feat(gallery): add WeMM embedding variants - #11775
Open
localai-org-maint-bot wants to merge 1 commit into
Open
Conversation
Tencent released three WeMM sizes with direct Sentence Transformers support. Add each safetensor repository so users can select the quality and resource tradeoff. Assisted-by: Codex:gpt-5
localai-org-maint-bot
force-pushed
the
cron/model-gallery-20260829-wemm
branch
from
August 29, 2026 12:09
a1154a1 to
3e525cd
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Add Tencent's WeMM Embedding 2B, 4B, and 9B safetensor repositories as
Transformers-backed gallery variants. The entries use Sentence Transformers,
which the current backend pins at the version required by the model cards.
LocalAI's embeddings API currently passes text to this backend. The entries
state that limit instead of advertising the models' upstream image and video
input support.
The backend downloads each Hugging Face repository snapshot directly, so these
entries do not declare gallery-managed files or artifact SHA-256 values. The
repositories resolved during validation at these revisions:
df8094e5caf29083d9cac28e96fad6cfbe3ee57fa28b25c5d18cf71ec46b115e06ea79ab00ee481959f673e3d53c4f71bb364adf344536dc1c2bc95eNotes for Reviewers
git diff --checkgo test ./core/gallery: 383 passed, 9 skipped, and 3 unrelatednetwork-dependent specs failed because this environment returned HTTP 403
for GitHub raw and gist URLs.
match the dimensions and Apache-2.0 terms in their model cards.
Signed commits