StarRing2022 / R1-NatureLinks
最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。
☆44Updated 5 months ago
Alternatives and similar repositories for R1-Nature
Users that are interested in R1-Nature are comparing it to the libraries listed below
Sorting:
- ☆94Updated 7 months ago
- The code for paper: Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search☆51Updated 3 weeks ago
- Official implementation for "ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization"☆79Updated 2 months ago
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆57Updated 8 months ago
- Qwen DianJin: LLMs for the Financial Industry by Alibaba Cloud☆119Updated 2 months ago
- open-o1: Using GPT-4o with CoT to Create o1-like Reasoning Chains☆116Updated 7 months ago
- XVERSE-MoE-A36B: A multilingual large language model developed by XVERSE Technology Inc.☆39Updated 10 months ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆33Updated last year
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆110Updated 2 months ago
- GLM Series Edge Models☆144Updated last month
- ☆36Updated 10 months ago
- Unleashing the Power of Cognitive Dynamics on Large Language Models☆62Updated 10 months ago
- Search, organize, discover anything!☆48Updated last year
- Scaling Preference Data Curation via Human-AI Synergy☆94Updated last month
- Deep Reasoning Translation (DRT) Project☆227Updated 2 months ago
- ☆76Updated 3 weeks ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆40Updated last year
- DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking☆48Updated 4 months ago
- (ICLR 2025) AgentRefine: Enhancing Agent Generalization through Refinement Tuning☆18Updated 5 months ago
- Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"☆136Updated 2 months ago
- ☆21Updated last week
- 一个面向多模态大模型训练的智能数据集构建与评估平台☆86Updated this week
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆98Updated this week
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆125Updated 8 months ago
- ☆287Updated 2 months ago
- ☆50Updated last month
- ☆91Updated last year
- ☆173Updated 5 months ago
- Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The infere…☆22Updated 2 months ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 10 months ago