SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Remove head mask in generative models (#35786)

Browse Source 
* just squash into one commit

* delete print
This commit is contained in:
Raushan Turganbay
2025-05-15 10:44:19 +02:00
committed by GitHub
parent 0173a99e73
commit 955e61b0da
47 changed files with 103 additions and 294 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/model_doc/hubert.md
View File

@@ -50,7 +50,7 @@ This model was contributed by [patrickvonplaten](https://huggingface.co/patrickv
- Hubert is a speech model that accepts a float array corresponding to the raw waveform of the speech signal.
- Hubert model was fine-tuned using connectionist temporal classification (CTC) so the model output has to be decoded
using [`Wav2Vec2CTCTokenizer`].
- The `head_mask` argument is ignored when using all attention implementation other than "eager". If you have a `head_mask` and want it to have effect, load the model with `XXXModel.from_pretrained(model_id, attn_implementation="eager")`
## Using Flash Attention 2