You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Something is WRONG. The decoding of PreTrainedTokenizerFast (which LLaMA-3 are using) decode weird output once you add that token to the vocab using .add_tokens(word) function.
I use standard tokenizer from LLaMA-3 repo and add only ONE word to the origin tokenizer and...:
Something is WRONG. The decoding of PreTrainedTokenizerFast (which LLaMA-3 are using) decode weird output once you add that token to the vocab using .add_tokens(word) function.
I use standard tokenizer from LLaMA-3 repo and add only ONE word to the origin tokenizer and...:
Any idea why ? LLaMA-2 LlamaTokenizer works just fine.
Thanks in advanced.
Steve
The text was updated successfully, but these errors were encountered: