Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🚀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! 👑 GitHub: Huggingface: #MLLM #MiniCPM

196,307 görüntüleme • 1 yıl önce •via X (Twitter)

10 Yorum

Henry Sibanda profil fotoğrafı
Henry Sibanda1 yıl önce

Almost everything openai has been holding back because ‘safety’ is available opensource except the speech to speech. And we all still doing just fine…

kache profil fotoğrafı
kache1 yıl önce

great work guys

Pabli! 🔥💥💫 profil fotoğrafı
Pabli! 🔥💥💫1 yıl önce

The previous one was great. This one is superb. 🙌✨

Hailey Collet profil fotoğrafı
Hailey Collet1 yıl önce

This + OWL-ViT (or Florence) + SAM2 is going to enable some crazy stuff

Tiezhen WANG profil fotoğrafı
Tiezhen WANG1 yıl önce

The demo is super cool!

J Sam🌐 profil fotoğrafı
J Sam🌐1 yıl önce

🐐

Alex Volkov (Thursd/AI) profil fotoğrafı
Alex Volkov (Thursd/AI)1 yıl önce

Going to absolutely mention this on the next @thursdai_pod tomorrow!

The Canaanite profil fotoğrafı
The Canaanite1 yıl önce

Wow, that's really something. Amazing work!

pallendromeda profil fotoğrafı
pallendromeda1 yıl önce

lol it is me

Soible_VR profil fotoğrafı
Soible_VR1 yıl önce

whats the status of llamacpp support for MiniCPM family?

Benzer Videolar

🚀 🚀Excited to announce the technical report of MiniCPM-o 4.5! MiniCPM-o 4.5 transitions #AI interaction from traditional turn-based processing to a real-time, native full-duplex stream-based paradigm. 🌊 The Omni-Flow Framework Instead of traditional VAD-based workarounds, we introduce the #Omni-#Flow framework. This unified stream paradigm aligns video, audio, and text on a synchronized millisecond timeline. • Native Full-Duplex: Simultaneous perception and response. • Proactive Interaction: Natively manages turn-taking without external VAD, supports proactive reminding. 📉 9B Scale, SOTA Performance MiniCPM-o 4.5 demonstrates SOTA multimodal intelligence at its scale: • Multimodal Benchmarks: Comparable to #Gemini 2.5 Flash on MMBench EN (87.6) and MathVista (80.1). • Streaming Evaluation: 54.4% win rate on LiveSports-3K-CC, surpassing specialized models. 💻 The Ultimate Edge AI — Fully Functional without Network Connection We are providing one-click installers for Windows (12G VRAM,RTX 5070) and macOS (M1-M5 Max/ M5 Pro). • Local API Support: Deploy your own inference server to integrate native full-duplex into custom apps. • Free Access: We are offering free community API services for exploration. • 100% Private: Your data never leaves your machine. Deploy in under 10 minutes. 🛠️👇 👐 Join the Open Future The weights are open. The protocol is public. 📄 Technical Report: 💻 GitHub: 🤗 HuggingFace: 🌐 Web Demo: #MiniCPMo #OpenSourceAI #EdgeAI #MachineLearning #ComputerVision #LLM

OpenBMB

147,824 görüntüleme • 2 ay önce