Edward Beeching

Research scientist at Hugging Face known for RLHF tooling (TRL), Zephyr/OpenHermes-style alignment work, and open reasoning models.

Role: researcher
Currently at: Hugging Face
Twitter: twitter.com/edwardbeeching
GitHub: github.com/edbeeching
Scholar: scholar.google.com/citations
Papers: 3

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: scholar.google.com/citations

Attribution policy →

3papers·1tool contribs

Authored papers

NuminaMath: The Largest Public Dataset in AI4Maths with 860k Pairs of Competition Math Problems and Solutions

blog

2024

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

arXiv 2024

2024

Godot Reinforcement Learning Agents

arXiv 2021

2021

Tool contributions

NuminaMath

Numina

An 860k-problem competition-math dataset with detailed solutions, the open community's go-to corpus for training math-specialized LLMs.

SFT DatasetMathScientific Reasoning

Affiliations

Currently at

Hugging Face

researcher · infra

Frequent co-authors

from 3 papers

Albert Jiang

researcher

1 shared paper

Ben Lipkin

grad-student

1 shared paper

Bin Dong

professor

Christian Wolf

Clément Romac

Emmanuel Dellandréa

Guillaume Lample

founder

1 shared paper

Jia Li

researcher

1 shared paper

Jilles Debangoye

1 shared paper

Kashif Rasul

researcher

1 shared paper