Downloads · 30 days
0
functiongemma-pocketassist-v5-task
2796gauravc/functiongemma-pocketassist-v5-task
functiongemma-pocketassist-v5-task is a machine learning model from 2796gauravc. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for litert. The card lists the license as gemma.
This is the MediaPipe-ready .task file for deployment in Android apps. The merged model is at 2796gauravc/functiongemma-pocketassist-v5.
Access
Public
Updated Feb 18, 2026
Repo size
284 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.task284 MB · 100%
At a glance
- Library
- litert
- License
- gemma
- Access
- Public
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026
- SHA
- 8d4b4aca
Base models
Model card
From the Hugging Face model README
FunctionGemma PocketAssist v5 — Android .task File
This is the MediaPipe-ready .task file for deployment in Android apps.
The merged model is at 2796gauravc/functiongemma-pocketassist-v5.
How to use on Android
Download the .task file and use with MediaPipe LLM Inference API:
// build.gradle.kts
implementation("com.google.mediapipe:tasks-genai:0.10.22")
// Inference
val options = LlmInference.LlmInferenceOptions.builder()
.setModelPath("/path/to/pocketassist_v5_q8_ekv1024.task")
.setMaxTokens(1024)
.setTopK(64)
.setTopP(0.95f)
.setTemperature(1.0f)
.setPreferredBackend(LlmInference.Backend.GPU) // or CPU
.build()
val llm = LlmInference.createFromOptions(context, options)
Functions
This model handles: search, get_password, save_password, save_note,
get_notes, get_digest, status, help
File Info
- Format:
.task(MediaPipe / LiteRT) - Quantization:
dynamic_int8 - KV cache max len: 1024
- Size: ~290 MB
- Library
- litert
- License
- gemma
- Languages
- en, hi
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026