LLM 模型排行

Composable Python framework for LLM agent workflows focused on simplicity and developer experience. We ❤️ OSS.

A live translation plugin for Potplayer, native ollama and custom api supported

Use Large Language Models like OpenAI's GPT-3.5 for data annotation and model enhancement. This framework combines human expertise with LLMs, employs Iterative Active Learning for continuous improvement, and integrates CleanLab (Confident Learning) to ensure high-quality datasets and better model performance

从零开始学大模型Transformer、GPT2、BERT pre-training and fine-tuning from scratch

🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into LLMs via sparse retrieval PEFT without increasing inference FLOPs / DeepSeek Engram 架构的非官方实现。通过参数高效微调 (PEFT) 为大语言模型注入超大规模条件记忆，支持稀疏更新且不增加推理开销。

A Free, Open Source MCP server for dynamic custom persona management with public a GitHub collection of personas, skills, templates, and other elements for AI models.

Tree prompting: easy-to-use scikit-learn interface for improved prompting.

Persona Control Language (PCL)

Modular Rust transformer/LLM library using Candle

A guide about how to use GPTQ models with langchain

dingospeed is a self-hosted huggingface mirror service

AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).

An efficient multi-modal instruction-following data synthesis tool and the official implementation of Oasis https://arxiv.org/abs/2503.08741.

🐌 A curated roadmap based on my 6 years of experience form zero to become a skilled AI Speech Engineer. This roadmap covers everything from fundamentals to cutting-edge research trends in the speech domain.

🐍 Personal AI agent in pure Python — OpenClaw reimagined. Memory, RAG, skills marketplace, cron, voice. Telegram/Discord/WhatsApp/Web. Works with DeepSeek, Claude, Gemini, Kimi, GLM, Ollama.

💻 context-aware AI coding assistant for the terminal to assist with code development, explanation, refactoring, review, debugging, and chat; compatible with both local and online language models.

Web UI for working with large language models

The minimal AI agent engine

Self-hosted subtitle manager & LLM translator for anime and media — *arr-compatible, fully local

Plugin for QGIS interaction using LLM. Enables geospatial analysis and data processing through natural language commands.