Pretergeek

Pretergeek's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 11 days ago

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Paper • 2503.10460 • Published Mar 13, 2025 • 30

upvoted a collection about 1 month ago

Ministral 3

Collection

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 149

upvoted an article about 1 month ago

view article

Article

The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU

• 

Jan 2

•

12

upvoted 6 collections 3 months ago

LLaVA-Video

Collection

Models focus on video understanding (previously known as LLaVA-NeXT-Video). • 8 items • Updated Feb 21, 2025 • 65

SmolLM3 evaluation datasets

Collection

Datasets to decontaminate the post-training mixtures against. Use the subset and column values described per entry • 13 items • Updated Jul 8, 2025 • 8

SmolLM3 pretraining datasets

Collection

datasets used in SmolLM3 pretraining • 15 items • Updated Aug 12, 2025 • 45

INTELLECT-2

Collection

INTELLECT-2 is a 32 billion parameter language model with globally distributed reinforcement learning. • 3 items • Updated Oct 7, 2025 • 26

INTELLECT-1 Dataset

Collection

INTELLECT-1 Training dataset • 5 items • Updated Oct 7, 2025 • 26

INTELLECT-1

Collection

13 items • Updated Oct 7, 2025 • 12

upvoted an article 4 months ago

view article

Article

Preserving Agency: Why AI Safety Needs Community, Not Corporate Control

• 

Sep 29, 2025

•

10

upvoted a paper 5 months ago

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published Jun 12, 2024 • 71

upvoted a collection 6 months ago

Cosmos-Reason1

Collection

⚠️ The latest version of Cosmos Reason is now live! 👉 https://huggingface.co/collections/nvidia/cosmos-reason2 • 8 items • Updated 3 days ago • 40

upvoted an article 7 months ago

view article

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

• 
• 

Jul 9, 2025

•

779

upvoted a paper 8 months ago

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

Paper • 2506.04308 • Published Jun 4, 2025 • 43

upvoted an article 9 months ago

view article

Article

Interactive Tools for machine learning, deep learning, and math

• 

May 26, 2025

•

47

upvoted 3 papers 9 months ago

Thinkless: LLM Learns When to Think

Paper • 2505.13379 • Published May 19, 2025 • 50

AdaptThink: Reasoning Models Can Learn When to Think

Paper • 2505.13417 • Published May 19, 2025 • 83

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Paper • 2505.11896 • Published May 17, 2025 • 58

upvoted a collection 9 months ago

Physical AI

Collection

Collection of open, commercial-grade datasets for physical AI developers • 25 items • Updated 3 days ago • 117

upvoted a paper 9 months ago

Think on your Feet: Adaptive Thinking via Reinforcement Learning for Social Agents

Paper • 2505.02156 • Published May 4, 2025 • 18