Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 12.1k

Running on CPU Upgrade

Hi @devingulliver !

Could you please provide me with the request file of the failed model?

https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/TRI-ML/mamba-7b-rw_eval_request_False_float16_Original.json

Hi @devingulliver !

I've rescheduled your model, according to logs, the model just got stuck on loading, but that was a problem on our end, it should be fine now

I'll close this issue now, please write here / reopen it in case of any problems with this model

It appears to have failed again (same request file). Is it for the same reason or a different reason?

Hi @devingulliver ,

The error for this model was connected with the last week backend update – we fixed it and I've resubmitted your model now, it should be fine

Somehow it's failed a third time. Is there a third issue with the backend or is something wrong with the model this time?

If there is an issue with the model, feel free to post the logs. The request file was linked earlier in the thread.

Hi @devingulliver ,

We are investigating the error on our side, we'll be back when we figure out it

It's been nearly a month, wanted to bump this once more to see if any progress could be shared

Closed without comment... were you able to resolve the issue?