SparkNLP - 1123 Introducing InternVL #14578
Merged
Conversation
This file contains hidden or 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
Signed-off-by: Prabod Rathnayaka <prabod@rathnayaka.me>
DevinTDHa approved these changes May 23, 2025
Member
DevinTDHa left a comment
DevinTDHa left a comment There was a problem hiding this comment.
Some minor changes needed for the python part (configProtoBytes not used), which I'll remove during the merge, but other than that looks good to me!
| | ||
| outputAnnotatorType = AnnotatorType.DOCUMENT | ||
| | ||
| configProtoBytes = Param(Params._dummy(), |
| image_assembler = ImageAssembler().setInputCol("image").setOutputCol("image_assembler") | ||
| | ||
| imageClassifier = (InternVLForMultiModal \ | ||
| .loadSavedModel("/mnt/research/Projects/ModelZoo/internVL/models/int4/OpenGVLab/InternVL2-1B", self.spark) \ |
Member
There was a problem hiding this comment.
We should change this to pretrained() for the master branch
DevinTDHa added a commit that referenced this pull request May 28, 2025
* add intervl scala api * add internvl python api * internvl docs * update scala and python api for tests Signed-off-by: Prabod Rathnayaka <prabod@rathnayaka.me> * add notebook * InternVL: minor python adjustments --------- Signed-off-by: Prabod Rathnayaka <prabod@rathnayaka.me> Co-authored-by: Devin Ha <devin@trungducha.de>
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 Outdated suggestions cannot be applied.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.
Description
This pull request introduces support for the
InternVLForMultiModalmodel, a multimodal large language model designed for visual question answering. The changes include the addition of a new annotator, utility functions for image preprocessing, and test cases to validate functionality. This annotator can load InternVL 2, 2.5 and 3 family of models.Motivation and Context
How Has This Been Tested?
Screenshots (if appropriate):
Types of changes
Checklist: