DolbyUUU / Logic-RL-Lite
Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".
☆81Updated 2 weeks ago
Alternatives and similar repositories for Logic-RL-Lite:
Users that are interested in Logic-RL-Lite are comparing it to the libraries listed below
- 枫短链系统 基于SpringCloud的SaaS平台 高并发、高可用、高性能的系统☆102Updated last week
- LotteryMaster - Let LLM be your lucky charm!☆143Updated this week
- Cosmos-AI is an innovative solution that leverages state-of-the-art LLMs and artificial intelligence algorithms for intelligent task deco…☆68Updated 3 weeks ago
- 学习笔记☆36Updated this week
- Re-movery☆510Updated 2 weeks ago
- ☆125Updated 3 months ago
- ☆483Updated 3 months ago
- Performance optimization for Centris software☆530Updated 2 weeks ago
- 互动媒体课程大作业，基于p5.js的动态艺术海报.☆121Updated 6 months ago
- 🔥KGminerproxy 原创正版，功能强大，全币种高性能（固定作者开发费用抽水千分之1.8,纯转发不抽水），专业的数字货币中转加密管理工具。专业的矿场运维，提升矿场利润的必备助手。☆96Updated 2 weeks ago
- ☆134Updated 4 months ago
- 一种基于栈式虚拟机的类c 语言编译器。This project has moved from https://sourceforge.net/projects/msct/. C-SVM: A Compiler for a C-Like Language Based on a…☆111Updated 8 months ago
- A comprehensive toolkit for Minecraft server plugin development, supporting Spigot/Paper/Folia platforms.☆440Updated this week
- Efficient Steganalysis System☆129Updated 3 months ago
- A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Pape…☆114Updated 4 months ago
- An extension for Visual Studio Code that integrates the power of OpenAI's GPT models into VSCode.☆165Updated last year
- ☆307Updated last year
- 如何低价充值 ChatGPT-Plus☆57Updated 2 months ago
- OD-FinLLM is a refined model derived from the LLaMA series, with specific enhancements for Chinese financial knowledge. This model is bui…☆273Updated 6 months ago
- Nestjs抽奖系统 Nodejs抽奖系统 责任链抽奖策略 抉择树抽奖策略☆18Updated 3 months ago
- Creating a simple Go module for Backend Teams' DevOps Workflow☆106Updated 3 months ago
- A toy system for generating event timelines from social media data, specifically focusing on the Olympic Game medalist events.☆6Updated 3 months ago
- Message queue based on the AMQP model implemented using cpp code☆341Updated this week
- Kafka Web UI By LCC 是一个专为简化Apache Kafka集群管理和操作而设计的图形化用户界面（GUI）。该项目旨在为开发者、运维人员和数据科学家提供一个直观且易用的平台，以进行Kafka主题（Topic）管理、消息生产和消费、以及集群监控等任务。通过该…☆135Updated 2 weeks ago
- Object_Detection_Dataset_Conversion☆129Updated 3 months ago
- A physics-guided hierarchical deep network (PhyRes-LSTM) framework, which integrates external knowledge with deep neural networks to guid…☆16Updated 6 months ago
- ☆124Updated this week
- 💻 CLI News 是一个命令行新闻工具，从 RSS feed 获取新闻并完成翻译，在摸鱼的时候方便地浏览新闻内容☆45Updated 2 months ago
- ☆114Updated this week
- Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.☆34Updated 2 weeks ago