mistral-7b-v0.1-layla-v2

Sure, please let me know once you've reset it. I will re-submit.

@clefourrier hello, just bumping this. Are you able to reset the model for me please?

Hi! Yes of course, could you point me to the correct results and request files for your specific model?

@clefourrier here are the files:

Result file: https://huggingface.co./datasets/open-llm-leaderboard/results/tree/main/l3utterfly/mistral-7b-v0.1-layla-v2

Request file: https://huggingface.co./datasets/open-llm-leaderboard/requests/blob/main/l3utterfly/mistral-7b-v0.1-layla-v2_eval_request_False_float16_Original.json

Thanks for the links!

I removed one of the excess result files and it looks like it's working now

Can you check on your end?

Closing for inactivity, feel free to reopen if needed