Edward Beeching's picture

Edward Beeching

edbeeching

·

https://edbeeching.github.io/

edbeeching

AI & ML interests

None yet

Articles

How NuminaMath Won the 1st AIMO Progress Prize

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Vision Language Models Explained

Constitutional AI with Open LLMs

Preference Tuning LLMs with Direct Preference Optimization Methods

Can foundation models label data like humans?

Creating a Coding Assistant with StarCoder

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

Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU

Train your first Decision Transformer

Introducing Decision Transformers on Hugging Face 🤗

Organizations

edbeeching's activity

upvoted an article 6 months ago

Article

How NuminaMath Won the 1st AIMO Progress Prize

Jul 11

• 107

upvoted a paper about 1 year ago

A General Theoretical Paradigm to Understand Learning from Human Preferences

Paper • 2310.12036 • Published Oct 18, 2023 • 13

upvoted a collection about 1 year ago

Reward models on the hub

UNMAINTAINED: See RewardBench... A place to collect reward models, an often not released artifact of RLHF. • 18 items • Updated Apr 13 • 25

upvoted 2 papers about 1 year ago

Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Paper • 2311.10702 • Published Nov 17, 2023 • 18

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 123

upvoted a paper over 1 year ago

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Paper • 2306.01116 • Published Jun 1, 2023 • 32