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
This is because LLaMA models need to use LLamaTokenizer for loading, and using AutoTokenizer for llama may cause infinite recursion problems, which is related to the transformers version.
Can somebody please explain what this means in a little more detail? It's not clear to me why AutoTokenizer can cause issues, and what it means for it to have infinite recursion problems.
The text was updated successfully, but these errors were encountered:
Can somebody please explain what this means in a little more detail? It's not clear to me why AutoTokenizer can cause issues, and what it means for it to have infinite recursion problems.
The text was updated successfully, but these errors were encountered: