The future of enterprise AI isn't a chatbot—it’s a digital workforce.
We're open-sourcing StaffDeck—an enterprise platform for building and managing digital employees.
Built by ModelBest, NEU–ModelBest Data Intelligence Joint Lab, THUNLP, @OpenBMB, and AI9Stars.
Instead of
🚀Introducing MiniCPM-V 2.6! 🔥
1、Surpassing GPT-4V in single image, multi-image and video understanding 📸🎥
2、Outperforms GPT-4o mini and Gemini 1.5 on OpenCompass 🏆
3、Real-time video analysis on iPad 📱💨
Try out the best on-device multimodal LLM here！ 👑
💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device
✨ Highlights:
~Match GPT-4o-202405 in vision, audio and multimodal live streaming
~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control
~Advanced OCR & video
🚨 MiniCPM-V 4.0 is here! 🚨
✨Key features:
🏗️4.1B parameters
🧠Matches GPT-4.1-mini-20250414 on image understanding tasks in OpenCompass evaluation
⚡Runs locally on iPhone 16 Pro Max at 17.9 tokens/sec
69.0 score on OpenCompass (vs 65.2 from MiniCPM-V 2.6 8B)
🚀Small model,
🚀 Introducing Ultra-FineWeb 🔥
~1T English and 120B Chinese tokens!
~Training fuel of MiniCPM4!
🎯 Highlights
~Efficient Verification Strategy: Reduces data verification cost by 90%
~High-Efficiency Filtering Pipeline: Optimizes selection of both positive and negative samples
Revolutionizing the Human-Agent Interaction Paradigm & From Reactive Agent to Proactive Agent!
We (Tsinghua NLP & OpenBMB) just introduced a groundbreaking new generation of Proactive Agent interactions! 🤖
Even the most advanced AI agents like ChatGPT are still traditional
🚀 Introducing MiniCPM-V 4.5 8B: pushing the boundary of multimodal AI!
～ SOTA VL Capability: Surpasses GPT-4o, Gemini 2.0 Pro, Qwen2.5-VL 72B on OpenCompass!
～ "Eagle Eye" Video: 96x visual token compression for high refresh rate and long video understanding
～ Controllable
As a dedicated contributor to the open-source community, OpenBMB feels deeply saddened and shocked by this.OpenBMB has always been a passionate participant in the open-source community. We look forward to working with global AI practitioners to accelerate our progress towards AGI
Shocked! Llama3-V project from a Stanford team plagiarized a lot from MiniCPM-Llama3-V 2.5!
its code is a reformatting of MiniCPM-Llama3-V 2.5, and the model's behavior is highly similar to a noised version of MiniCPM-Llama3-V 2.5 checkpoint.
Evidence: github.com/OpenBMB/MiniCP…
🔥 Test-time Scaling for MLLMs’ trustworthiness
🌟 Thrilled to introduce our new work RLAIF-V, a novel framework for aligning MLLMs through open-source feedback, achieving trustworthiness that surpasses GPT-4V!
💪 Notable features:
- Inference-time Scaling by RLAIF-V reward
-
🚀 Excited to introduce MiniCPM-Llama3-V 2.5! With 8B parameters, it’s our latest breakthrough, outperforming top models like GPT-4V. 📈
💪 Superior OCR capabilities
🔑 Supports 30+ languages
HuggingFace:huggingface.co/openbmb/MiniCP…
GitHub:github.com/OpenBMB/MiniCP…
