FEAT: [embedding] add support for jina-embeddings-v4 model #3814
Conversation
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
Add support for jina-embeddings-v4 model with 2048 dimensions and 32768 max tokens
Update transformers package version in both model_spec.json and model_spec_modelscope.json to ensure compatibility and security fixes
…ddings Add check for tokenizer attribute before assignment to prevent errors with models that don't have a tokenizer. Also extend CLIP model check to include Jina Embeddings v4 for proper base64 encoding handling.
Extend the token counting logic to support Jina Embeddings v4 models, similar to how CLIP models are handled
# Conflicts: # xinference/model/embedding/model_spec.json # xinference/model/embedding/model_spec_modelscope.json # xinference/model/embedding/sentence_transformers/core.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
add support for jina-embeddings-v4 model