Fix/local models#30
Open
moro-no-kimi wants to merge 6 commits into
Open
Conversation
shubham0204
requested changes
Jan 3, 2026
| # thereby reducing the size of the R class for that library | ||
| android.nonTransitiveRClass=true No newline at end of file | ||
| android.nonTransitiveRClass=true | ||
| # Use Java 21 |
Owner
There was a problem hiding this comment.
Any specific reason we are upgrading to Java 21? Also, to upgrade the JDK used to compile the app's source code, we modify the below options in app/build.gradle.kts:
compileOptions {
sourceCompatibility = JavaVersion.VERSION_17
targetCompatibility = JavaVersion.VERSION_17
}
kotlinOptions {
jvmTarget = "17"
}
Owner
There was a problem hiding this comment.
As no new types of files have been included in the project, I would prefer sticking to the existing .gitignore. If there comes a new file that has to be excluded from VCS, we simply add a new exclusion to .gitignore.
| name = "Qwen2.5 3B Instruct Q8", | ||
| description = "A Qwen family model series", | ||
| downloadUrl = "https://huggingface.co/litert-community/Qwen2.5-3B-Instruct/resolve/main/Qwen2.5-3B-Instruct_multi-prefill-seq_q8_ekv1280.task", | ||
| name = "Qwen3 4B Thinking Q4", |
Owner
There was a problem hiding this comment.
Is it possible to keep Qwen2.5 3B Instruct Q8 and add Qwen3 4B Thinking Q4? You may add the link to an un-guarded Qwen 2.5 3B LiteRT model file.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I noticed that the Qwen and Phi models weren't working because the app was forcing use of a Gemini API key. This allows for those models to be used without entering a key. Also added DeepSeek R1 and Qwen3-4b