1. X
  2. Edward Beeching
Log inSign up
Edward Beeching
234 posts
user avatar
Edward Beeching
@edwardbeeching
Research Scientist @HuggingFace. PhD in Deep RL approaches for Robotic Navigation @INRIA.
Lyon, France
Joined July 2010
70
Following
2,548
Followers
RepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Edward Beeching
    @edwardbeeching
    Jan 28, 2025
    As part of our open reproduction of R1, we have roughly reproduced DeepSeek's MATH-500 eval numbers with Hugging Face's lighteval suite. We had to improve our latex parser to get the last few %.
    Image
    145K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Mar 28, 2022
    A month ago I joined🤗@huggingface as a Research Scientist. They're great: opening an office in Lyon, allowing me to work on open-source projects and trusting me to define my own schedule. I am proud to have added the Decision Transformer to🤗transformers. huggingface.co/blog/decision-…
    Image
  • user avatar
    Edward Beeching
    @edwardbeeching
    Sep 8, 2022
    Today @huggingface 🤗 release a long awaited tutorial on training Decision Tranformers models as a blogpost and colab notebook. The is part of a series on the application of transformer models in Deep RL settings. 👉 huggingface.co/blog/train-dec… #reinforcementlearning #transformers
    Image
    GIF
  • user avatar
    Edward Beeching
    @edwardbeeching
    Dec 15, 2022
    Sneak peak of WIP of an upcoming FPS environment for my @godotengine Reinforcement Learning library. Agents trained using async PPO and population-based training with sample-factory. 👉 github.com/edbeeching/god… It will soon be available on the @huggingface hub!
    Image
    00:00
  • user avatar
    Edward Beeching
    @edwardbeeching
    Oct 10, 2023
    We will soon release the @huggingface LLM alignment handbook. Using these recipes you can build state of the art chatbots such as Zephyr-7b, released today. Register your interest by starring the github github.com/huggingface/al… You can find out about Zephyr-7b in this thread:
    Image
    50K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Jul 10, 2024
    The winning AI Math Olypiad model is out! Using an approach we call Self-Consistency with Tool Integrated Reasoning. Constraints of Kaggle (T4 GPUs) required us to use activation aware quantization in order to not degrade model performance. Details and code to follow next week.
    Image
    Image
    user avatar
    Lewis Tunstall
    @_lewtun
    Jul 10, 2024
    Introducing NuminaMath-7B-TIR, the small but mighty model that won the first progress prize of the AI Math Olympiad 🥇! > Fine-tuned with iterative SFT on DeepSeekMath-7B from @deepseek_ai > Stage 1: learn math with chain of thought samples > Stage 2: learn code with
    20K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Apr 22, 2024
    We are proud to release the first open-source multi-modal, multi-task and multi-domain model! Called JAT. A crucial step for generalist agents. What started out as an open reproduction of GATO with @QGallouedec, @ClementRomac and myself, has evolved into a far greater project.
    Image
    00:00
    28K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Jul 22, 2024
    Our prize winning Math recipe is now released with datasets, training code and a new 72B math model. See thread for more details:
    Image
    Image
    user avatar
    Lewis Tunstall
    @_lewtun
    Jul 21, 2024
    We have just released the ✨NuminaMath datasets: the largest collection of ~1M math competition problem-solution pairs, ranging in difficulty from junior challenge to Math Olympiad preselection. These datasets were used to win the 1st Progress Prize of the AI Math Olympiad and
    40K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Feb 2, 2024
    When I am not busy Aligning LLMs, I spend my free time developing Godot RL Agents, an RL library for the #Godot game engine. Today we released version 0.7.0 with a number of new features, bugfixes and examples. Thanks to all the contributors for creating cool example envs:
    Image
    00:00
    12K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Dec 1, 2022
    Announcing the release of Sample Factory 2.0. A lightning fast production grade Deep RL library. Sample Factory 2.0 is a collaboration between @petrenko_ai from @uscresl and 🤗 @huggingface. 👉 github.com/alex-petrenko/… Find out more on this 🧵
    Image
    00:00
  • user avatar
    Edward Beeching
    @edwardbeeching
    Dec 21, 2022
    The last environment for my @godotengine Reinforcement Learning lib, a team FPS. The release is planned for tomorrow once I have updated the docs. 👉 github.com/edbeeching/god… Env source code and builds are already available on the @huggingface hub: 👉 huggingface.co/datasets?sort=…
    Image
    00:00
    17K
  • user avatar
    Edward Beeching
    @edwardbeeching
    May 23, 2023
    We have a new leader on the Open LLM leaderboard. Congrats to ausboss/llama-30b-supercot! They combined chain-of-thought datasets, code explanations and instructions, snippets, logical deductions and Alpaca GPT-4 prompts. Check it out here: huggingface.co/spaces/Hugging…
    Image
    34K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Dec 22, 2022
    Godot RL Agents v0.4.0 has been released. 👉github.com/edbeeching/god… This includes: ‣ Godot 4 support ‣ 3 RL frameworks: Sample Factory, Stable Baselines 3 and rllib ‣ 2 Advanced Racing and FPS environments ‣ Updated docs (still WIP🙂) Find out more in this thread 🧵
    Image
    GitHub - edbeeching/godot_rl_agents: An Open Source package that allows video game creators, AI...
    From github.com
    15K
  • user avatar
    Edward Beeching
    @edwardbeeching
    Jan 26, 2024
    Thanks to the community for their feedback on DPO vs. IPO vs. KTO. In particular, we thank the authors of IPO, who have worked with us this week to improve TRL's IPO implementation. IPO now is comparable to DPO! Check out the updated blogpost. huggingface.co/blog/pref-tuni…
    Image
    21K
Advertisement
Advertisement