Python 排行榜

[ACL 2026] CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy

Low-Cost Cross-Domain Web Structured Information Extraction using specialized LoRA adapters.

📘 Taiwan-LLM Tutor: Large Language Models for Taiwanese Secondary Education

LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)

Official Implementation of "Fine-Tuning is Fine, if Calibrated.", NeurIPS 2024

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

一个开箱即用、用于二分类任务的大语言微调模型框架。An out-of-the-box LLM fine-tuning framework for medical binary classification.

🚀 Pre-trained YOLO for Document Layout Analysis. Instantly find text 📄, tables 📊, and figures 🖼️. Fast, accurate, and ready to use! ✨

A Deep Learning project that uses Diffusion transformers (DiT) to generate Grand Theft Auto V driving footage

Save any web url as zip ( image + assets + html + css + js )

Mono repo with support for HuggingFace packages including diffusers, embeddings, transformers and grouding dino

✌ CLoG: Benchmarking Continual Learning of Image Generation Models

Simple RAG system powered by Milvus.

Minimal local-first multimodal RAG library powered by SQLite + sqlite-vec.

The documentation repo for Weaviate Database, Cloud, Agents and much more!

Project Context Clues aim to vectorize CyberOps recon and threat intel data for AI driven systems.

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement

Agent-based Multimodal Urban Moblity Simulator resulting from the ERC MAGnUM project

[IEEE T-BIOM] FaceXBench: Evaluating Multimodal LLMs on Face Understanding

小红书图文笔记 Agent Skill，支持看图理解、主动提问、智能选题、实时热梗搜索、标题正文、标签评论钩子和风险检查。