Hugging Face's logo

Carbon Explorers
non-profit
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
loubnabnlย  updated a Space 20 days ago
carbon-explorers/dna-chat-test
lewtunย  submitted a paper 9 months ago
Single-minus gluon tree amplitudes are nonzero
lewtunย  submitted a paper 9 months ago
Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
View all activity
loubnabnlย 
posted an update 7 days ago
view post
Post
4,317
๐ˆ๐ง๐ญ๐ซ๐จ๐๐ฎ๐œ๐ข๐ง๐  ๐Ÿงฌ ๐…๐ข๐ง๐ž๐ƒ๐๐€: ๐ญ๐ก๐ž ๐›๐ž๐ฌ๐ญ ๐๐š๐ญ๐š๐ฌ๐ž๐ญ ๐ญ๐จ ๐ญ๐ž๐š๐œ๐ก ๐š๐ง๐ฒ ๐ฅ๐š๐ง๐ ๐ฎ๐š๐ ๐ž ๐ฆ๐จ๐๐ž๐ฅ ๐ƒ๐๐€.
Training Qwen3-14B on it produces Carbon-X, the strongest open model on DNA benchmarks, on par with GPT-6.1 Sol.

It contains:
- Midtraining: 300B+ tokens of genomic sequences, papers and web pages mixing DNA with text
- SFT: 200K samples, from variant effect prediction to sequence question answering
- RL: 98K prompts with verifiable rewards

Data, models and the full recipe are open.
HuggingFaceBio/FineDNA

Enjoy this late Halloween treat! ๐ŸŽƒ
  • 5 replies
ยท
loubnabnlย 
updated a Space 20 days ago
danaaubakirovaย 
updated a Space about 1 month ago
loubnabnlย 
published a Space about 1 month ago
lewtunย 
submitted 2 papers to Daily Papers 9 months ago
lvwerraย 
authored a paper about 1 year ago
lvwerraย 
authored a paper over 1 year ago
loubnabnlย 
authored a paper over 1 year ago
danaaubakirovaย 
posted an update over 1 year ago
danaaubakirovaย 
authored 2 papers over 1 year ago
loubnabnlย 
posted an update over 1 year ago
lewtunย 
authored 2 papers over 1 year ago
lvwerraย 
authored a paper over 1 year ago
loubnabnlย 
authored a paper over 1 year ago
lewtunย 
authored a paper over 1 year ago
lewtunย 
posted an update over 1 year ago
view post
Post
5,753
Introducing OlympicCoder: a series of open reasoning models that can solve olympiad-level programming problems ๐Ÿง‘โ€๐Ÿ’ป

- 7B open-r1/OlympicCoder-7B
- 32B open-r1/OlympicCoder-32B

We find that OlympicCoder models outperform Claude 3.7 Sonnet, as well as others over 100x larger ๐Ÿ’ช

Together with the models, we are releasing:

๐Ÿ“ŠCodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots

๐Ÿ† IOI'2024: a new benchmark of VERY hard programming problems where even frontier models struggle to match human performance open-r1/ioi

For links to the models and datasets, check out our latest progress report from Open R1: https://huggingface.co/blog/open-r1/update-3
  • 1 reply
ยท
lewtunย 
posted an update over 1 year ago
view post
Post
5,595
Introducing OpenR1-Math-220k!

open-r1/OpenR1-Math-220k

The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch ๐Ÿ’ช

Whatโ€™s new compared to existing reasoning datasets?

โ™พ Based on https://huggingface.co/datasets/AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.

๐Ÿณ 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.

๐Ÿ“€ 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.

โณ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that canโ€™t be verified with a rules-based parser)

๐Ÿ“Š We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.

๐Ÿ”Ž Read our blog post for all the nitty gritty details: https://huggingface.co/blog/open-r1/update-2