Omar Sanseviero's picture

Omar Sanseviero

osanseviero

·

https://osanseviero.github.io/hackerllama/

AI & ML interests

Llamas, model merging, massive ASR for data collection, 3D ML, on-device ML, quantization, model judging, ML in browser, healthcare applications, education, intersection of art and ML.🦙

Organizations

upvoted an article 13 days ago

Article

Gemma 3n fully available in the open-source ecosystem!

By

and 7 others •

14 days ago

• 105

upvoted a paper 17 days ago

VideoPrism: A Foundational Visual Encoder for Video Understanding

Paper • 2402.13217 • Published Feb 20, 2024 • 30

upvoted a changelog about 1 month ago

Changelog

New Inference Providers Dashboard

Jun 5

• 58

upvoted a collection about 1 month ago

GRMR V3 Models

An improved set of models for grammar correction. (Chat template should work, no "responding as an LLM" anymore, that kind of stuff). • 6 items • Updated Jun 4 • 10

upvoted a paper about 1 month ago

One RL to See Them All: Visual Triple Unified Reinforcement Learning

Paper • 2505.18129 • Published May 23 • 60

upvoted an article about 1 month ago

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

May 15

• 115

upvoted 2 collections about 2 months ago

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 4 items • Updated May 30 • 181

Gemma 3n Preview

4 items • Updated 29 days ago • 151

upvoted an article 3 months ago

Article

17 Reasons Why Gradio Isn't Just Another UI Library

By

and 1 other •

Apr 16

• 40

upvoted a collection 3 months ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 19 items • Updated Apr 18 • 27

upvoted a paper 3 months ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14 • 276

upvoted an article 3 months ago

Article

The Large Language Model Course

By

•

Jan 16

• 195

upvoted a collection 3 months ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated May 30 • 202

upvoted an article 3 months ago

Article

Custom Vibe Coding Quest Part 2: 🚙 Fine-Tuning Gemma 3 for Code Reasoning

By

•

Apr 1

• 25

upvoted a paper 3 months ago

Gemma 3 Technical Report

Paper • 2503.19786 • Published Mar 25 • 52

upvoted a collection 4 months ago

Gemma 3 Release

24 items • Updated May 30 • 399

upvoted an article 4 months ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

By

and 3 others •

Mar 12

• 441

upvoted a collection 4 months ago

Cohere Labs Aya Vision

Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated Apr 15 • 69

upvoted an article 4 months ago

Article

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

By

and 3 others •

Mar 4

• 75

upvoted a paper 4 months ago

Magma: A Foundation Model for Multimodal AI Agents

Paper • 2502.13130 • Published Feb 18 • 58