Nathan Lambert's picture

Nathan Lambert

natolambert

·

https://www.natolambert.com/

AI & ML interests

Reinforcement learning, Ethics, Robotics, Dynamics Models

Recent Activity

updated a collection 13 days ago

2024 Interconnects Artifacts

liked a dataset 13 days ago

HuggingFaceTB/finemath

updated a collection 14 days ago

2024 Interconnects Artifacts

View all activity

Articles

Ethics and Society Newsletter #4: Bias in Text-to-Image Models

Can foundation models label data like humans?

Creating a Coding Assistant with StarCoder

StackLLaMA: A hands-on guide to train LLaMA with RLHF

Red-Teaming Large Language Models

What Makes a Dialog Agent Useful?

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Stable Diffusion with 🧨 Diffusers

Organizations

natolambert's activity

upvoted a paper 16 days ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published 19 days ago • 132

upvoted a collection 23 days ago

PixMo

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 • 9 items • Updated Nov 27, 2024 • 51

upvoted 3 collections about 1 month ago

OLMo 2

Artifacts for the second set of OLMo models. • 17 items • Updated Nov 27, 2024 • 58

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 7 items • Updated Nov 27, 2024 • 29

Tulu 3 Datasets

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 32 items • Updated Nov 27, 2024 • 63

upvoted 2 collections 3 months ago

Molmo

Artifacts for open multimodal language models. • 5 items • Updated Nov 27, 2024 • 289

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated Nov 28, 2024 • 451

upvoted 2 collections 4 months ago

Skywork-Reward-Data-Collection

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

OLMoE

Artifacts for open mixture-of-experts language models. • 13 items • Updated Nov 27, 2024 • 28

upvoted a collection 5 months ago

Hermes 3

The Hermes 3 Series of Models • 10 items • Updated 21 days ago • 100

upvoted a collection 6 months ago

Aligned Diffusion Model via DPO

18 items • Updated Jul 8, 2024 • 3

upvoted 2 collections 7 months ago

Tulu V2.5 Suite

A suite of models trained using DPO and PPO across a wide variety (up to 14) of preference datasets. See https://arxiv.org/abs/2406.09279 for more! • 44 items • Updated Nov 27, 2024 • 14

SciRIFF

Data and models to enhance instruction-following for scientific literature understanding. • 9 items • Updated Nov 27, 2024 • 8

upvoted a collection 9 months ago

[lecture artifacts] aligning open language models

artifacts referenced in the talk timeline! Slides: https://docs.google.com/presentation/d/1quMyI4BAx4rvcDfk8jjv063bmHg4RxZd9mhQloXpMn0/edit?usp=sharin • 63 items • Updated Apr 17, 2024 • 56

upvoted 2 collections 10 months ago

Reward Bench

Datasets, spaces, and models for the reward model benchmark! • 5 items • Updated Nov 27, 2024 • 8

Gemma release

Groups the Gemma models released by the Google team. • 40 items • Updated 19 days ago • 328

upvoted 2 collections 11 months ago

Model Merging

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12, 2024 • 218

OLMo Suite

Artifacts for the first set of OLMo models. • 18 items • Updated Nov 27, 2024 • 69

upvoted 2 collections about 1 year ago

Deita

14 items • Updated May 20, 2024 • 9

Awesome feedback datasets

A curated list of datasets with human or AI feedback. Useful for training reward models or applying techniques like DPO. • 19 items • Updated Apr 12, 2024 • 66