超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1
☆34Apr 5, 2025Updated last year
Alternatives and similar repositories for 24-Game-Reasoning
Users that are interested in 24-Game-Reasoning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario☆32Oct 5, 2025Updated 8 months ago
- ☆68Oct 27, 2025Updated 7 months ago
- ☆32Feb 28, 2026Updated 3 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆27Dec 23, 2024Updated last year
- The official repository of the Omni-MATH benchmark.☆94Dec 22, 2024Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [ISSTA 2025] A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing☆13Feb 9, 2025Updated last year
- Collection of python scripts for interfacing with paraview for the Chair for Electromagnetic Theory at Saarland University☆14Sep 3, 2025Updated 9 months ago
- ☆12Feb 21, 2020Updated 6 years ago
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆32Oct 9, 2025Updated 8 months ago
- The repository implements the paper "Learning Graph Quantized Tokenizers for Transformers".☆31Apr 2, 2025Updated last year
- AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence☆10Mar 2, 2025Updated last year
- 小红书爬虫☆10May 26, 2023Updated 3 years ago
- 日常脚本☆15Jun 2, 2026Updated 2 weeks ago
- Code and Data for EMNLP 2023 Paper "MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Langu…☆14Apr 7, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- diagnosis_zero, R1 Zero reproduce on disease diagnosis☆33Jul 24, 2025Updated 10 months ago
- The official implementation of "Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding"☆22Jun 26, 2025Updated 11 months ago
- ☆22Jan 3, 2026Updated 5 months ago
- [EMNLP 2024] FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents☆22Jan 6, 2025Updated last year
- ☆13Nov 23, 2022Updated 3 years ago
- [ICLR 2023] This repository contains the official Pytorch implementation for the paper "Transformer-based model for symbolic regression v…☆29Jul 2, 2025Updated 11 months ago
- [ICLR 2025] No Preference Left Behind: Group Distributional Preference Optimization☆16Apr 21, 2025Updated last year
- ☆10May 28, 2023Updated 3 years ago
- Code of EMNLP 2025 paper 'UltraIF: Advancing Instruction Following from the Wild'.☆21Apr 3, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- This repository contains the code and dataset for activity recognition using mmWave radar sensors. The dataset was collected in two diffe…☆23Jun 16, 2023Updated 3 years ago
- 基于一阶泰勒展开的点堆中子动力学方程求解程序☆16Mar 18, 2019Updated 7 years ago
- ☆25Apr 3, 2024Updated 2 years ago
- [ACL 2024] REANO: Optimising Retrieval-Augmented Reader Models through Knowledge Graph Generation☆12Sep 4, 2024Updated last year
- ☆34Apr 1, 2025Updated last year
- Event Modeling Risk Assessment using Linked Diagrams (EMRALD) is a software tool developed at INL for researching the capabilities of dyn…☆29Updated this week
- A miniaturized version of the Kimi-K2 model optimized for deployment on single H100 GPUs.☆35Jul 16, 2025Updated 11 months ago
- 可视化量化机器学习论文关系的知识图谱系统☆25Dec 9, 2025Updated 6 months ago
- ☆28Oct 6, 2021Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code of "Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model"☆13Jul 8, 2025Updated 11 months ago
- DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models (NeurIPS 2024 D&B Track)☆24Mar 6, 2025Updated last year
- ☆15Nov 29, 2023Updated 2 years ago
- On Policy Distillation Build on top of Verl☆76May 25, 2026Updated 3 weeks ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆28Sep 10, 2024Updated last year
- [CVPR 2024] Targeted Representation Alignment for Open-World Semi-Supervised Learning☆14Sep 23, 2024Updated last year
- Waffer-thin FlaskGPT on Vercel.☆12Jun 1, 2023Updated 3 years ago