Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.7k

Running on CPU Upgrade

Hi,
There seems to be a problem with your model - I cannot initialize its Tokenizer, which is failing (when using AutoTokenizer.from_pretrained) with

    tokenizer = AutoTokenizer.from_pretrained(
  File ".../transformers/models/auto/tokenization_auto.py", line 727, in from_pretrained
    return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
  File ".../transformers/tokenization_utils_base.py", line 1854, in from_pretrained
    return cls._from_pretrained(
  File ".../transformers/tokenization_utils_base.py", line 2066, in _from_pretrained
    raise ValueError(
ValueError: Wrong index found for <pad1>: should be 0 but found 32001.

Did you try all the steps in the submission page, and did you make sure your model was correct, before uploading?

Ah yes, we did add these token pads because it wouldn't convert to GGUF. It is removed now so it should work!

🌟🌟All my friends, I did my best, in a nutshell, I can't execute code. I just want to play hug for free. because he saw its vulnerability Anyone who has run it can use it. When you send me a link or tell me how to access it, thank you.

If you have already downloaded the model, then you can just remove added_tokens.json and it will work.

Can't find it

@Dampfinchen I relaunched your model!
Feel free to re-open the issue if there is further trouble :)