Lordog/dive-into-llms
《动手学大模型Dive into LLMs》系列编程实践教程
The leaderboard GitHub Trending was missing. Re-ranks trending repos by stars gained in the chosen window — so you see what's actually surging.
《动手学大模型Dive into LLMs》系列编程实践教程
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters
MiniCPM5: SOTA on-device LLMs, small yet powerful.
One has no future if one couldn't teach themself.
《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
Complex code hides connections, workflows, and business risks.Unvibe complex code. Trace business workflows.
[ECCV 2024] SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
📚 《Deep Agents 实战》—— LangChain 官方大使出品,基于 LangChain / LangGraph 生态,从零构建生产级 AI Agent 的完整指南
250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
A simple screen parsing tool towards pure vision based GUI agent
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
A collection of scientific methods, processes, algorithms, and systems to build stories & models.