Browsing Tag
Gemma
14 posts
Serve and Inference Gemma 4 on TPU
Introduction Earlier in April 2026, Google released Gemma 4, the latest family of open multimodal models, and momentum…
Gemma 4 as an LLM-as-a-Judge: Batch Responsible AI Evaluation on Cloud TPU v5e
TPU Batch Eval Pipeline for RAI-Checklist-CLI Calibrated Trust (the governance framework I’ve been building for agentic AI systems)…
Fine-Tuning Gemma 3 on TPU for Medical Q&A with Keras and JAX
I wanted to build a medical Q&A fine-tuning project that stayed genuinely TPU-native on Kaggle. This project uses…
Pipeline to create .task files for MediaPipe LLM Inference API
Pipeline to create .task files for MediaPipe LLM Inference API Written by Georgios Soloupis, AI and Android GDE. MediaPipe logo…
On-Device Function Calling with FunctionGemma
A Practical Guide to preparing and using Google’s smallest function calling model for Mobile and Web Developers Why…
Fine-Tuning Gemma with LoRA for On-Device Inference (Android, iOS, Web) with Separate LoRA Weights
Prologue Lately, I’ve become deeply interested in working with Edge AI. What fascinates me most is the potential…
PaliGemma on Android using Hugging Face API
Introduction At Google I/O 2024, Google unveiled a new addition to the Gemma family: PaliGemma, alongside several new…
Next-Gen RAG with Couchbase and Gemma 3: Building a Scalable AI-Powered Knowledge System
Introduction Retrieval-Augmented Generation (RAG) is revolutionizing AI applications by combining the power of retrieval-based search with generative models.…
PaliGemma Fine-tuning for Multimodal Classification
Creating more dependable and accurate machine learning models nowadays depends on combining data from several modalities, including text…
Online Knowledge Distillation: Advancing LLMs like Gemma 2 through Dynamic Learning
Large Language Models (LLMs) are rapidly evolving, with recent developments in models like Gemini and Gemma 2 bringing…
