Hugging Face's logo

Training Transformers Together

non-profit
https://training-transformers-together.github.io
training-transformers-together
Activity Feed

AI & ML interests

Training DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)

Recent Activity

thomwolfย  authored a paper about 1 month ago
SmolVLM: Redefining small and efficient multimodal models
thomwolfย  authored a paper about 1 month ago
YourBench: Easy Custom Evaluation Sets for Everyone
osansevieroย  authored a paper about 2 months ago
Gemma 3 Technical Report
View all activity

training-transformers-together's activity

julien-cย 
posted an update 18 days ago
view post
Post
4181
BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript ๐Ÿ”ฅ

I spent the last few weeks working on this, so I hope you will like it.

I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.

It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.

But while doing that, came my second realization:

Once you have a MCP Client, an Agent is literally just a while loop on top of it. ๐Ÿคฏ

โžก๏ธ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents
  • 1 reply
ยท
thomwolfย 
posted an update 29 days ago
view post
Post
4780
If you've followed the progress of robotics in the past 18 months, you've likely noticed how robotics is increasingly becoming the next frontier that AI will unlock.

At Hugging Faceโ€”in robotics and across all AI fieldsโ€”we believe in a future where AI and robots are open-source, transparent, and affordable; community-built and safe; hackable and fun. We've had so much mutual understanding and passion working with the Pollen Robotics team over the past year that we decided to join forces!

You can already find our open-source humanoid robot platform Reachy 2 on the Pollen website and the Pollen community and people here on the hub at pollen-robotics

We're so excited to build and share more open-source robots with the world in the coming months!
  • 1 reply
ยท
thomwolfย 
authored 2 papers about 1 month ago
awacke1ย 
posted an update about 1 month ago
view post
Post
1655
AI Vision & SFT Titans ๐ŸŒŸ Turns PDFs into text, snaps pics, and births AI art.

https://huggingface.co/spaces/awacke1/TorchTransformers-Diffusion-CV-SFT

1. OCR a grocery list or train a titan while sipping coffee? โ˜•
2. Camera Snap ๐Ÿ“ท: Capture lifeโ€™s chaosโ€”your catโ€™s face or that weird receipt. Proof youโ€™re a spy!
3. OCR ๐Ÿ”: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen ๐ŸŽจ: Prompt โ€œneon superhero meโ€
5. PDF ๐Ÿ“„: Double-page OCR Single-page sniping

Build Titans ๐ŸŒฑ: Train tiny AI models. ๐Ÿ’ชCharacters๐Ÿง‘โ€๐ŸŽจ: Craft quirky heroes.
๐ŸŽฅ
thomwolfย 
posted an update about 1 month ago
view post
Post
3389
The new DeepSite space is really insane for vibe-coders
enzostvs/deepsite

With the wave of vibe-coding-optimized LLMs like the latest open-source DeepSeek model (version V3-0324), you can basically prompt out-of-the-box and create any app and game in one-shot.

It feels so powerful to me, no more complex framework or under-the-hood prompt engineering to have a working text-to-app tool.

AI is eating the world and *open-source* AI is eating AI itself!

PS: and even more meta is that the DeepSite app and DeepSeek model are both fully open-source code => time to start recursively improve?

PPS: you still need some inference hosting unless you're running the 600B param model at home, so check the very nice list of HF Inference Providers for this model: deepseek-ai/DeepSeek-V3-0324
  • 1 reply
ยท
osansevieroย 
authored a paper about 2 months ago
thomwolfย 
posted an update 2 months ago
view post
Post
2885
We've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1.

And even we were mind-blown by the results we got with this latest model we're releasing: โšก๏ธOlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)

It's beating Claude 3.7 on (competitive) programming โ€“a domain Anthropic has been historically really strong atโ€“ and it's getting close to o1-mini/R1 on olympiad level coding with just 7B parameters!

And the best part is that we're open-sourcing all about its training dataset, the new IOI benchmark, and more in our Open-R1 progress report #3: https://huggingface.co/blog/open-r1/update-3

Datasets are are releasing:
- open-r1/codeforces
- open-r1/codeforces-cots
- open-r1/ioi
- open-r1/ioi-test-cases
- open-r1/ioi-sample-solutions
- open-r1/ioi-cots
- open-r1/ioi-2024-model-solutions
julien-cย 
posted an update 2 months ago
view post
Post
3775
Important notice ๐Ÿšจ

For Inference Providers who have built support for our Billing API (currently: Fal, Novita, HF-Inference โ€“ with more coming soon), we've started enabling Pay as you go (=PAYG)

What this means is that you can use those Inference Providers beyond the free included credits, and they're charged to your HF account.

You can see it on this view: any provider that does not have a "Billing disabled" badge, is PAYG-compatible.
ยท
awacke1ย 
posted an update 2 months ago
awacke1ย 
posted an update 3 months ago
view post
Post
2484
๐Ÿš€ Blast into the future with ZaxxonGalaxian โ€“ a thrilling 3D action game where you navigate epic battles through towering 3D cityscapes! Face off against relentless swarm bots, climb the leaderboard, and dominate the skies. awacke1/ZaxxoGalaxian
thomwolfย 
authored a paper 3 months ago
mryabย 
authored a paper 4 months ago
thomwolfย 
authored a paper 4 months ago
awacke1ย 
posted an update 4 months ago
view post
Post
3206
Deep Research Evaluator was asked:
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.

1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]


To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.

1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.
awacke1ย 
posted an update 4 months ago
julien-cย 
posted an update 5 months ago
view post
Post
10704
After some heated discussion ๐Ÿ”ฅ, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co/docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community ๐Ÿ”ฅ

cc: @reach-vb @pierric @victor and the HF team
ยท
thomwolfย 
posted an update 5 months ago
view post
Post
6164
We are proud to announce HuggingFaceFW/fineweb-2: A sparkling update to HuggingFaceFW/fineweb with 1000s of ๐Ÿ—ฃ๏ธlanguages.

We applied the same data-driven approach that led to SOTA English performance in๐Ÿท FineWeb to thousands of languages.

๐Ÿฅ‚ FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.

The dataset is released under the permissive ๐Ÿ“œ ODC-By 1.0 license, and the ๐Ÿ’ป code to reproduce it and our evaluations is public.

We will very soon announce a big community project, and are working on a ๐Ÿ“ blogpost walking you through the entire dataset creation process. Stay tuned!

In the mean time come ask us question on our chat place: HuggingFaceFW/discussion

H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
  • 2 replies
ยท
thomwolfย 
posted an update 5 months ago
thomwolfย 
posted an update 5 months ago