MiniCPM's profile picture. A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

MiniCPM

@MiniCPM

A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

Multilingual ability - ask MiniCPM-o 2.6 to be your language assistant!


💡💡💡 MiniCPM-o 2.6 is now supported by Align-Anything (github.com/PKU-Alignment/…), a framework by PKU-Alignment Team for aligning any-to-any modality large models with human intentions. It supports DPO and SFT fine-tuning on both vision and audio. Try it now!


MiniCPM-o 2.6 Advanced Voice Chat with different accents and real-time interruption.


Example 2 More details: github.com/OpenBMB/MiniCP…

MiniCPM's tweet image. Example 2

More details: github.com/OpenBMB/MiniCP…

📢 ATTENTION! We are currently working on merging MiniCPM-o 2.6 into the official repositories of llama.cpp, ollama, and vllm. Until the merge is complete, please USE OUR LOCAL FORKS of llama.cpp, ollama, and vllm.


🚨 o3-mini crushed DeepSeek R1 "Write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"


We have updated the usage of MiniCPM-o 2.6 int4 quantization version and resolved the model initialization error. Click here and try it now: huggingface.co/openbmb/MiniCP…

huggingface.co

openbmb/MiniCPM-o-2_6-int4 · Hugging Face

openbmb/MiniCPM-o-2_6-int4 · Hugging Face


Asking MiniCPM-o 2.6 to recall the word that was just erased...


Play puzzle or trick game with MiniCPM-o 2.6


You can easily build your own local WebUI demo using the following commands. Please ensure that transformers==4.44.2 is installed, as other versions may have compatibility issues.

MiniCPM's tweet image. You can easily build your own local WebUI demo using the following commands.

Please ensure that transformers==4.44.2 is installed, as other versions may have compatibility issues.

🔥🔥🔥 We open-source MiniCPM-o 2.6, which matches GPT-4o-202405 on vision, speech and multimodal live streaming. It advances popular capabilities of MiniCPM-V 2.6, and supports various new fun features. Try it now!


United States Trends

Loading...

Something went wrong.


Something went wrong.