shabie

Even if I give the local model path that resembles the model name identically (no path prefixes i.e. it is simply "xlm-roberta-base" for example) for the `embedding` argument, it is...

Tokenizer text recovery problem

1

I am trying to recover the text but it is not possible since the `token.original_spelling` for a token `: (` does not contain the original number of spaces. Here is...

[TODO] `create_features` does not detect rotated images leading to no extractions

6

## TODO I specially like this answer with `tesserocr` (faster than `pytesseract`): https://stackoverflow.com/a/69131832/7996306

Question about the choice of `contiguous` usage

1

Hi, Thanks a lot for putting this implementation out there. It helped me a lot! I was just curious why the `contiguous()` was called after `permute` or `transpose` but always...

I am planning to run SFT on real chatlogs so naturally I don't have the `prompt` field like in the Ultrachat dataset. AFAICT, this field is not used to perform...