Thomas Wolf's picture

Thomas Wolf PRO

thomwolf

AI & ML interests

NLP and open-source :-)

Recent Activity

liked a model 1 day ago
Qwen/Qwen2.5-32B
liked a dataset 1 day ago
open-r1/codeforces-cots
liked a dataset 1 day ago
gaia-benchmark/GAIA
View all activity

Organizations

Hugging Face's profile picture Natural Language Processing with Transformers's profile picture BigScience Workshop's profile picture Flax Community's profile picture datablations's profile picture Training Transformers Together's profile picture BigScience Data's profile picture Evaluation datasets's profile picture HuggingFaceBR4's profile picture Godot Engine Demos's profile picture OpenAssistant's profile picture Evaluation on the Hub's profile picture HuggingFaceM4's profile picture Simulation Environments Tests and Builds's profile picture (De)fusing's profile picture HuggingFaceGECLM's profile picture CodeParrot's profile picture BigCode's profile picture Hugging Face H4's profile picture CV as NLP's profile picture Explorer of Simulate alpha's profile picture BigCode Data's profile picture Hugging Face Extreme-Scale's profile picture Hugging Face H4 Community's profile picture Blog-explorers's profile picture GAIA's profile picture Hugging Face TB Research's profile picture Hugging Face Smol Cluster's profile picture Open LLM Leaderboard's profile picture TTS Eval (OLD)'s profile picture the circle of truth - war scene's profile picture Nanotron Research's profile picture LeRobot's profile picture Journalists on Hugging Face's profile picture NewTechKids's profile picture MLX Community's profile picture Hugging Face Assignments's profile picture HuggingFaceFW's profile picture TTS AGI's profile picture Social Post Explorers's profile picture dora-rs's profile picture HuggingFaceEval's profile picture HuggingFaceFW-Dev's profile picture Hugging Face Discord Community's profile picture DataComp 's profile picture Data Agents's profile picture Hugging Face FineVideo's profile picture HuggingFace Science Team's profile picture Art's profile picture smol-explorers's profile picture Nerdy Face's profile picture Hugging Face Science's profile picture LeMaterial's profile picture open/ acc's profile picture smolagents's profile picture Hugging Face Agents Course's profile picture Open R1's profile picture Hugging Face Reasoning Course's profile picture SIMS's profile picture OpenEvals's profile picture Open Agents's profile picture

thomwolf's activity

posted an update 6 days ago
view post
Post
2255
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
reacted to ngxson's post with πŸš€ 17 days ago
view post
Post
3077
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             | βœ… (best) | 🟑                      | 🟑                       | βœ…    |
| GPU             | βœ…        | βœ…                      | βœ…                       | βœ…    |
| Mobile          | βœ…        | 🟑 (via executorch)     | ❌                       | βœ…    |
| Apple silicon   | βœ…        | 🟑                      | βœ… (via MLX framework)   | βœ…    |
  • 1 reply
Β·
upvoted an article 21 days ago
view article
Article

FastRTC: The Real-Time Communication Library for Python

β€’ 145
reacted to m-ric's post with 🀯 21 days ago
view post
Post
4751
We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones πŸ”₯

Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.

To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.

🎯 For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an β€œAttributeTree” object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!

πŸ“ For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.

As a result, their system outperforms previous approaches by far!

As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 πŸ†

I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! πŸ‘‰ SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys πŸ‘‰ http://www.surveyx.cn/