Kimina-Prover-RL
•
12
Project-Numina
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
Articles
LxYxvv
updated
2
datasets
about 1 month ago
ranWang
updated
a
dataset
about 1 month ago
liyongsea
published
a
dataset
about 1 month ago
liyongsea
published
a
dataset
about 2 months ago
thibautbar
authored
a
paper
5 months ago
HaimingW
authored
7
papers
7 months ago
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
Paper
•
2310.10180
•
Published
•
1
FIMO: A Challenge Formal Dataset for Automated Theorem Proving
Paper
•
2309.04295
•
Published
•
1
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
Paper
•
2402.08957
•
Published
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
Paper
•
2406.14408
•
Published
Process-Driven Autoformalization in Lean 4
Paper
•
2406.01940
•
Published
DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
Paper
•
2310.02954
•
Published
Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
Paper
•
2504.11354
•
Published
•
6
desaxce
authored
a
paper
7 months ago
lewtun
authored
a
paper
7 months ago
spolu
authored
a
paper
7 months ago
rookiemango
authored
a
paper
8 months ago
lewtun
authored
a
paper
8 months ago
lewtun
authored
a
paper
9 months ago
Post
4028
Introducing OlympicCoder: a series of open reasoning models that can solve olympiad-level programming problems 🧑💻
- 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 💪
Together with the models, we are releasing:
📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots
🏆 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
- 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 💪
Together with the models, we are releasing:
📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots
🏆 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