Edward Neuhaus's picture

Edward Neuhaus

Pretergeek

·

https://ko-fi.com/pretergeek

pretergeek

AI & ML interests

NLP, ML, LLMs, AI Ethics, AI Welfare, Privacy in AI, FOSS.

Recent Activity

liked a model about 5 hours ago

llava-hf/LLaVA-NeXT-Video-7B-32K-hf

reacted to mike-ravkine's post with 🔥 3 days ago

There is no anxiety quite like powering up 2KW of basement compute after rewiring it all. Small bit of trouble with the horizontal 3090 because I misread my motherboard manual, but otherwise so far so good.. Next we see if I've built up enough cooling to hit my target TDP on those 3-slot nvlinked cards especially. The 4-slot bridges are much easier to work with but their prices went bananas and I couldn't acquire a second, so gotta get a little creative with intakes.

liked a model 6 days ago

lmms-lab/LLaVA-OneVision-1.5-8B-Instruct

View all activity

Organizations

None yet

upvoted a collection 6 days ago

LLaVA-Video

Models focus on video understanding (previously known as LLaVA-NeXT-Video). • 8 items • Updated Feb 21 • 64

upvoted 2 collections 9 days ago

SmolLM3 evaluation datasets

Datasets to decontaminate the post-training mixtures against. Use the subset and column values described per entry • 13 items • Updated Jul 8 • 7

SmolLM3 pretraining datasets

datasets used in SmolLM3 pretraining • 15 items • Updated Aug 12 • 36

upvoted 3 collections 12 days ago

INTELLECT-2

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

INTELLECT-1 Dataset

INTELLECT-1 Training dataset • 5 items • Updated Oct 7 • 25

INTELLECT-1

13 items • Updated Oct 7 • 11

upvoted an article about 1 month ago

Article

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

By

•

Sep 29

• 10

upvoted a paper 3 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 3 months ago

Cosmos-Reason1

Multimodal world understanding through reasoning • 8 items • Updated 2 days ago • 37

upvoted an article 4 months ago

Article

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

Jul 9

• 706

upvoted a paper 5 months ago

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

Paper • 2506.04308 • Published Jun 4 • 43

upvoted an article 6 months ago

Article

Interactive Tools for machine learning, deep learning, and math

By

•

May 26

• 47

upvoted 3 papers 6 months ago

Thinkless: LLM Learns When to Think

Paper • 2505.13379 • Published May 19 • 50

AdaptThink: Reasoning Models Can Learn When to Think

Paper • 2505.13417 • Published May 19 • 82

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

Paper • 2505.11896 • Published May 17 • 58

upvoted a collection 6 months ago

Physical AI

Collection of open, commercial-grade datasets for physical AI developers • 23 items • Updated 2 days ago • 89

upvoted a paper 6 months ago

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

Paper • 2505.02156 • Published May 4 • 18

upvoted a collection 9 months ago

The Big Benchmarks Collection

Gathering benchmark spaces on the hub (beyond the Open LLM Leaderboard) • 13 items • Updated Nov 18, 2024 • 253

upvoted a paper 10 months ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published Jan 8 • 285

upvoted a collection 12 months ago

Useful Spaces

14 items • Updated May 27 • 1