Generate: handle text conditioning with multimodal encoder-decoder models #22748
Add model to doc tests
70fedc1a
Remove generate and replace by prepare_inputs_for_generation
cd6c4eb1
More fixes
837eb9b1
Remove print statements
db32984d
Update integration tests
8904491c
Remove model from auto mapping
08c1fa79
Use auto processor
ae729bf5
Remove is_encoder_decoder
1c02ffd7
Remove notebook link
ddcb6914
tmp commit
a7aef082
nits
6eb1f2a6
add test
b9de6faa
types
9bee8686
fix tests
c8f494c2
sgugger
approved these changes
on 2023-04-13
gante
merged
9dfd6a4b
into main 3 years ago
gante
deleted the img2text_decoder_input_ids branch 3 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub