OpenBMB (Open Lab for Big Model Base) aims to build foundation models and systems towards AGI.
78
Repository pubblici
146.983
Stelle totali
6633
Follower
OpenBMB è un'organizzazione attiva su GitHub, focalizzata sulla costruzione di modelli fondamentali e sistemi per il raggiungimento dell'AGI. Tra i linguaggi principali utilizzati ci sono Python, JavaScript e TypeScript. I loro repository includono progetti significativi come ChatDev e VoxCPM, che affrontano sfide nell'ambito dell'intelligenza artificiale e della generazione di linguaggio.
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
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
An Autonomous LLM Agent for Complex Task Solving
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation
Task-oriented AI Agent productivity platform
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
百亿参数的中英文双语基座大模型
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
EdgeClaw: Edge-Cloud Collaborative Personal AI Assistant based on OpenClaw
[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 LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
Parsing-free RAG supported by VLMs
An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation
An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
Efficient Training (including pre-training and fine-tuning) for Big Models
Efficient Inference for Big Models
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
Live Training for Open-source Big Models
Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718
A large-scale, fine-grained, diverse preference dataset (and models).
A List of Big Models
Nessuna descrizione fornita per questo repository.
MiniCPM-V apps — fully offline multimodal chat on iOS / Android / HarmonyOS
Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测,知己知彼。
A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation 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
a local-first desktop pet powered by MiniCPM5
Efficient, Low-Resource, Distributed transformer implementation based on BMTrain
[ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating 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.
Official PyTorch+CUDA Full-functional Web Demo for MiniCPM-o 4.5
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Extrapolating RLVR to General Domains without Verifiers
[ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
An open platform for enhancing the capability of LLMs in workflow orchestration.
Nessuna descrizione fornita per questo repository.
Model Compression for Big Models
Nessuna descrizione fornita per questo repository.
A Toolkit for Running On-device Large Language Models (LLMs) in APP
Repo for paper "Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents"
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding
ClawXMemory: A Multi-Level Memory Plugin for OpenClaw with Long-Term Context
[SIGIR '26] Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
ArcLight: A Lightweight LLM Inference Framework
[ACL '26] This is the code repo for our ACL '26 Findings paper "MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization"
Nessuna descrizione fornita per questo repository.
An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
This is the code repo for our paper "Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search".
Nessuna descrizione fornita per questo repository.
This is the code repo for the paper "RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards".
Document for XAgent.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
BMInf demos.
SGLang is a fast serving framework for large language models and vision language models.
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
OmniEvalKit is an evaluation framework designed for omni-modal large language models, with a focus on audio and audio-visual understanding. Based on OmniEvalKit, you can quickly reproduce benchmarks, implement your own models or datasets, and conduct fair comparisons with other open-source models. MiniCPM-o is evaluated using this framework.
Nessuna descrizione fornita per questo repository.
SciCore-Omics the first tri-modal foundation model linking histology images, spatial transcriptomics, and biological language.
The official implementation of the Rational Decision-Making Agent with Internalized Utility Judgment
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Demo page for VoxCPM
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
Nessuna descrizione fornita per questo repository.
OpenBMB sviluppa una varietà di progetti su GitHub, concentrandosi principalmente su modelli di linguaggio e sistemi per l'intelligenza artificiale. I loro repository includono ChatDev e VoxCPM, che sono progettati per migliorare la collaborazione tra agenti e la generazione di voce multilingue.
OpenBMB utilizza diversi linguaggi di programmazione, tra cui Python, JavaScript, TypeScript, HTML, Cuda e C++. Questi linguaggi supportano la loro ricerca e sviluppo di modelli fondamentali e applicazioni di intelligenza artificiale.
Sì, i repository di OpenBMB sono pubblici su GitHub. Questo consente a chiunque di esplorare i loro progetti, contribuire e beneficiare delle soluzioni open-source che sviluppano nel campo dell'intelligenza artificiale.
Monitora OpenBMB con RepoGuard e ricevi un avviso nel momento in cui appare un nuovo repository pubblico.
Monitora questo account