Omar Sanseviero's picture

In a Training Loop 🔄

Omar Sanseviero

osanseviero

google

·

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-4-31B-it:fix(chat_template): Emit multimodal placeholders in tool response content-parts

new activity 6 days ago

google/gemma-4-26B-A4B-it:fix(chat_template): Emit multimodal placeholders in tool response content-parts

new activity 6 days ago

google/gemma-4-E4B-it:fix(chat_template): Emit multimodal placeholders in tool response content-parts

View all activity

Organizations

upvoted a collection 20 days ago

Gemma 4

12 items • Updated 19 days ago • 847

upvoted an article 3 months ago

Article

Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era

Reubencf

•

Mar 7

• 8

upvoted a collection 5 months ago

T5Gemma 2

3 items • Updated Mar 12 • 77

upvoted a paper 8 months ago

EmbeddingGemma: Powerful and Lightweight Text Representations

Paper • 2509.20354 • Published Sep 24, 2025 • 50

upvoted an article 8 months ago

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

+5

ariG23498, sergiopaniego, reach-vb, pcuenq, ArthurZ, SaylorTwift, cyrilvallez

•

Sep 11, 2025

• 188

upvoted an article 9 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

+4

tomaarsen, Xenova, alvarobartt, ariG23498, pcuenq, sergiopaniego

•

Sep 4, 2025

• 275

upvoted a collection 9 months ago

EmbeddingGemma

3 items • Updated Mar 12 • 119

upvoted a collection 11 months ago

T5Gemma

32 items • Updated Mar 12 • 82

upvoted an article 11 months ago

Article

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

+6

ariG23498, pcuenq, sergiopaniego, reach-vb, FL33TW00D-HF, Xenova, Steveeeeeeen, kashif

•

Jun 26, 2025

• 121

upvoted a paper 11 months ago

VideoPrism: A Foundational Visual Encoder for Video Understanding

Paper • 2402.13217 • Published Feb 20, 2024 • 40

upvoted a changelog 12 months ago

Hugging Face Changelog

New Inference Providers Dashboard

Jun 5, 2025

• 69

upvoted a collection 12 months 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, 2025 • 10

upvoted a paper 12 months ago

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

Paper • 2505.18129 • Published May 23, 2025 • 62

upvoted an article 12 months ago

Article

The Transformers Library: standardizing model definitions

+2

lysandre, ArthurZ, pcuenq, julien-c

•

May 15, 2025

• 122

upvoted 2 collections about 1 year ago

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 9 items • Updated Mar 12 • 493

Gemma 3n Preview

4 items • Updated Mar 12 • 208

upvoted an article about 1 year ago

Article

17 Reasons Why Gradio Isn't Just Another UI Library

ysharma, abidlabs

•

Apr 16, 2025

• 44

upvoted a collection about 1 year ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 29 items • Updated Aug 14, 2025 • 32

upvoted a paper about 1 year ago

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

Paper • 2504.10479 • Published Apr 14, 2025 • 310

upvoted an article about 1 year ago

Article

The Large Language Model Course

mlabonne

•

Jan 16, 2025

• 229