vasanthrpjan1-boop

Hi @kibergus, I investigated this issue and found the problematic code in `tokenization_utils_base.py` (lines 3525-3562). The root cause is that `parse_response()` converts tokens to text via `decode()` before parsing, losing...

Hi @aselimc, I'd like to help with this feature! I'm a contributor who recently submitted fixes for Conditional DETR (#42679) and Flash Attention 4 detection (#42405). I can implement the...