[internvl] fix chat template (#37656)
* fix chat template * update * update conversion * rename `fake_image_token` in tests
This commit is contained in:
committed by
GitHub
parent
9ec8be56dd
commit
1e9087368c
@@ -257,6 +257,7 @@ InternVL models can also handle video inputs. Here is an example of how to perfo
|
||||
... add_generation_prompt=True,
|
||||
... tokenize=True,
|
||||
... return_dict=True,
|
||||
... num_frames=8,
|
||||
>>> ).to(model.device, dtype=torch.float16)
|
||||
|
||||
>>> output = model.generate(**inputs, max_new_tokens=25)
|
||||
|
||||
Reference in New Issue
Block a user