FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a mu…

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

100 % FREE, Private (No Internet) DeepSeek’s Advanced RAG: Boost Your RAG Chatbot: Hybrid Retrieval (BM25 + FAISS) + Neural Reranking + HyDe🚀

(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

FlashMLA: Efficient MLA decoding kernels

🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"

Dify-Plus 是 Dify 的企业级增强版，集成了基于 gin-vue-admin 的管理中心，并针对企业场景进行了功能优化。本项目源于内部使用，现开源以解决行业共同痛点，欢迎社区交流与贡献。 🚀 Dify-Plus = 管理中心 + Dify 二开

MoBA: Mixture of Block Attention for Long-Context LLMs

Build & Optimize your RAG.

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Integrate the DeepSeek API into popular softwares

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3.1

Democratizing Reinforcement Learning for LLMs

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

LLM inference in C/C++

Fully open reproduction of DeepSeek-R1

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos"

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.0 - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Strea…

Introducing the Assistant Swarm. An extension to the OpenAI Node SDK to automatically delegate work to any assistant you create in OpenAi through one united interface and manager. Now you can deleg…

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, and more.

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.

The ultimate LLM/AI application development framework in Golang.

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.