Victor Gallego's picture

Victor Gallego

vicgalle

·

https://github.com/vicgalle

AI & ML interests

Preference fine-tuning, alignment & synthetic data. Building LLMs in general!

Organizations

vicgalle's activity

upvoted an article 15 days ago

Article

VLM Art Analysis

By

•

Oct 4

• 11

upvoted a collection 18 days ago

steiner-preview

Reasoning models trained on synthetic data using reinforcement learning. • 3 items • Updated 20 days ago • 23

upvoted a paper 23 days ago

Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems

Paper • 2410.13334 • Published 24 days ago • 12

upvoted a paper about 1 month ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7 • 165

upvoted a collection about 2 months ago

Llama 3.2 Re-upload

10 items • Updated Sep 25 • 11

upvoted 2 papers about 2 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19 • 134

Hermes 3 Technical Report

Paper • 2408.11857 • Published Aug 15 • 36

upvoted an article 3 months ago

Article

Tensor Parallelism

By

•

Aug 20

• 9

upvoted a collection 3 months ago

Hermes 3

The Hermes 3 Series of Models • 8 items • Updated Aug 23 • 87

upvoted a paper 3 months ago

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models

Paper • 2408.03837 • Published Aug 7 • 17

upvoted a collection 4 months ago

Llama 3.1

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated Sep 25 • 612

upvoted 3 articles 4 months ago

Article

Announcing Finance Commons and the Bad Data Toolbox: Pioneering Open Data and Advanced Document Processing

By

•

Jul 19

• 17

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 258

Article

The Rise of Agentic Data Generation

By

•

Jul 15

• 75

upvoted 2 papers 4 months ago

BM25S: Orders of magnitude faster lexical search via eager sparse scoring

Paper • 2407.03618 • Published Jul 4 • 11

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Paper • 2406.20094 • Published Jun 28 • 94

upvoted a paper 5 months ago

Symbolic Learning Enables Self-Evolving Agents

Paper • 2406.18532 • Published Jun 26 • 11

upvoted a collection 5 months ago

Probably DPO datasets

A collection of datasets that probably support DPO • 146 items • Updated Jun 26 • 12

upvoted 2 papers 5 months ago

TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings

Paper • 2406.15586 • Published Jun 21 • 2

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch

Paper • 2406.14563 • Published Jun 20 • 29