cannot request eval for llm leaderboard because of tokenizer?

#8
by gestalt73 - opened

I'd love to see how this fine tuned model stack up but the custom tokenizer is getting in the way. :-(

Model "ehartford/dolphin-2_2-yi-34b" uses YiTokenizer, which is not in a transformers release, therefore not supported at the moment.

Sign up or log in to comment