Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support textonly inference for LLaVA-OneVision. #215

Merged
merged 1 commit into from
Aug 28, 2024
Merged

Support textonly inference for LLaVA-OneVision. #215

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions lmms_eval/models/llava_onevision.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -453,6 +453,10 @@ def _collate(x):
if len(visual) > 1 or "image_aspect_ratio" not in self._config.__dict__: # for multi image case, we treat per image aspect ratio as "pad" by default.
self._config.image_aspect_ratio = getattr(gen_kwargs, "image_aspect_ratio", "pad")
eval_logger.info(f"Setting image aspect ratio: {self._config.image_aspect_ratio}")

if len(visual) == 0: # For textonly task
image_tensor = None
task_type = 'textonly'

if type(visual[0]) == PIL.Image.Image and "task_type" not in metadata and "sample_frames" not in metadata: # For image task
image_tensor = process_images(visual, self._image_processor, self._config)
Expand Down
Loading