Maximum sequence length of flan-t5 base , large , xl ,xxl ?
#20
by
ali-issa
- opened
Hello, could someone provide more information regarding the maximum input and output size of the Flan-T5 models? While reading the paper, I noticed it was trained on 1024 input length and 256 output length, but I also saw conflicting information. Can someone please clarify? Thank you.
Hi
@ali-issa
I think that there should be no strong limit for the maximum length, please have a look at my comment here: https://huggingface.co/google/flan-t5-xxl/discussions/41#65117d0d33ddefa58fee136f and let me know if this makes sense