Handle VLM weight name prefixes in QuantizedModel loader#1996
Draft
uday610 wants to merge 1 commit intomicrosoft:mainfrom
Draft
Handle VLM weight name prefixes in QuantizedModel loader#1996uday610 wants to merge 1 commit intomicrosoft:mainfrom
uday610 wants to merge 1 commit intomicrosoft:mainfrom
Conversation
This change makes the quantized model weight loader work with VLM checkpoints where weight names include extra prefixes like `model.language_model.*` and vision tower weights like `model.visual.*`. - Skip weights under `model.visual.*` - Normalize `model.language_model.* → model.*` before existing pattern matching and layer parsing No functional change for pure LLM checkpoints.
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This change makes the quantized model weight loader work with VLM checkpoints where weight names include extra prefixes like
model.language_model.*and vision tower weights likemodel.visual.*.Skip weights under
model.visual.*Normalize
model.language_model.* → model.*before existing pattern matching and layer parsingNo functional change for pure LLM checkpoints.