[Model] Support multiple images for qwen-vl (#8247)

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Alex Brooks
2024-09-12 11:10:54 -06:00
committed by GitHub
parent e56bf27741
commit c6202daeed
4 changed files with 343 additions and 65 deletions

View File

@@ -254,7 +254,7 @@ Multimodal Language Models
-
* - :code:`QWenLMHeadModel`
- Qwen-VL
- Image\ :sup:`E`
- Image\ :sup:`E+`
- :code:`Qwen/Qwen-VL`, :code:`Qwen/Qwen-VL-Chat`, etc.
-
* - :code:`Qwen2VLForConditionalGeneration`