Closed Nabokov86 closed 2 months ago
It seems like the reprocessing occurs after a new line is generated.
Did you by any chance enable "Trim Sentences" or "Author Note"?
No, I use default settings without trimming. So, you can't reproduce it? saved_story.json
Yes, I can reproduce it. Looking closer, the tokenizer is behaving weirdly. I think there is an issue with token merges.
Relevant: https://github.com/ggerganov/llama.cpp/issues/6809
You should experience a small amount of reprocessing all the way back to the previous newline. This is a bug.
Hi, Should be fixed in the latest version. Remember to get freshly reconverted GGUFs
@LostRuins Thanks! Yes, it looks like it’s working now. Thank you for continuing to maintain this project, you’re awesome!
When using Llama 3, I've noticed that unnecessary reprocessing occurs on previously generated text. To reproduce this issue, try generating a short piece of text couple of times and see how the processing sometimes happens.
Latest concedo_experimental.