Chao Chen

📚 🔍 bRAG: Complete RAG Guide A comprehensive project showcasing RAG implementations with LangChain - from basics to advanced features like multi-query retrieval, ColBERT indexing, and RAG-Fusion. Check out this 1.7K+ starred guide 🚀 github.com/bRAGAI/bRAG-la…

最近大家说的热火朝天的MCP，到底有什么神奇功效？ 一起看看来自AI Jason的这期讲解，LLM+MCP直接起飞

微软出了一门给初学者学习的 AI 智能体课程：AI Agents for Beginners。 共 10 节课程，涵盖构建 AI 智能体的所有基础知识，旨在教授我们从零开始构建一个AI智能体。 GitHub：github.com/microsoft/ai-a… 课程内容已做了中文翻译，学习起来更加轻松，同时提供每节课所使用的示例代码，方便我们运行。

I built a Deepseek R1 RAG Reasoning Agent running locally on my computer. It's an Agentic RAG reasoning agent that can think, reason and fall back to web search if needed. 100% Opensource code with step-by-step tutorial.

大模型要回答好问题，最重要的是要先认真学习 很多优化方法都可以归结这一点，如： - Anthropic提出的Context Retrieval：anthropic.com/news/contextua… - Jina团队提出的Late Chunking：jina.ai/news/late-chun… - RAGFix团队提出的Fully-Formatted Facts：@JamesStakelum/the-end-of-ai-hallucinations-a-breakthrough-in-accuracy-for-data-engineers-e67be5cc742a" target="_blank" rel="nofollow noopener">medium.com/@JamesStakelum… 这些方法做的都是通过上下文彻底理解文中每一段、每句话、每个词。 下面这篇论文提出的先对文档造QA对，回答时召回问题和答案而不是召回原始文档chunk，原理也是类似：arxiv.org/pdf/2408.09017 到目前为止，我们看到的这些方法都还是基于当个文档的。但我们知道很多时候单看一篇文章是看不懂的，还需要主题学习。 可以预期，下一阶段的研究会发展到怎么让AI进行有效的主题学习。

🔗We open-source the training recipes and technical details in the blog post: novasky-ai.github.io/posts/sky-t1-7…. All the related code for SFT, RL, and evaluation: github.com/NovaSky-AI/Sky…. Model weights and data: huggingface.co/collections/No…. Collaborate, replicate, and innovate!

9 FREE Books from MIT for Absolute Beginners - Artificial Intelligence (AI) - Machine Learning (ML) - Deep Learning (DL) - Reinforcement Learning (RL)

浙江大学出的这个开源的书籍「大模型基础」值得一看，行文风格挺不错的，易读、严谨、有深度的大模型教材。 github.com/ZJU-LLMs/Found…

KV caching in LLMs, clearly explained (with visuals):

(1/5)🚨LLMs can now self-improve to generate better citations✅ 📝We design automatic rewards to assess citation quality 🤖Enable BoN/SimPO w/o external supervision 📈Perform close to “Claude Citations” API w/ only 8B model 📄arxiv.org/abs/2502.09604 🧑‍💻github.com/voidism/SelfCi…

这份文件真是清杀疯了！清华大学104页《DeepSeek：从入门到精通》。短短四五天，就有50万播放的视频了。资料链接：pan.quark.cn/s/4691006cb600

Github 🤖: Open-source GenBI AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, and BI. 📊 Helps you chat with data to generate SQL, charts, and reports, using your choice of LLM. It provides an open-source GenBI solution for data-driven teams seeking insights without code. What it offers: → Wren AI is an open-source GenBI AI Agent that enables data-driven teams to interact with their data through chat. → It generates Text-to-SQL queries, charts, spreadsheets, reports, and BI insights. → It supports multiple LLMs including OpenAI, Azure OpenAI, DeepSeek, Google Gemini, Vertex AI, Bedrock, Anthropic, Groq, Ollama, and Databricks. → Wren AI allows users to ask data questions in multiple languages and provides AI-generated summaries and visualizations of query results. → It features AI-powered data exploration, semantic indexing for context, and allows exporting data to Excel and Google Sheets.

MIT's "Machine Learning" lecture notes PDF: introml.mit.edu/_static/spring…

新发布的最强开源语音模型 Zonos 语音生成质量非常高，而且这次有中文 - 两种1.6B 模型，transformer 和 SSM - 用5到30秒的语音进行高保真语音克隆 - 可以调节速度，音高，音频质量和情绪 - 添加文本和音频前缀，实现更丰富的说话人匹配效果 -在 RTX 4090 显卡上运行时，实时率约为 2 倍

You can try it here in their playground and even build with their API: playground.zyphra.com/audio And as usual, available on Hugging Face: - Hybrid: huggingface.co/Zyphra/Zonos-v… - Transformer: huggingface.co/Zyphra/Zonos-v…

I recently gave a tutorial on knowledge distillation for LLMs, explaining the mathematical derivations behind the commonly used methods. Sharing the slides here given the recent interest in this topic. drive.google.com/file/d/1xMohjQ…

DeepSeek by hand is just another level, @ProfTomYeh made a lecture on it: - Multi-Head Attention - Multi-Head Latent Attention - Single Expert - Mixture of Experts - Sparse Mixture of Experts - Shared+Routed Mixture of Experts - RoPE

Nobody can explain Transformers and Self-Attention like professor Bryce... He's one of the Hidden gems of YouTube, his all videos are packed with knowledge and he teach with enthusiasm and dedication. Below 👇🏻 link in comments.

Run DeepSeek-R1 (671B) locally on @OpenWebUI - Full Guide No GPU required. Using our 1.58-bit Dynamic GGUF and llama.cpp. Tutorial: docs.openwebui.com/tutorials/inte…

A quick summary of deepseek-v3 model (there may be wrong or missing details as this is based on a quick skim) tons of respect to their engineering team...