Initial commit: HeliBoard + Gemma 4 on-device AI correction
Integrates LiteRT-LM (Google) with Gemma 4 E2B-it for on-device spell/grammar correction in HeliBoard. After sentence-ending punctuation, the model checks the sentence and shows a correction in the suggestion strip. Tapping it replaces the original text — fully offline, no cloud API. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
+26
@@ -0,0 +1,26 @@
|
||||
*.iml
|
||||
.gradle/
|
||||
local.properties
|
||||
.idea/
|
||||
.DS_Store
|
||||
build/
|
||||
/captures/
|
||||
.externalNativeBuild/
|
||||
.cxx/
|
||||
*.jks
|
||||
*.keystore
|
||||
|
||||
# Gradle wrapper jar (commit only the .properties file)
|
||||
gradle/wrapper/gradle-wrapper.jar
|
||||
gradlew
|
||||
gradlew.bat
|
||||
|
||||
# HeliBoard sources are cloned by setup_heliboard.sh — not tracked here
|
||||
heliboard/
|
||||
|
||||
# AI model files are too large for git — push to device via ADB
|
||||
*.litertlm
|
||||
*.task
|
||||
|
||||
# Claude internal files
|
||||
.claude/
|
||||
Reference in New Issue
Block a user