Overview
Fresh
13Stale
0Expired
0Merged
7Pull Requests
Add DeepSeek-V4.1-Flash
Remove now useless keys_to_ignore_at_inference in all configs
Simplify cache handling in generate
Set _skip_keys_device_placement directly inside PreTrainedModel
Restore SentencePiece nmt_nfkc normalization in DebertaV2Tokenizer
Load more