DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Repository Index
106,102 visible repositories in the index
97–120 of 271 · Most stars
Neo-reGeorg is a project that seeks to aggressively refactor reGeorg
- regeorg
- neoreg
- reduh
- socks-proxy
Graphical client for the Soulseek peer-to-peer network
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
- deepseek-r1
- llm
- r1v
- reasoning
DeepTeam is a framework to red team LLMs and AI agents.
- llm-guardrails
- llm-red-teaming
- llm-safety
- python
[OBSOLETE - see readme] A tool for creating GIF screencasts of a terminal, with key presses overlaid.
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
- 3d-generation
- aigc
- diffusion-models
- generative-model
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Official SeedVR2 Video Upscaler for ComfyUI
- ai
- comfyui
- comfyui-nodes
- upscaler
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
TokenSpeed is a speed-of-light LLM inference engine.
Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨
This is the development home of the workflow management system Snakemake. For general information, see
- snakemake
- reproducibility
- workflow-management
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Warning: This project does not have any current developer. See bellow.
High-speed downloader for multiple platforms
- api
- bark
- bilibili
- douyin
🎙️ A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
Apple MLX native implementations of state-of-the-art generative image & video models
- ai
- apple-silicon
- diffusers
- flux
cubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台,算法全链路流程,多租户,算力租赁平台,token中转,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务,VGPU虚拟化,云边端协同,边缘计算,自动化标注平台,deepseek等大模型sft微调/奖励模型/强化学习训练,vllm/ollama/mindie大模型多机推理,私有知识库llmops智能体,AI模型市场,支持国产异构算力调度,昇腾/寒武纪/海光/摩尔/沐曦等,支持ib/roce/RDMA,信创支持
Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral, DeepSeek, Poe or OpenRouter. Preserves formatting. Resumes where you left off. No file size limits.
- llm
- ollama
- translation
- localization-tool
CMS Detection and Exploitation suite - Scan WordPress, Joomla, Drupal and over 180 other CMSs
- cms
- content-management-system
- cms-framework
- wordpress
invisible playwright: Playwright that anti-bots cannot see, so no captchas: same API, anti-detect stealth headless Firefox, undetected fingerprint, bypass bot detection, Python web scraping and browser automation.
- datadome
- perimeterx
- akamai
- antidetect-browser
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.