OpenBMB

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Parsing-free RAG supported by VLMs

An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation

An End-to-End Infrastructure for Training and Evaluating Various LLM Agents

A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation Models

CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and quantization.

GitHub repository OpenBMB/RAGEval; metadata recovered from GitHub Search API.

An open platform for enhancing the capability of LLMs in workflow orchestration.

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines Topics: deepseek, demo, easy, embedding, flask, gpt, huggingface-transformers, llm, mcp, multimodal, openai, qwen.

This is the code repo for the paper "RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards".

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation Topics: agent, ai, gpt, gpt-4, llm.

An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity. Topics: agent, ai, genai, ioa, llm.

ArcLight: A Lightweight LLM Inference Framework