[Model] support input embeddings for qwen2vl (#8856)
This commit is contained in:
@@ -281,7 +281,7 @@ Multimodal Language Models
|
||||
-
|
||||
* - :code:`Qwen2VLForConditionalGeneration`
|
||||
- Qwen2-VL
|
||||
- Image\ :sup:`+` / Video\ :sup:`+`
|
||||
- Image\ :sup:`E+` / Video\ :sup:`+`
|
||||
- :code:`Qwen/Qwen2-VL-2B-Instruct`, :code:`Qwen/Qwen2-VL-7B-Instruct`, :code:`Qwen/Qwen2-VL-72B-Instruct`, etc.
|
||||
-
|
||||
* - :code:`UltravoxModel`
|
||||
|
||||
Reference in New Issue
Block a user