Stars
仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
An alternative BEAM implementation, designed for WebAssembly
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Question and Answer based on Anything.
Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)
A efficient and effective few-shot NL2SQL method on GPT-4.
中文nlp解决方案(大模型、数据、模型、训练、推理)
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理、编程语言和数据结构。
CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理和 C++基础四大块，一起努力向offers发起冲击！
文本相似度，语义向量，文本向量，text-similarity，similarity, sentence-similarity，BERT，SimCSE，BERT-Whitening，Sentence-BERT, PromCSE, SBERT
Secrets of RLHF in Large Language Models Part I: PPO
MindSpore online courses: Step into LLM
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Example models using DeepSpeed