Downloads · 30 days
30
13% of all-time downloads
functiongemma-synthetic-270m-int8
Yagna1/functiongemma-synthetic-270m-int8
functiongemma-synthetic-270m-int8 is a machine learning model from Yagna1. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
FunctionGemma 270M fine-tuned on synthetic Mobile Actions dataset with INT4 quantization.
All-time downloads
229
Public
Parameters
268M
854 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors536 MB · 62%
At a glance
- Model type
- gemma3_text
- Access
- Public
- Created
- Dec 21, 2025
- Updated
- Dec 21, 2025
- SHA
- e04a3763
Model card
From the Hugging Face model README
functiongemma-synthetic-270m-int8
FunctionGemma 270M fine-tuned on synthetic Mobile Actions dataset with INT4 quantization.
Features
- ✅ Trained on 138 synthetic examples for LiteRT-LM compatibility
- ✅ INT8 quantized for optimal on-device performance
- ✅ Compatible with Google AI Edge Gallery app
- ✅ Supports: flashlight, contacts, email, maps, WiFi, calendar
Files
mobile/functiongemma_synthetic_int4.task- Ready-to-use .task bundle for Androidmobile/functiongemma_int8.tflite- INT8 quantized TFLite modelmobile/tokenizer.model- SentencePiece tokenizer
Usage
- Download
functiongemma_synthetic_int8.task - Import into Google AI Edge Gallery app
- Enable "Mobile Actions" support
- Test with prompts like "Turn on flashlight" or "Create contact John Doe"
Training Details
- Base:
unsloth/functiongemma-270m-it - Dataset: Custom synthetic Mobile Actions (138 examples)
- Format:
<start_function_call>call:function{params}<end_function_call> - Quantization: INT4 for edge deployment
- Type
- gemma3_text
- Created
- Dec 21, 2025
- Updated
- Dec 21, 2025