Data Is Better Together Contributor

community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

data-is-better-together-contributor's activity

fdaudens 
posted an update about 4 hours ago
view post
Post
107
🤯 Gemma 3's image analysis blew me away!

Tested 2 ways to extract airplane registration numbers from photos with 12B model:

1️⃣ Gradio app w/API link (underrated feature IMO) + ZeroGPU infra on Hugging Face in Google Colab. Fast & free.

2️⃣ LMStudio + local processing (100% private). Running this powerhouse on a MacBook w/16GB RAM is wild! 🚀

Colab: https://colab.research.google.com/drive/1YmmaP0IDEu98CLDppAAK9kbQZ7lFnLZ1?usp=sharing
burtenshaw 
posted an update about 11 hours ago
view post
Post
325
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 17 hours ago
view post
Post
700
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
·
AtAndDev 
posted an update 1 day ago
view post
Post
881
Gemma 3 seems to be really good at human preference. Just waiting for ppl to see it.
prithivMLmods 
posted an update 1 day ago
view post
Post
1483
Gemma-3-4B : Image and Video Inference 🖼️🎥

🧤Space: prithivMLmods/Imagineo-Chat

@gemma3-4b : {Tag + Space_+ 'prompt'}
@gemma3-4b-video : {Tag + Space_+ 'prompt'}
By default, it runs: prithivMLmods/Qwen2-VL-OCR-2B-Instruct

Additionally, I have also tested Aya-Vision 8B vs Custom Qwen2-VL-OCR for OCR with test case samples on messy handwriting for experimental purposes to optimize edge device VLMs for Optical Character Recognition.

📜Read the blog here: https://huggingface.co/blog/prithivMLmods/aya-vision-vs-qwen2vl-ocr-2b
  • 1 reply
·
fdaudens 
posted an update 1 day ago
view post
Post
540
Ever wanted 45 min with one of AI’s most fascinating minds? Was with @thomwolf at HumanX Vegas. Sharing my notes of his Q&A with the press—completely changed how I think about AI’s future:

1️⃣ The next wave of successful AI companies won’t be defined by who has the best model but by who builds the most useful real-world solutions. "We all have engines in our cars, but that’s rarely the only reason we buy one. We expect it to work well, and that’s enough. LLMs will be the same."

2️⃣ Big players are pivoting: "Closed-source companies—OpenAI being the first—have largely shifted from LLM announcements to product announcements."

3️⃣ Open source is changing everything: "DeepSeek was open source AI’s ChatGPT moment. Basically, everyone outside the bubble realized you can get a model for free—and it’s just as good as the paid ones."

4️⃣ Product innovation is being democratized: Take Manus, for example—they built a product on top of Anthropic’s models that’s "actually better than Anthropic’s own product for now, in terms of agents." This proves that anyone can build great products with existing models.

We’re entering a "multi-LLM world," where models are becoming commoditized, and all the tools to build are readily available—just look at the flurry of daily new releases on Hugging Face.

Thom's comparison to the internet era is spot-on: "In the beginning you made a lot of money by making websites... but nowadays the huge internet companies are not the companies that built websites. Like Airbnb, Uber, Facebook, they just use the internet as a medium to make something for real life use cases."

Love to hear your thoughts on this shift!
  • 1 reply
·
burtenshaw 
posted an update 1 day ago
view post
Post
1025
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
·
not-lain 
posted an update 1 day ago
fdaudens 
posted an update 2 days ago
view post
Post
1650
🔥The Open R1 team just dropped OlympicCoder and it's wild:

- 7B model outperforms Claude 3.7 Sonnet on IOI benchmark (yes, 7B!!)
- 32B crushes all open-weight models tested, even those 100x larger 🤯

Open-sourcing the future of code reasoning! 🚀

Check it out https://huggingface.co/blog/open-r1/update-3
prithivMLmods 
posted an update 2 days ago
fdaudens 
posted an update 4 days ago
view post
Post
5649
Honored to be named among their 12 pioneers and power players in the news industry in the 2025 Tech Trends Report from Future Today Strategy Group.

Incredible group to be part of - each person is doing groundbreaking work at the intersection of AI and journalism. Worth following them all: they're consistently sharing practical insights on building the future of news.

Take the time to read this report, it's packed with insights as always. The news & information section's #1 insight hits hard: "The most substantive economic impact of AI to date has been licensing payouts for a handful of big publishers. The competition will start shifting in the year ahead to separate AI 'haves' that have positioned themselves to grow from the 'have-nots.'"

This AI-driven divide is something I've been really concerned about. Now is the time to build more than ever!

👉 Full report here: https://ftsg.com/wp-content/uploads/2025/03/FTSG_2025_TR_FINAL_LINKED.pdf
  • 2 replies
·
fdaudens 
posted an update 7 days ago
view post
Post
4038
AI will bring us "a country of yes-men on servers" instead of one of "Einsteins sitting in a data center" if we continue on current trends.

Must-read by @thomwolf deflating overblown AI promises and explaining what real scientific breakthroughs require.

https://thomwolf.io/blog/scientific-ai.html
  • 2 replies
·
davidberenstein1957 
posted an update 8 days ago
ZennyKenny 
posted an update 8 days ago
view post
Post
482
It took me a while, but I've finally got it working: ZennyKenny/note-to-text

Using a Meta LLaMa checkpoint from Unsloth and some help from the HF community, you can capture handwritten notes and convert them into digital format in just a few second.

Really exciting times for AI builders on Hugging Face.
  • 2 replies
·
prithivMLmods 
posted an update 8 days ago
burtenshaw 
posted an update 8 days ago
view post
Post
3539
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 
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