Skip to content

make search encoder compatible with encoder#3404

Merged
Samoed merged 1 commit into
v2.0.0from
make_search_encoder_compatible
Oct 17, 2025
Merged

make search encoder compatible with encoder#3404
Samoed merged 1 commit into
v2.0.0from
make_search_encoder_compatible

Conversation

@Samoed

@Samoed Samoed commented Oct 17, 2025

Copy link
Copy Markdown
Member

Previously, if execute this

import mteb

model = mteb.get_model("baseline/random-encoder-baseline")
task = model.get_task("SomeSTS")
mteb.evaluate(model, task, cache=None)

would produce error. I think it's better to add this option if user wrap encoder model with search encoder to be able to execute all tasks

@KennethEnevoldsen

Copy link
Copy Markdown
Contributor

I am not sure I get the error here, did you mean to write random-cross-encoder?

@KennethEnevoldsen KennethEnevoldsen left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Assuming you did then I think this is all good

@Samoed

Samoed commented Oct 17, 2025

Copy link
Copy Markdown
Member Author

I forgot to add SearchEncoderWrapper to the example like in test

import mteb
from mteb.models.sentence_transformer_wrapper import SentenceTransformerEncoderWrapper

model = SentenceTransformerEncoderWrapper(mteb.get_model("baseline/random-encoder-baseline"))
task = model.get_task("SomeSTS")
mteb.evaluate(model, task, cache=None)

@KennethEnevoldsen

Copy link
Copy Markdown
Contributor

makes sense - all good

@Samoed Samoed merged commit 25176c1 into v2.0.0 Oct 17, 2025
11 checks passed
@Samoed Samoed deleted the make_search_encoder_compatible branch October 17, 2025 14:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants