A Gemini and Gemma tokenizer in Java
It’s always interesting to know how the sausage is made , don’t you think? That’s why, a while ago, I looked at embedding model tokenization , and I implemented a little visualization to see the…
Read the full articleYou might also wanna read
The Prompt API: Running Gemini Nano in the Browser for Natural Language Processing
Discover the infinite possibilities of the Prompt API.
developer.chrome.com·2mo ago
Gemini Embedding Model Enhances AI Applications Through Context Engineering
The Gemini Embedding model enhances AI applications, particularly through context engineering, which is being successfully adopted by variou
developers.googleblog.com·11mo ago
Google Releases Gemini 3.1 Pro AI Model with 2M Token Context for Complex Tasks
3.1 Pro is designed for tasks where a simple answer isn’t enough.
blog.google·4mo agoAPI that auto-routes to the cheapest AI provider (OpenAI/Anthropic/Gemini)
Article URL: Comments URL: Points: 10 # Comments: 4
How Multi-Token Prediction drafters accelerate Gemma 4 inference by up to 3x
An overview of how Multi-Token Prediction (MTP) drafters are making Gemma 4 models up to 3x faster at inference.
Google·2mo ago
Gemlet: Native Keyboard-First Gemini Client for macOS
Gemlet is a native, keyboard-first client for Gemini on macOS. Stop hunting for browser tabs to launch AI instantly with global hotkeys. It
Product Hunt·4mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.