OpenBMB's Projects
🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation
Model Compression for Big Models
Efficient Inference for Big Models
BMInf demos.
A List of Big Models
A collection of phenomenons observed during the scaling of big foundation models, which may be developed into consensus, principles, or laws in the future
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
Efficient Training (including pre-training and fine-tuning) for Big Models
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
百亿参数的中英文双语基座大模型
Live Training for Open-source Big Models
Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding
Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718
An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
Port of Facebook's LLaMA model in C/C++
MiniCPM on iOS.
MiniCPM-2B: An end-side LLM outperforming Llama2-13B.
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
MiniCPM on Android platform.
A Toolkit for Running On-device Large Language Models (LLMs) in APP
Efficient, Low-Resource, Distributed transformer implementation based on BMTrain
Get up and running with Llama 3, Mistral, Gemma, and other large language models.
[ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.