83 133 434

Thomas Wolf PRO

thomwolf

https://thomwolf.io

AI & ML interests

NLP and open-source :-)

Recent Activity

liked a model about 4 hours ago

sesame/csm-1b

liked a model 1 day ago

Qwen/Qwen2.5-32B

liked a dataset 1 day ago

open-r1/codeforces-cots

View all activity

Organizations

thomwolf's activity

liked a model about 4 hours ago

sesame/csm-1b

Text-to-Speech • Updated 2 days ago • 7.62k • 1.2k

liked a model 1 day ago

Qwen/Qwen2.5-32B

Text Generation • Updated Sep 20, 2024 • 119k • 126

liked 2 datasets 1 day ago

open-r1/codeforces-cots

Viewer • Updated 1 day ago • 238k • 3.31k • 72

gaia-benchmark/GAIA

Updated Feb 13 • 9.06k • 269

liked a Space 1 day ago

483

Sesame CSM

🌱

Conversational speech generation

liked a dataset 4 days ago

open-r1/OpenR1-Math-220k

Viewer • Updated 29 days ago • 450k • 52.4k • 513

liked a model 5 days ago

open-r1/OlympicCoder-7B

Text Generation • Updated 1 day ago • 3.2k • 119

liked a dataset 6 days ago

facebook/natural_reasoning

Viewer • Updated 26 days ago • 1.15M • 12.5k • 423

posted an update 6 days ago

Post

2264

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: ⚡️OlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)

It's beating Claude 3.7 on (competitive) programming –a domain Anthropic has been historically really strong at– 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

liked a Space 7 days ago

smolagents LLM leaderboard

🏆

A leaderboard for LLMs powering smolagents

liked a model 7 days ago

RekaAI/reka-flash-3

Updated 5 days ago • 3.56k • 292

liked a model 11 days ago

peakji/steiner-32b-preview

Updated Oct 21, 2024 • 658 • 89

liked a Space 15 days ago

Find a leaderboard

🔍

Explore and discover all leaderboards from the HF community

liked a model 16 days ago

ecmwf/aifs-single-1.0

Graph Machine Learning • Updated 21 days ago • 477 • 18

liked a Space 17 days ago

R1-distilled leaderboard

⚡

Generate a leaderboard for open-r1 models using evaluation scores

liked a Space 18 days ago

328

AI Deadlines

⚡

Schedule tasks efficiently using AI-generated deadlines

reacted to ngxson's post with 🚀 18 days ago

Post

3082

A comprehensive matrix for which format should you use.

Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats

| Hardware        | GGUF      | PyTorch                | Safetensors              | ONNX  |
|-----------------|-----------|------------------------|--------------------------|-------|
| CPU             | ✅ (best) | 🟡                      | 🟡                       | ✅    |
| GPU             | ✅        | ✅                      | ✅                       | ✅    |
| Mobile          | ✅        | 🟡 (via executorch)     | ❌                       | ✅    |
| Apple silicon   | ✅        | 🟡                      | ✅ (via MLX framework)   | ✅    |

1 reply

upvoted an article 21 days ago

Article

FastRTC: The Real-Time Communication Library for Python

22 days ago

• 145

liked a Space 21 days ago

SmolVLM2 IPhone Waitlist

⏰