Generate: handle text conditioning with multimodal encoder-decoder models (#22748)
This commit is contained in:
@@ -69,4 +69,4 @@ The original code can be found [here](https://github.com/google-research/pix2str
|
||||
## Pix2StructForConditionalGeneration
|
||||
|
||||
[[autodoc]] Pix2StructForConditionalGeneration
|
||||
- forward
|
||||
- forward
|
||||
|
||||
Reference in New Issue
Block a user