How to increase max token output ?

#40
by Truc95 - opened

Hello,

While using Florence-2 for OCR tasks, the maximum token output is easily reached - around 400 words.
Is it possible to increase the maximum output ? I have tried to change both max_new_tokens which has no effect.
I have tried "max_position_embeddings" but it seems that changing this parameter would require a retraining of the model.

Is there any way to increase the output tokens ?

It's not possible, the max token trained are limited to 1024

Thank you for the explanation, @lucasjin . I noticed the behavior where I sometimes received sentences with a length of 1265 characters. It now makes sense that this is due to the tokenization process. I had set max_new_tokens to 4098 (as I process OCR for long documents), but the sentences always seemed to cut off at the same place. This limitation aligns with the model's tokenization and maximum token handling.

Sign up or log in to comment