Qwen/Qwen2.5-32B
Text Generation
β’
Updated
β’
119k
β’
126
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
Organizations
thomwolf's activity
liked
a
model
1 day ago
liked
2
datasets
1 day ago
liked
a
Space
1 day ago
liked
a
dataset
4 days ago
liked
a
model
5 days ago
liked
a
dataset
6 days ago
posted
an
update
6 days ago
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: β‘οΈOlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)
It's beating Claude 3.7 on (competitive) programming βa domain Anthropic has been historically really strong atβ 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
And even we were mind-blown by the results we got with this latest model we're releasing: β‘οΈOlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)
It's beating Claude 3.7 on (competitive) programming βa domain Anthropic has been historically really strong atβ 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
liked
a
model
7 days ago
liked
a
model
11 days ago
liked
a
Space
14 days ago
liked
a
model
15 days ago
liked
2
Spaces
17 days ago
reacted to
ngxson's
post with π
17 days ago
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
Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats
| Hardware | GGUF | PyTorch | Safetensors | ONNX |
|-----------------|-----------|------------------------|--------------------------|-------|
| CPU | β
(best) | π‘ | π‘ | β
|
| GPU | β
| β
| β
| β
|
| Mobile | β
| π‘ (via executorch) | β | β
|
| Apple silicon | β
| π‘ | β
(via MLX framework) | β
|
- 1 reply
upvoted
an
article
21 days ago
Article
FastRTC: The Real-Time Communication Library for Python
β’
145
liked
a
Space
21 days ago
reacted to
m-ric's
post with π€―
21 days ago
Post
4751
We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones π₯
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.
π― 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 βAttributeTreeβ object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
π 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 π
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! π SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys π http://www.surveyx.cn/
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.
π― 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 βAttributeTreeβ object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
π 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 π
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! π SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys π http://www.surveyx.cn/