An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
- agentic
- rlhf
- rlvr
79,841 visible repositories in the index
1,417–1,440 of 4,033 · Most stars
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
A high-performance distributed training framework for Reinforcement Learning
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
oletools - python tools to analyze MS OLE2 files (Structured Storage, Compound File Binary Format) and MS Office documents, for malware analysis, forensics and debugging.
Devon: An open-source pair programmer
🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...
Patch PE, ELF, Mach-O binaries with shellcode new version in development, available only to sponsors
Ghost Framework is an Android post-exploitation framework that exploits the Android Debug Bridge to remotely access an Android device.
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
AI reads books: Page-by-Page PDF Knowledge Extractor & Summarizer. script performs an intelligent page-by-page analysis of PDF books, methodically extracting knowledge points and generating progressive summaries at specified intervals
0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch
Auto-register & manage accounts for ChatGPT, Cursor, Kiro, Grok, Windsurf, Trae & 13+ AI platforms · Protocol/browser dual-mode · Plugin-based · One-click Mac/Windows desktop app
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.
Entropy Based Sampling and Parallel CoT Decoding
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
Updog is a replacement for Python's SimpleHTTPServer. It allows uploading and downloading via HTTP/S, can set ad hoc SSL certificates and use http basic auth.
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
A minimalist command line knowledge base manager
Jiagu深度学习自然语言处理工具 知识图谱关系抽取 中文分词 词性标注 命名实体识别 情感分析 新词发现 关键词 文本摘要 文本聚类
Easy to Use, 100% Open Source Learning Management System
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
Web app for Scrapyd cluster management, Scrapy log analysis & visualization, Auto packaging, Timer tasks, Monitor & Alert, and Mobile UI. Docs 文档 :point_right:
Official implementation of Character Region Awareness for Text Detection (CRAFT)
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]