DenOfEquity cc378589a4 (T5) pad chunks to length of largest chunk (#1990) ...

When the prompt is chunked using the BREAK keyword, chunks will be padded to the minimum size of 256 tokens - but chunks can be longer. torch.stack then fails if all chunks are not the same size, so find the largest and pad all to match.
#1988 (doesn't quite ID the real issue, prompts longer than 255 tokens work fine)

2024-10-07 11:37:06 +01:00

..

classic_engine.py

make results more consistent to A1111

2024-08-08 01:53:03 -07:00

emphasis.py

Create emphasis.py

2024-08-04 12:21:57 -07:00

parsing.py

Implement A1111 Text Processing from Scratch

2024-08-04 12:43:31 -07:00

t5_engine.py

(T5) pad chunks to length of largest chunk (#1990)

2024-10-07 11:37:06 +01:00

textual_inversion.py

Text Processing Engine is Finished

2024-08-04 18:42:51 -07:00