Fix tiny-random-llava-next in VLM Pipeline #1660
Open
+9
−2
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
yatarkan
changed the title
Wovchena
reviewed
Jan 31, 2025
| @@ -19,6 +19,9 @@ ov::genai::VLMConfig::VLMConfig(const std::filesystem::path& json_path) { | |||
|
|
|||
| // Setting llava_next specific config params | |||
| read_json_param(parsed, "image_newline", image_newline); | |||
| if (parsed.contains("vision_config")) { | |||
| read_json_param(parsed.at("vision_config"), "patch_size", vision_config_patch_size); | |||
| } | |||
There was a problem hiding this comment.
ProcessorConfig already has patch_size field. Why doesn't ProcessorConfig check for vision_config in json?
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Outdated suggestions cannot be applied.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.
Ticket: CVS-160437
llava models store patch size parameter in
config.json, not inpreprocessor_config.jsonlike other vlm models. In GenAI we have default value for patch size (14) set in processor config.However, tiny versions of llava models have different patch size value (2).
In this PR the patch size value from vlm config is propagated to vision encoder.