[docs] last hidden state vs hidden_states[-1] #26142
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Intuitively one may think that
output.hidden_states[-1]
(returned whenoutput_hidden_states
is set toTrue
) should match theoutput.last_hidden_states
exactly. However, this is not always the case. Models like CLIP, ClipSeg, GroupVit, OWLViT, and X-CLIP applylayernorm
before returning thelast_hidden_states
. Some other models applypost_layernorm
ornorm
.This PR adds a small note in the docs to address possible confusion.