[Model] VLM2Vec, the first multimodal embedding model in vLLM (#9303)

Browse Source

...

This commit is contained in:

Cyrus Leung

2024-10-16 14:31:00 +08:00

committed by GitHub

parent 7e7eae338d

commit 7abba39ee6

16 changed files with 465 additions and 261 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

tests/models/embedding/vision_language/__init__.py