OpenBMB

Parsing-free RAG supported by VLMs

Efficient Training (including pre-training and fine-tuning) for Big Models

AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

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

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

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

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

Task-oriented AI Agent productivity platform

Live Training for Open-source Big Models

Efficient Inference for Big Models

MiniCPM5: SOTA on-device LLMs, small yet powerful.

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

Enterprise Digital Employee Platform

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

An Autonomous LLM Agent for Complex Task Solving