Ben Burtenshaw (@ben_burtenshaw) / X

Ben Burtenshaw

2,072 posts

Ben Burtenshaw

@ben_burtenshaw

community MLE 🤗 @huggingface gh/hf username: burtenshaw anon feedback: admonymous.co/ben-burtenshaw

Earth

Joined February 2024

Replies Articles Media

Ben Burtenshaw
@ben_burtenshaw
Feb 10, 2025
The @huggingface agents course is finally out! This first unit of the course sets you up with all the fundamentals to become a pro in agents. - What's an AI Agent? - What are LLMs? - Understanding AI Agents through the Thought-Action-Observation Cycle - Thought, Internal
Ben Burtenshaw
@ben_burtenshaw
Dec 3, 2024
For anyone interested in fine-tuning or aligning LLMs, I’m running this free and open course called smol course. It’s not big like Li Yin and Maxime Labonne, it’s just smol. - It focuses on practical use cases, so if you’re working on something, bring it along. - It’s peer
Ben Burtenshaw
@ben_burtenshaw
Mar 12, 2025
Let’s make Gemma 3 think! Here’s a notebook to make Gemma reason with GRPO & TRL. I made this whilst prepping the next unit of the reasoning course: In this notebooks I combine together google’s model with some community tooling - First, I load the model from the @huggingface
Ben Burtenshaw
@ben_burtenshaw
Apr 30, 2025
Qwen3 Finetuning Notebook. I’m tuning @Alibaba_Qwen 3 for a fast local coding, and here’s a notebook for the process. 🧵More in the thread. More to come
Ben Burtenshaw
@ben_burtenshaw
Jun 26, 2025
Let's fine-tune Gemma 3n for free on Colab! I'm speed running this notebook to supervised fine-tune @GoogleDeepMind 's new Gemma on GUI grounding.
Ben Burtenshaw
@ben_burtenshaw
Feb 17, 2025
NEW COURSE! We’re cooking hard on @huggingface courses, and it’s not just agents. The NLP course is getting the same treatment with a new chapter on Supervised Fine-Tuning! The new SFT chapter will guide you through these topics: 1️⃣ Chat Templates: Master the art of
Ben Burtenshaw
@ben_burtenshaw
Mar 3, 2025
New Course on building reasoning models like Deepseek R1! It’s called The Reasoning Course and it's FREE and CERTIFIED. To sign up just follow the org. info in the thread
Ben Burtenshaw
@ben_burtenshaw
Oct 14, 2025
nanochat day 1: sharing everything we have: - we've got an org on the hub to share resources and discuss learning - we've trained a tokenizer and published it on the hub. - integrated base training with trackio for free logging. curves! if you're also working on this. join the
This post is unavailable.
Ben Burtenshaw
@ben_burtenshaw
May 15, 2025
Excited to launch our FREE Model Context Protocol (MCP) Course! Go from beginner to informed & learn to build AI apps leveraging external data & tools. - learn how MCP works - how to connect your LLMS to MCP Servers - how to deploy AI Agent applications with MCPs
Ben Burtenshaw
@ben_burtenshaw
Oct 9, 2025
deepmind just dropped a handy little colab on fine-tuning gemma3-270m for emoji generation. this is a super lower resource task with 270m parameter model, qlora, short sequences. so it's a great one to try out locally or on colab. it's also a nice one to deploy in a js app
Ben Burtenshaw
@ben_burtenshaw
Mar 19, 2025
Unsloth shipped a super educational notebook on how to fine tune @GoogleDeepMind Gemma3 with GRPO, for free! It's all on @huggingface learn.
Unsloth AI
@UnslothAI
Mar 19, 2025
We teamed up with @huggingface to release a free notebook for fine-tuning Gemma 3 with GRPO! Learn to: • Enable reasoning in Gemma 3 (1B) • Prepare/understand reward functions • Make GRPO work for tiny LLMs Notebook: colab.research.google.com/github/unsloth… Details: huggingface.co/reasoning-cour…
Ben Burtenshaw
@ben_burtenshaw
Sep 24, 2025
too much new learning material! we're releasing a few chapters of hard study on post training AI models. it covers all major aspects plus more to come. - Evaluating Large Language models on benchmarks and custom use cases - Preference Alignment with DPO - Fine tuning Vision
Ben Burtenshaw
@ben_burtenshaw
Oct 2, 2025
still experimenting with LoRA based on the @thinkymachines configuration and just implemented it in colab. In this notebook I set up a fine tune of Qwen/Qwen3-0.6B on the OpenR1-Math dataset with lora rank of 1. with this setup you can get the same reward accuracy as full
00:00
Ben Burtenshaw
@ben_burtenshaw
Apr 1, 2025
NEW MODEL: GemmaCoder3-12b is a code reasoning model that improves performance on the LiveCodeBench benchmark 11 points over the base model. This makes for a useful code model because: - At 8 bit it runs nicely on 32gb of RAM - Gemma3's 128k context length is great for large
GIF