Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.6k

Running on CPU Upgrade

Hi @legolasyiu ,

I've resubmitted your model, it should be fine now.
It seems like the problem was with the base_model field – you submitted the model with weight_type Original, but the base_model field is required for Delta or Adapter weight_type. Plus I changed the precision according to the model card

I close this issue, please, feel free to open a new one or ping me here if you encounter any issues with this exact model again

Thanks for fixing it

Hello team,

So sorry, it failing again.
It still fails,

https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/EpistemeAI/Fireball-Mistral-Nemo-Base-2407-v1-DPO2_eval_request_False_float16_Original.json

please let me know if it is on my end or others?

This is top priority to test, because it is most heavily finetuned and ORPO form of the Mistral Nemo base
https://huggingface.co/datasets/open-llm-leaderboard/requests/resolve/main/EpistemeAI/Fireball-12B_eval_request_False_float16_Original.json

Please assist. I really appreciate your assistance.

Thomas Yiu