Overview

Fresh

13

Stale

0

Expired

0

Merged

7
Pull 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

Commit 40ed19f

Gather —

Logic —

Template —