Pass img_min_params and img_max_params to ctx_clip_params#2133
Merged
LostRuins merged 14 commits intoLostRuins:concedo_experimentalfrom Apr 16, 2026
Merged
Pass img_min_params and img_max_params to ctx_clip_params#2133LostRuins merged 14 commits intoLostRuins:concedo_experimentalfrom
LostRuins merged 14 commits intoLostRuins:concedo_experimentalfrom
Conversation
Merge upstream
Merge upstream
Merge upstream
Merge upstream
Merge upstream
Merge upstream
Merge from upstream
Merge from upstream
Merge upstream
Merge upstream
Merge upstream
These values determine the minimum and maximum size (in tokens) of vision embeddings. The default value of -1 uses a model-dependent default size, for example for Gemma 4 the default is a 280 token embedding. For higher quality results (at the cost of using more memory and slower speed) you can increase the size of the embedding to 1120 tokens.
Collaborator
|
Personally in favor of this, I know lostruins was planning a more universal option down the line which this shouldn't rule out. But I think these particular vars will be helpful since they will be mentioned in llamacpp guides and are generally highly desired by the community. |
Owner
|
looks good |
Owner
|
I noticed you added the GUI variable but didn't actually add the GUI element. I'm thinking we can probably put in on the same row as Visionmaxres 
I will add it after merging, probably |
Author
Ah, my bad, I always load models from the command line so I forgot this UI existed. |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
These values determine the minimum and maximum size (in tokens) of vision embeddings. The default value of -1 uses a model-dependent default size, for example for Gemma 4 the default is a 280 token embedding. For higher quality results (at the cost of using more memory and slower speed) you can increase the size of the embedding to 1120 tokens.