Spaces:

---

open-llm-leaderboard

/

open_llm_leaderboard

like 12.6k

Running on CPU Upgrade

Sorry again for bothering you, @clefourrier . Every time we try to submit this merged model :

https://huggingface.co./datasets/open-llm-leaderboard/requests/blob/main/Baptiste-HUVELLE-10/LeTriomphant2.2_ECE_iLAB_eval_request_False_bfloat16_Original.json

the leaderboard fails the evaluation. However, when we manually test the inference, it works fine without hallucinations.

Did we miss something?

Thank you very much in advance,

Hi @Marsouuu ,

Thank you for providing the link to the request file!

According to the log, it was a CUDA error. I'll look at the model evaluation manually and get back to you when I get the results

Hello and thank you very much for your time, @alozowski ,

I’m looking forward to hearing back from you soon so we can fix it if the issue is on our end. 😁

Thanks again!