[Model][VLM] Support multi-images inputs for InternVL2 models (#8201)
This commit is contained in:
@@ -214,7 +214,7 @@ Multimodal Language Models
|
||||
-
|
||||
* - :code:`InternVLChatModel`
|
||||
- InternVL2
|
||||
- Image\ :sup:`E`
|
||||
- Image\ :sup:`E+`
|
||||
- :code:`OpenGVLab/InternVL2-4B`, :code:`OpenGVLab/InternVL2-8B`, etc.
|
||||
-
|
||||
* - :code:`LlavaForConditionalGeneration`
|
||||
|
||||
Reference in New Issue
Block a user