Merged
Conversation
Signed-off-by: pengdurice <pengduhit@gmail.com>
Collaborator
| Thanks for the contribution! |
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
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add support for Qwen3-VL dense models, locally tested with Qwen3-VL-4B-Instruct, Qwen3-VL-8B-Thinking, Qwen3-VL-32B-Instruct.
Note
Medium Risk
Adds a new architecture JSON that affects how MergeKit identifies and maps Qwen3-VL dense model weights; incorrect keys/weight names could break loading or merges for these models. Change is isolated to data/config with no broader code logic modifications.
Overview
Adds a new modular architecture definition
qwen3_vl_dense.jsonto support dense Qwen3-VL models (Qwen3VLForConditionalGeneration).The definition introduces module weight mappings for the text decoder (dense MLP projections), the multi-modal projector (deepstack merger layers), and the vision tower blocks, along with updated config keys for
vision_config.depthandtext_config.vocab_sizeand required tagalong files.Written by Cursor Bugbot for commit f1f257f. This will update automatically on new commits. Configure here.