Updates in VisionLanguageCollator and in coco_captions
#563
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
… into xrdaukar/gx-llava-gcp
OPE-353 Make sure HuggingFace vision models are supported with lema platform
List of model architectures supported by HuggingFace that we could support. Model that were tested with this script:
|
nikg4
changed the title
coco_captions dataset and in VisionLanguageCollatorVisionLanguageCollator and in coco_captions
OPE-354 [bug] Make sure llava, blip-2 (and others) work with simple vision language datasets
For now, they work with a dummy template |
taenin
reviewed
Sep 30, 2024
taenin
approved these changes
Sep 30, 2024
… into xrdaukar/gx-llava-gcp
oelachqar
approved these changes
Oct 1, 2024
| images = [] | ||
| text_inputs = [] | ||
| for item in batch: | ||
| for required_key in (_PIXEL_VALUES_KEY, _INPUT_IDS_KEY): |
There was a problem hiding this comment.
I'm not sure if these are necessarily always required -- a vision/language model can handle text only inputs (e.g. a follow-up to an answer) and image only inputs (e.g. captioning)
There was a problem hiding this comment.
Added TODO to reconsider this . Note that this PR just raises a better error message, it doesn't change validation condition
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
-- Update
coco_captionsto load image bytes fromexample["image"]["bytes"]if available (i.e., prefer to useIMAGE_BINARYoverIMAGE_PATHwhen possible)-- Raise more descriptive error messages if one of expected keys is missing in examples /items respectively
-- Add
minimal_multimodal_training.pyto VSCode launch config-- Misc minor clean-ups
Tested with local
coco_captionsdataset.Towards OPE-353
Fixes OPE-354