Set tokenizer "model_max_length" property to 8192

#39
by NohTow - opened

Somehow composer exported model_max_length tokenizer property to a very huge value instead of 8192.
This breaks the tokenizer.model_max_length call that some pipelines rely on.

As we corrected max_pos_embeddings, I suggest we also fix this for consistency, although this is not an hard limit.
See this issue for more information.

bwarner changed pull request status to merged

Sign up or log in to comment