Hugging Face's logo

FeeL (Feedback Loop)

non-profit
Activity Feed Request to join this org

AI & ML interests

Human Feedback and LLMs

Recent Activity

burtenshaw  updated a Space 7 days ago
feel-fl/open-human-feedback-chat
davidberenstein1957  updated a dataset 9 days ago
feel-fl/feel-feedback
burtenshaw  authored a paper about 1 month ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
View all activity

feel-fl's activity

burtenshaw 
posted an update about 8 hours ago
view post
Post
282
Still speed running Gemma 3 to think. Today I focused on setting up gpu poor hardware to run GRPO.

This is a plain TRL and PEFT notebook which works on mac silicone or colab T4. This uses the 1b variant of Gemma 3 and a reasoning version of GSM8K dataset.

🧑‍🍳 There’s more still in the oven like releasing models, an Unsloth version, and deeper tutorials, but hopefully this should bootstrap your projects.

Here’s a link to the 1b notebook: https://colab.research.google.com/drive/1mwCy5GQb9xJFSuwt2L_We3eKkVbx2qSt?usp=sharing
burtenshaw 
posted an update about 14 hours ago
view post
Post
664
everybody and their dog is fine-tuning Gemma 3 today, so I thought I'd do a longer post on the tips and sharp edges I find. let's go!

1. has to be install everything form main and nightly. this is what I'm working with to get unsloth and TRL running

git+https://github.com/huggingface/transformers@main
git+https://github.com/huggingface/trl.git@main
bitsandbytes
peft


plus this with --no-deps

git+https://github.com/unslothai/unsloth-zoo.git@nightly
git+https://github.com/unslothai/unsloth.git@nightly


2. will brown's code to turn GSM8k into a reasoning dataset is a nice toy experiment https://gist.github.com/willccbb/4676755236bb08cab5f4e54a0475d6fb

3. with a learning rate of 5e-6 rewards and loss stayed flat for the first 100 or so steps.

4. so far none of my runs have undermined the outputs after 1 epoch. therefore, I'm mainly experimenting with bigger LoRA adapters.

from trl import GRPOConfig

training_args = GRPOConfig(
    learning_rate = 5e-6,
    adam_beta1 = 0.9,
    adam_beta2 = 0.99,
    weight_decay = 0.1,
    warmup_ratio = 0.1,
    lr_scheduler_type = "cosine",
    optim = "adamw_8bit",
    logging_steps = 1,
    per_device_train_batch_size = 2,
    gradient_accumulation_steps = 1,
    num_generations = 2,
    max_prompt_length = 256,
    max_completion_length = 1024 - 256,
    num_train_epochs = 1,
    max_steps = 250,
    save_steps = 250,
    max_grad_norm = 0.1,
    report_to = "none",
)


5. vision fine-tuning isn't available in TRL's GRPOTrainer, so stick to text datasets. but no need to load the model differently in transformers or Unsloth

from transformers import AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained("google/gemma-3-4b-it)


if you want an introduction to GRPO, check out the reasoning course, it walks you through the algorithm, theory, and implementation in a smooth way.

https://huggingface.co/reasoning-course
  • 2 replies
·
burtenshaw 
posted an update 1 day ago
view post
Post
978
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 Hugging Face hub with transformers’s latest release for Gemma 3
- I use PEFT and bitsandbytes to get it running on Colab
- Then, I took Will Browns processing and reward functions to make reasoning chains from GSM8k
- Finally, I used TRL’s GRPOTrainer to train the model

Next step is to bring Unsloth AI in, then ship it in the reasoning course. Links to notebook below.

https://colab.research.google.com/drive/1Vkl69ytCS3bvOtV9_stRETMthlQXR4wX?usp=sharing
·
burtenshaw 
updated a Space 7 days ago
davidberenstein1957 
posted an update 8 days ago
burtenshaw 
posted an update 8 days ago
view post
Post
3538
I’m super excited to work with @mlabonne to build the first practical example in the reasoning course.

🔗 https://huggingface.co/reasoning-course

Here's a quick walk through of the first drop of material that works toward the use case:

- a fundamental introduction to reinforcement learning. Answering questions like, ‘what is a reward?’ and ‘how do we create an environment for a language model?’

- Then it focuses on Deepseek R1 by walking through the paper and highlighting key aspects. This is an old school way to learn ML topics, but it always works.

- Next, it takes to you Transformers Reinforcement Learning and demonstrates potential reward functions you could use. This is cool because it uses Marimo notebooks to visualise the reward.

- Finally, Maxime walks us through a real training notebook that uses GRPO to reduce generation length. I’m really into this because it works and Maxime took the time to validate it share assets and logging from his own runs for you to compare with.

Maxime’s work and notebooks have been a major part of the open source community over the last few years. I, like everyone, have learnt so much from them.
davidberenstein1957 
updated a dataset 9 days ago
davidberenstein1957 
posted an update 9 days ago
view post
Post
4166
🥊 Epic Agent Framework Showdown! Available today!

🔵 In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!

🛑 In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!

🔗 URL: https://huggingface.co/agents-course

We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at

- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows

The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.

Who won? You decide!
davidberenstein1957 
posted an update 10 days ago
view post
Post
2978
🫸 New release to push vector search to the Hub with vicinity and work with any serialisable objects.

🧑‍🏫 KNN, HNSW, USEARCH, ANNOY, PYNNDESCENT, FAISS, and VOYAGER.

🔗 Example Repo: minishlab/my-vicinity-repo
burtenshaw 
posted an update 14 days ago
view post
Post
5396
I made a real time voice agent with FastRTC, smolagents, and hugging face inference providers. Check it out in this space:

🔗 burtenshaw/coworking_agent
·
burtenshaw 
posted an update 16 days ago
view post
Post
6197
Now the Hugging Face agent course is getting real! With frameworks like smolagents, LlamaIndex, and LangChain.

🔗 Follow the org for updates https://huggingface.co/agents-course

This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers:

- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use

The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .
burtenshaw 
posted an update 22 days ago
view post
Post
7292
AGENTS + FINETUNING! This week Hugging Face learn has a whole pathway on finetuning for agentic applications. You can follow these two courses to get knowledge on levelling up your agent game beyond prompts:

1️⃣ New Supervised Fine-tuning unit in the NLP Course https://huggingface.co/learn/nlp-course/en/chapter11/1
2️⃣New Finetuning for agents bonus module in the Agents Course https://huggingface.co/learn/agents-course/bonus-unit1/introduction

Fine-tuning will squeeze everything out of your model for how you’re using it, more than any prompt.
  • 2 replies
·
burtenshaw 
posted an update 24 days ago
view post
Post
3516
NEW COURSE! We’re cooking hard on Hugging Face courses, and it’s not just agents. The NLP course is getting the same treatment with a new chapter on Supervised Fine-Tuning!

👉 Follow to get more updates https://huggingface.co/nlp-course

The new SFT chapter will guide you through these topics:

1️⃣ Chat Templates: Master the art of structuring AI conversations for consistent and helpful responses.

2️⃣ Supervised Fine-Tuning (SFT): Learn the core techniques to adapt pre-trained models to your specific outputs.

3️⃣ Low Rank Adaptation (LoRA): Discover efficient fine-tuning methods that save memory and resources.

4️⃣ Evaluation: Measure your model's performance and ensure top-notch results.

This is the first update in a series, so follow along if you’re upskilling in AI.
  • 2 replies
·
burtenshaw 
posted an update 27 days ago
view post
Post
3591
Hey, I’m Ben and I work at Hugging Face.

Right now, I’m focusing on educational stuff and getting loads of new people to build open AI models using free and open source tools.

I’ve made a collection of some of the tools I’m building and using for teaching. Stuff like quizzes, code challenges, and certificates.

burtenshaw/tools-for-learning-ai-6797453caae193052d3638e2
  • 1 reply
·
davidberenstein1957 
posted an update 30 days ago
view post
Post
3287
🚀 Find banger tools for your smolagents!

I created the Tools gallery, which makes tools specifically developed by/for smolagents searchable and visible. This will help with:
- inspiration
- best practices
- finding cool tools

Space: davidberenstein1957/smolagents-and-tools
  • 1 reply
·
burtenshaw 
posted an update about 1 month ago
view post
Post
9142
The Hugging Face agents course is finally out!

👉 https://huggingface.co/agents-course

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?
- Messages and Special Tokens
- Understanding AI Agents through the Thought-Action-Observation Cycle
- Thought, Internal Reasoning and the Re-Act Approach
- Actions, Enabling the Agent to Engage with Its Environment
- Observe, Integrating Feedback to Reflect and Adapt
davidberenstein1957 
posted an update about 1 month ago
burtenshaw 
posted an update about 1 month ago
view post
Post
3700
SmolLM2 paper is out! 😊

😍 Why do I love it? Because it facilitates teaching and learning!

Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.

- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.

upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
  • 1 reply
·
burtenshaw 
authored a paper about 1 month ago
davidberenstein1957 
posted an update about 1 month ago