Predicting with PrettyBigModel `InvalidArgumentError: indices[0,0] = 1024 is not in [0, 1024)` about gpt2 HOT 5 CLOSED

This is a known bug. I haven't yet had the time to track down the exact cause. Three things you can try are setting the precision to float32, use a GPU instead of a CPU or change the "train_batch_size" and "predict_batch_size" parameters to 1. Some of these seem to fix it sometimes. I will fix this bug when I have the time to actually track down its source.

The bug also shouldn't happen if you predict with a single word.

from gpt2.

I encountered the same issue working on gpt-2-simple: minimaxir/gpt-2-simple#38

The solution was to subtract the length of the prefix tokens from the maximum length to prevent OOB.

from gpt2.

Maybe you can try tensorflow==1.13.0
as:
https://medium.com/@NPCollapse/replicating-gpt2-1-5b-86454a7f26af
hints:

Tensorflow (I was using version 1.13) is…not perfect.

from gpt2.

I got the same error, here is the full output and traceback I got: https://hasteb.in/wilupika.py

Maybe it will be helpful :)

from gpt2.

Thanks minimaxir! I've implemented that fix now and think everything should be working. If this problem crops up again for anyone, feel free to reopen this issue.

from gpt2.