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.🦙

Recent Activity

new activity 6 days ago

google/gemma-3-1b-it:Update README.md

updated a model 7 days ago

google/gemma-3-27b-pt-qat-q4_0-gguf

View all activity

Organizations

osanseviero's activity

upvoted a collection 7 days ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 7 days ago • 110

upvoted a paper 14 days ago

Gemma 3 Technical Report

Paper • 2503.19786 • Published 16 days ago • 43

upvoted a collection 28 days ago

Gemma 3 Release

17 items • Updated 7 days ago • 321

upvoted an article 29 days ago

Article

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

30 days ago

• 381

upvoted a collection about 1 month ago

C4AI Aya Vision

Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated Mar 4 • 68

upvoted an article about 1 month ago

Article

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

Mar 4

• 73

upvoted a paper about 1 month ago

Magma: A Foundation Model for Multimodal AI Agents

Paper • 2502.13130 • Published Feb 18 • 58

upvoted an article about 2 months ago

Article

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

Feb 19

• 68

upvoted a collection about 2 months ago

GemmaX2

GemmaX2 language models, including pretrained and instruction-tuned models of 2 sizes, including 2B, 9B. • 7 items • Updated Feb 7 • 21

upvoted 2 papers about 2 months ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 180

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 141

upvoted a collection about 2 months ago

PaliGemma 2 Mix

13 items • Updated 7 days ago • 60

upvoted a paper about 2 months ago

Scaling Pre-training to One Hundred Billion Data for Vision Language Models

Paper • 2502.07617 • Published Feb 11 • 29

upvoted an article 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.21k

upvoted a paper 2 months ago

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

Paper • 2501.18512 • Published Jan 30 • 29

upvoted an article 2 months ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 837