Stars
Toolkit for linearizing PDFs for LLM datasets/training
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调(全参数/Lora)、部署国内外开源大模型(LLM)/多模态大模型(MLLM)教程
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
DeepEP: an efficient expert-parallel communication library
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Integrate the DeepSeek API into popular softwares
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
Automate the process of making money online.
Bringing BERT into modernity via both architecture changes and scaling
Medical o1, Towards medical complex reasoning with LLMs
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
📄 A curated list of awesome .cursorrules files
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
Awesome-RAG: Collect typical RAG papers and systems.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
整理目前开源的最优表格识别模型,完善前后处理,模型转换为ONNX Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
一个把长文转款成摘要卡片/图片的前端应用,使用 Kimi 对文章进行结构化总结。
🧠 世界上覆盖最全的优秀Qwen提示语大全,欢迎贡献你的提示词。🧠 The most comprehensive collection of excellent Qwen prompts in the world. Feel free to contribute your own prompts!
🧑🚀 全世界最好的LLM资料总结(数据处理、模型训练、模型部署、o1 模型、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具,将PDF转换成Markdown和JSON格式。
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.