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.🦙

Articles

Welcome Llama 3 - Meta's new open LLM

CodeGemma - an official Google release for code LLMs

🪆 Introduction to Matryoshka Embedding Models

Welcome Gemma - Google's new open LLM

Constitutional AI with Open LLMs

Preference Tuning LLMs with Direct Preference Optimization Methods

Mixture of Experts Explained

Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face

Inference for PROs

Spread Your Wings: Falcon 180B is here

Code Llama: Llama 2 learns to code

Results of the Open Source AI Game Jam

Llama 2 is here - get it on Hugging Face

The Falcon has landed in the Hugging Face ecosystem

Hugging Face Machine Learning Demos on arXiv

What's new in Diffusers? 🎨

Announcing Evaluation on the Hub

An Introduction to Deep Reinforcement Learning

Welcome spaCy to the 🤗 Hub

Sentence Transformers in the 🤗 Hub

Organizations

osanseviero's activity

upvoted an article about 22 hours ago

Article

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

2 days ago

• 51

upvoted a collection 7 days ago

OpenELM Instruct Models

4 items • Updated 18 days ago • 91

upvoted a paper 7 days ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published 8 days ago • 222

upvoted a collection 8 days ago

Quantized-FT-Orca-Math

Models trained during quantization aware fine-tuning experiments using PyTorch's FSDP. • 8 items • Updated 14 days ago • 5

upvoted an article 11 days ago

Article

Fine-tune Llama 3 with ORPO

By

•

8 days ago

• 146

upvoted an article 12 days ago

Article

Welcome Llama 3 - Meta's new open LLM

13 days ago

• 224

upvoted a collection 12 days ago

Meta Llama 3

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated 12 days ago • 443

upvoted a collection 13 days ago

Idefics2 🐶

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 8 items • Updated 13 days ago • 57

upvoted a collection 14 days ago

fuck quadratic attention

11 items • Updated 6 days ago • 17

upvoted 5 articles 14 days ago

Article

Custom architectures with HuggingFace 🤗

By

•

9 days ago

• 18

Article

Create Mixtures of Experts with MergeKit

By

•

Mar 28

• 8

Article

Merge Large Language Models with mergekit

By

•

Jan 9

• 12

Article

Running Privacy-Preserving Inference on Hugging Face Endpoints

15 days ago

• 13

Article

Design choices for Vision Language Models in 2024

By

•

14 days ago

• 17

upvoted 2 papers 15 days ago

ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization

Paper • 2402.09320 • Published Feb 14 • 6

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Paper • 2404.05961 • Published 22 days ago • 61

upvoted an article 15 days ago

Article

Mergoo: Efficiently Build Your Own MoE LLM

By

•

3 days ago

• 27

upvoted a collection 15 days ago

Pile-T5

T5 trained on the Pile with Llama Tokenizer • 4 items • Updated 16 days ago • 16

upvoted an article 17 days ago

Article

Llama 2 is here - get it on Hugging Face

Jul 18, 2023

• 10

upvoted a collection 17 days ago

Antidote Project

Data and models generated within the Antidote Project (https://univ-cotedazur.eu/antidote) • 17 items • Updated 5 days ago • 5

upvoted 2 articles 18 days ago

Article

Vision Language Models Explained

20 days ago

• 56

Article

Mixture of Depth is Vibe

By

•

9 days ago

• 34

upvoted 2 papers 19 days ago

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Paper • 2404.07143 • Published 20 days ago • 90

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Paper • 2404.07839 • Published 19 days ago • 36

upvoted an article 19 days ago

Article

Making thousands of open LLMs bloom in the Vertex AI Model Garden

21 days ago

• 14

upvoted a collection 19 days ago

Zephyr ORPO

Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook • 3 items • Updated 19 days ago • 13

upvoted a paper 20 days ago

VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild

Paper • 2403.16973 • Published Mar 25 • 2

upvoted an article 20 days ago

Article

DS-MoE: Making MoE Models More Efficient and Less Memory-Intensive

By

•

22 days ago

• 25

upvoted a paper 21 days ago

Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models

Paper • 2404.05567 • Published 22 days ago • 10

upvoted an article 21 days ago

Article

CodeGemma - an official Google release for code LLMs

22 days ago

• 91

upvoted a collection 21 days ago

CodeGemma Release

12 items • Updated 19 days ago • 53

upvoted a collection 22 days ago

RecurrentGemma Release

6 items • Updated 19 days ago • 12

upvoted an article 22 days ago

Article

Welcome Gemma - Google's new open LLM

Feb 21

• 6

upvoted a collection 22 days ago

Aurora-M models

Aurora-M models (base, biden-harris redteams and instruct) • 5 items • Updated 4 days ago • 15

upvoted an article 23 days ago

Article

Data is better together

Mar 4

• 3

upvoted 2 papers 23 days ago

Linear Attention Sequence Parallelism

Paper • 2404.02882 • Published 27 days ago • 3

More Agents Is All You Need

Paper • 2402.05120 • Published Feb 3 • 46

upvoted 4 articles 23 days ago

Article

Code Llama: Llama 2 learns to code

Aug 25, 2023

• 2

Article

Diffusion Models

By

•

15 days ago

• 11

Article

Mixture of Experts Explained

Dec 11, 2023

• 44

Article

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

27 days ago

• 18

upvoted a collection 23 days ago

Mistral Instruct Merges

Merge of Mistral Instruct 1 and 2 using different mergekit techniques • 6 items • Updated Jan 17 • 1

upvoted an article 23 days ago

Article

RAG Empowerment: Cohere C4AI Command-R and Transformers Unveiled

By

•

23 days ago

• 9

upvoted an article 25 days ago

Article

The LASER technique: Evaluating SVD compression

By

•

26 days ago

• 6

upvoted a paper 28 days ago

Octopus v2: On-device language model for super agent

Paper • 2404.01744 • Published 29 days ago • 50

upvoted a collection 28 days ago

PDF Document / OCR Datasets

Document datasets with .pdf files that are usable with pixparse libraries and tools. • 2 items • Updated Mar 30 • 36

upvoted a paper 29 days ago

Jamba: A Hybrid Transformer-Mamba Language Model

Paper • 2403.19887 • Published Mar 28 • 97

upvoted 4 collections about 1 month ago

boulderspot

find places to climb outside from aerial imagery • 4 items • Updated 30 days ago • 3

Moirai-1.0-R models

3 items • Updated Mar 26 • 20

HyperGraph Datasets

Collection of HyperGraph Datasets • 17 items • Updated 27 days ago • 7

DBRX

DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27 • 85

upvoted a paper about 1 month ago

Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Paper • 2403.18814 • Published Mar 27 • 37

upvoted 3 collections about 1 month ago

MGM

Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 11 items • Updated 9 days ago • 42

Llama2-7B HQQ+

Extreme low-bit quantization with HQQ+ (HQQ + LoRA adapter) • 3 items • Updated 11 days ago • 14

InternLM2

7 items • Updated Feb 22 • 5

upvoted 2 papers about 1 month ago

InternLM2 Technical Report

Paper • 2403.17297 • Published Mar 26 • 25

Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Paper • 2403.12881 • Published Mar 19 • 14

upvoted a collection about 1 month ago

ORPO

This is the official collection of "ORPO: Monolithic Preference Optimization without Reference Model". • 5 items • Updated 19 days ago • 10

upvoted a paper about 1 month ago

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12 • 52

upvoted a collection about 1 month ago

Multimodal

243 items • Updated 20 days ago • 12