Python 排行榜

[EMNLP22] Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models

PLMFit platform for TL on PLMs

DomainUp turns a simple YAML into a full reverse-proxy with Let’s Encrypt for Docker — perfect for self-hosters & DevOps.

A Streamlit-powered machine learning playground that automatically detects classification or regression tasks, builds pipelines with preprocessing, trains models interactively, and visualizes metrics using Plotly. Backward-compatible, fully responsive, and deployable on Streamlit Cloud or Docker.

Using langchain framework created some useful Ai applications.

基于YOLOV8的人脸检测模型，从huggingface上面下载，通过gradio进行部署，实现输入图片的URL或者上传图片，模型检测出所有的人脸，并返回位置信息

ContextQA - The open-source tool for data-driven conversations

Fine-tune the newly released Llama-3.2 lightweight models.

AI orbit monitor — papers, models, benchmarks, company news in one dashboard. 40+ sources, LMArena leaderboard, local LLM summary.

Access different AI models in a one place

A modular framework for building and deploying Retrieval-Augmented Generation (RAG) systems with built-in evaluation and monitoring.

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

This repository provides core code for managing large volumes of video footage, enabling content understanding, automatic tagging, and vector database storage. It integrates multimodal models and LLMs for accurate descriptions and semantic search. A web interface allows visualization.

Ensemble Integration: a customizable pipeline for generating multi-modal, heterogeneous ensembles

✨ Official code for our paper: "Uncertainty-o: One Model-agnostic Framework for Unveiling Epistemic Uncertainty in Large Multimodal Models".

FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain (EMNLP 2025)

🦉 Generate quizzes from video application

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Portable offline AI audio studio with web UI & local API – XTTS, Fish Speech, Kokoro, Stable Audio, ACE-Step, voice cloning, music gen (no install)

A python toolbox for analyzing and plotting free recall data