66 52 339

Victor Gallego

vicgalle

https://github.com/vicgalle

AI & ML interests

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

Recent Activity

liked a model 5 days ago

Qwen/QwQ-32B-Preview

liked a model 11 days ago

AIDC-AI/Marco-o1

liked a model 18 days ago

Qwen/Qwen2.5-Coder-32B-Instruct

View all activity

Organizations

vicgalle's activity

liked a model 5 days ago

Qwen/QwQ-32B-Preview

Text Generation • Updated 4 days ago • 26.7k • • 910

liked a model 11 days ago

AIDC-AI/Marco-o1

Text Generation • Updated 9 days ago • 8.33k • 590

liked a model 18 days ago

Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • Updated 14 days ago • 157k • • 1.13k

liked a dataset 24 days ago

lingjie23/TexAes

Viewer • Updated 27 days ago • 50.4k • 53 • 2

updated a collection about 1 month ago

Configurable Safety Tuning ⚙️

Collection

CST allows for configurable inference-time control of LLM safety levels, so users can dictate model behavior based on the system prompt • 11 items • Updated Oct 27 • 2

liked a dataset about 1 month ago

JailbreakBench/JBB-Behaviors

Viewer • Updated Sep 26 • 500 • 4.26k • 24

upvoted an article about 1 month ago

Article

VLM Art Analysis

•

Oct 4

• 11

liked a model about 1 month ago

jukofyork/creative-writer-v0.1-alfa-35b

Text Generation • Updated Oct 27 • 84 • 2

upvoted a collection about 1 month ago

steiner-preview

Collection

Reasoning models trained on synthetic data using reinforcement learning. • 3 items • Updated Oct 20 • 24

liked a model about 1 month ago

peakji/steiner-32b-preview

Updated Oct 21 • 40 • 41

liked a dataset about 2 months ago

ai-safety-institute/AgentHarm

Viewer • Updated Oct 14 • 416 • 1.01k • 17

upvoted a paper about 2 months ago

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

Paper • 2410.13334 • Published Oct 17 • 12

liked a model about 2 months ago

mistralai/Ministral-8B-Instruct-2410

Updated 17 days ago • 56k • 354

upvoted a paper about 2 months ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7 • 166

liked a model about 2 months ago

lmms-lab/llava-critic-72b

Updated Oct 4 • 126 • 14

New activity in vicgalle/ConfigurableBeagle-11B 2 months ago

Adding the Open Portuguese LLM Leaderboard Evaluation Results

#4 opened 2 months ago by

leaderboard-pt-pr-bot

upvoted a collection 2 months ago

Llama 3.2 Re-upload

Collection

10 items • Updated Sep 25 • 11

upvoted a paper 2 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19 • 135

liked a dataset 2 months ago

toloka/beemo

Viewer • Updated 13 days ago • 2.19k • 271 • 13

liked a dataset 3 months ago

sequelbox/Celestia

Viewer • Updated Oct 30 • 126k • 161 • 9