Nathan Lambert

natolambert's activity

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

upvoted a paper 7 days ago

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

Paper • 2507.01352 • Published 13 days ago • 50

upvoted a collection 12 days ago

Reward Models

Collection

Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge • 8 items • Updated 4 days ago • 15

upvoted 2 collections about 1 month ago

Reward Bench 2

Collection

Datasets, spaces, and models for Reward Bench 2 benchmark and paper! • 11 items • Updated Jun 3 • 12

Common Pile v0.1

Collection

All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated Jun 6 • 26

upvoted a collection 2 months ago

OpenVision

Collection

27 items • Updated May 8 • 29

upvoted a collection 3 months ago

Qwen3

Collection

72 items • Updated 30 days ago • 850

upvoted a paper 3 months ago

Reinforcement Learning from Human Feedback

Paper • 2504.12501 • Published Apr 16 • 3

upvoted a collection 5 months ago

OLMoE (January 2025)

Collection

Improved OLMoE for iOS app. Read more: https://allenai.org/blog/olmoe-app • 10 items • Updated Apr 30 • 15

upvoted an article 6 months ago

view article

Article

Putting RL back in RLHF

By and 1 other •

Jun 12, 2024

• 96

upvoted a collection 6 months ago

2024 Interconnects Artifacts

Collection

Models & datasets mentioned in the bottom section of posts! • 280 items • Updated Jan 2 • 6

upvoted a paper 7 months ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 146

upvoted a collection 7 months ago

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 10 items • Updated Apr 30 • 72

upvoted 3 collections 8 months ago

OLMo 2

Collection

Artifacts for the OLMo 2 release. • 35 items • Updated May 1 • 134

Tulu 3 Models

Collection

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated Apr 30 • 100

Tulu 3 Datasets

Collection

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 33 items • Updated Apr 30 • 88

upvoted 4 collections 10 months ago

Molmo

Collection

Artifacts for open multimodal language models. • 5 items • Updated Apr 30 • 305

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated Apr 28 • 626

Skywork-Reward-Data-Collection

Collection

Open-source preference datasets used to train the Skywork reward model series • 17 items • Updated Oct 12, 2024 • 17

OLMoE (November 2024)

Collection

Artifacts for open mixture-of-experts language models. • 13 items • Updated Apr 30 • 30

upvoted a collection 11 months ago

Hermes 3

Collection

The Hermes 3 Series of Models • 11 items • Updated 25 days ago • 124