Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.4k

Running on CPU Upgrade

I have updated the license to precisely match this model as it is directly analogous to mine, which was processed correctly and shows on the leaderboard (currently number 1): https://huggingface.co/MaziyarPanahi/calme-2.1-qwen2-72b

Hi @dfurman ,

Could you please send me the requests file for your model as it is written in our documentation here? Thus I will be able to help you to check the problem

Hi @alozowski ,

I am seeing the model back in the "running evaluation queue". The file when it completes: https://huggingface.co/datasets/open-llm-leaderboard/dfurman__Qwen2-72B-Orpo-v0.1-details.

I think the problem is fixed?

Here is the requests file for your model (link). Yes, according to it, the model is running and will soon appear on the Leaderboard

Since the problem is solved, I close this issue. Please, ping me here in case of any problem with this model or start a new discussion

Folllowing up on this @alozowski , status has changed to "FAILED". Any assistance as to why? Thanks!

https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/dfurman/Qwen2-72B-Orpo-v0.1_eval_request_False_bfloat16_Original.json

Hi! There was a problem when loading your model (on part 6/31) - I passed it to pending again.

Thanks @clefourrier !!