The official gpt4free repository | various collection of powerful language models | o4, o3 and deepseek r1, gpt-4.1, gemini 2.5

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993886460 (Beware of fake account)

🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。

SGLang is a fast serving framework for large language models and vision language models.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4v, Phi4, ...) (AAAI 2025).

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Solve Visual Understanding with Reinforced VLMs

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI (Kunlun Inc.), specializing in vision-language reasoning.

🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案，包含从训练到推理的完整代码和脚本，以及实践中积累一些经验和结论。)

Official code for paper "Group-in-Group Policy Optimization for LLM Agent Training". This codebase supports training LLM/VLM agents via RL.

Explore the Multimodal “Aha Moment” on 2B Model

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

AI-powered assistant to help you with your daily tasks, powered by Llama 3, DeepSeek R1, and many more models on HuggingFace.

ReasonFlux Series - A family of LLM post-training algorithms focusing on data selection, reinforcement learning, and inference scaling

✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Conversational voice AI agents