In the age of AI, large language models (LLMs) are akin to martial arts secrets; their training processes consume massive computing power and data, much like martial arts experts who have spent years in secluded training. The release of open-source models is like these experts sharing their secrets with the public, but they come with certain licenses (such as Apache 2.0 and LLaMA 2 Community License) to protect their intellectual property (IP). However, the world can be treacherous, and incidents of 'shelling' are bound to occur. Some developers claim they have trained new LLMs when, in fact, they are using other foundational models (like Lla

On October 30, Mianbi Intelligence announced a strategic partnership with Baidu Intelligent Cloud, aiming to jointly develop collaborative solutions for large models. According to the partnership agreement, the two parties will leverage Baidu Intelligent Cloud's Qianfan Large Model Platform, Wenxin series large models, as well as Mianbi's MiniCPM series edge large models and cutting-edge technology accumulation across multiple terminals and different scenarios, to collaboratively develop and promote edge-cloud collaborative technology solutions that further enhance the performance of large models in practical applications such as embodied intelligence, smart terminals, and edge computing, while reducing the inference costs of large models.

MianBi Intelligence has recently launched MiniCPM 3.0, a high-performance AI model that operates on devices with just 2GB of memory, heralding a new era of edge AI experience. The MiniCPM 3.0 model features 4 billion parameters and outperforms GPT-3.5, providing AI services on mobile devices comparable to those of GPT-3.5. This allows users to enjoy fast, secure, and feature-rich local AI services without relying on cloud processing, ensuring a smoother and more private intelligent interaction experience.

The latest version 2.6 of WallFacer’s MiniCPM-V series has rapidly climbed to the Top 3 on GitHub and HuggingFace trends, surpassing ten thousand stars. Since its release in February, it has accumulated over a million downloads, becoming a benchmark for on-device model capabilities. MiniCPM-V2.6 achieves performance enhancements for on-device multimodal models with 8 billion parameters, including real-time video understanding, multi-image joint understanding, and multi-image in-context learning, with a quantized backend memory of only 6GB and an inference speed of up to 18 tokens.

"MiniCPM-V2.6" is an edge-side multimodal artificial intelligence model that, with only 8B parameters, has achieved SOTA (State of the Art) results in single image, multiple images, and video understanding, all under 20B parameters, significantly enhancing edge AI's multimodal capabilities and being fully comparable to GPT-4V.

One of the major highlights of MiniCPM-Llama3-V2.5 is its efficient energy consumption. When running on mobile devices, it requires only 8GB of VRAM in combination with the NVIDIA GeForce RTX 4070 graphics card to achieve rapid inference and extremely fast operation speed. Additionally, the image encoding speed has been improved by 150 times, marking the first realization of system-level multimodal acceleration on the edge. Even more impressive, this model supports over 30 languages, providing robust support for multilingual environments.