MiniCPM-V-2_6
Maintainer: openbmb
674
⚙️
| Property | Value |
|---|---|
| Run this model | Run on HuggingFace |
| API spec | View on HuggingFace |
| Github link | No Github link provided |
| Paper link | No paper link provided |
Create account to get full access
Model overview
MiniCPM-V-2_6 is the latest and most capable model in the MiniCPM-V series. It is built on SigLip-400M and Qwen2-7B with a total of 8B parameters. Compared to the previous MiniCPM-Llama3-V 2.5 model, MiniCPM-V-2_6 exhibits significant performance improvements and introduces new features for multi-image and video understanding.
Model inputs and outputs
Inputs
- Single image:
MiniCPM-V-2_6can process images of any aspect ratio up to 1.8 million pixels. - Multiple images: The model can perform conversation and reasoning over multiple images.
- Video:
MiniCPM-V-2_6can accept video inputs and provide dense captions for spatial-temporal information.
Outputs
- Text: The model generates coherent and relevant text responses based on the input images or videos.
- Image/Video understanding:
MiniCPM-V-2_6can provide detailed captions, analysis, and insights about the visual content.
Capabilities
MiniCPM-V-2_6 exhibits state-of-the-art performance on a wide range of benchmarks, surpassing popular models like GPT-4o mini, GPT-4V, Gemini 1.5 Pro, and Claude 3.5 Sonnet. Its key capabilities include:
- Leading single-image performance: With only 8B parameters,
MiniCPM-V-2_6achieves an average score of 65.2 on the OpenCompass benchmark, outperforming larger models. - Multi-image understanding and in-context learning: The model demonstrates state-of-the-art performance on multi-image benchmarks like Mantis-Eval, BLINK, Mathverse mv, and Sciverse mv.
- Video understanding:
MiniCPM-V-2_6outperforms GPT-4V, Claude 3.5 Sonnet, and LLaVA-NeXT-Video-34B on the Video-MME benchmark, with and without subtitles. - Trustworthy behavior: Leveraging the latest RLAIF-V and VisCPM techniques, the model exhibits significantly lower hallucination rates than GPT-4o and GPT-4V on the Object HalBench.
- Multilingual capabilities:
MiniCPM-V-2_6supports multiple languages, including English, Chinese, German, French, Italian, and Korean. - Superior efficiency: The model produces only 640 tokens when processing a 1.8M pixel image, 75% fewer than most models, leading to faster inference and lower resource usage.
What can I use it for?
MiniCPM-V-2_6 can be used for a wide range of applications that involve understanding and reasoning about visual content, such as:
- Image captioning and analysis: The model can generate detailed descriptions and insights about the content of single or multiple images.
- Multimodal question answering:
MiniCPM-V-2_6can answer questions that require understanding both the text and visual information. - Real-time video understanding: The model's efficient processing allows for real-time inference on end-side devices like iPads, enabling applications like video summarization and scene analysis.
- Assistive technology: The model's capabilities can be leveraged to build intelligent assistants that can interact with users using both text and visual inputs.
Things to try
One interesting aspect of MiniCPM-V-2_6 is its ability to process high-resolution images efficiently. This can be particularly useful for tasks that require detailed visual analysis, such as document understanding or fine-grained object detection. Developers can experiment with feeding the model high-resolution images and observe how it extracts and utilizes the additional visual information.
Another intriguing aspect is the model's performance on video understanding. Researchers and engineers can explore how MiniCPM-V-2_6 handles various video-based tasks, such as video captioning, activity recognition, or video question answering, and compare its capabilities to other state-of-the-art models in this domain.
Finally, the model's multilingual support opens up opportunities for cross-lingual multimodal applications. Developers can test the model's ability to understand and generate text in different languages while seamlessly incorporating visual information, which could be valuable for building inclusive and globally accessible applications.
This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!
Related Models
🖼️
MiniCPM-V-2
509
MiniCPM-V-2 is a strong multimodal large language model developed by openbmb for efficient end-side deployment. It is built based on SigLip-400M and MiniCPM-2.4B, connected by a perceiver resampler. The latest version, MiniCPM-V 2.0, has several notable features. MiniCPM-V 2.0 achieves state-of-the-art performance on multiple benchmarks, even outperforming strong models like Qwen-VL-Chat 9.6B, CogVLM-Chat 17.4B, and Yi-VL 34B on OpenCompass, a comprehensive evaluation over 11 popular benchmarks. It also shows strong OCR capability, achieving comparable performance to Gemini Pro in scene-text understanding, and state-of-the-art performance on OCRBench among open-source models. Additionally, MiniCPM-V 2.0 is the first end-side LMM aligned via multimodal RLHF for trustworthy behavior, allowing it to match GPT-4V in preventing hallucinations on Object HalBench. The model can also accept high-resolution 1.8 million pixel images at any aspect ratio. Model inputs and outputs Inputs Text**: The model can take in text inputs. Images**: MiniCPM-V 2.0 can accept high-resolution 1.8 million pixel images at any aspect ratio. Outputs Text**: The model generates text outputs. Capabilities MiniCPM-V 2.0 demonstrates state-of-the-art performance on a wide range of multimodal benchmarks, including OCRBench, TextVQA, MME, MMB, and MathVista. It outperforms even larger models like Qwen-VL-Chat 9.6B and Yi-VL 34B on the comprehensive OpenCompass evaluation. The model's strong OCR capabilities make it well-suited for tasks like scene-text understanding. Additionally, MiniCPM-V 2.0 is the first end-side LMM to be aligned via multimodal RLHF for trustworthy behavior, preventing hallucinations on the Object HalBench. This makes it a reliable choice for applications where accuracy and safety are paramount. What can I use it for? The high-performance and trustworthy nature of MiniCPM-V 2.0 make it a great choice for a variety of multimodal applications. Some potential use cases include: Multimodal question answering**: The model's strong performance on benchmarks like TextVQA and MME suggest it could be useful for tasks that involve answering questions based on a combination of text and images. Scene text understanding**: MiniCPM-V 2.0's state-of-the-art OCR capabilities make it well-suited for applications that involve extracting and understanding text from images, such as document digitization or visual search. Multimodal content generation**: The model's ability to generate text conditioned on images could enable applications like image captioning or visual storytelling. Things to try One interesting aspect of MiniCPM-V 2.0 is its ability to accept high-resolution 1.8 million pixel images at any aspect ratio. This could enable better perception of fine-grained visual information, such as small objects and optical characters, which could be useful for applications like optical character recognition or detailed image understanding. Additionally, the model's alignment via multimodal RLHF for trustworthy behavior is a notable feature. Developers could explore ways to leverage this capability to build AI systems that are reliable and safe, particularly in sensitive domains where accurate and unbiased outputs are critical.
Updated Invalid Date
🧪
MiniCPM-Llama3-V-2_5
1.2K
MiniCPM-Llama3-V-2_5 is the latest model in the MiniCPM-V series, built on SigLip-400M and Llama3-8B-Instruct with a total of 8B parameters. It exhibits significant performance improvements over the previous MiniCPM-V 2.0 model. The model achieves leading performance on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, surpassing widely used proprietary models like GPT-4V-1106, Gemini Pro, Qwen-VL-Max and Claude 3 with 8B parameters. It also demonstrates strong OCR capabilities, scoring over 700 on OCRBench, outperforming proprietary models such as GPT-4o, GPT-4V-0409, Qwen-VL-Max and Gemini Pro. Model inputs and outputs Inputs Images**: The model can process images with any aspect ratio up to 1.8 million pixels. Text**: The model can engage in multimodal interactions, accepting text prompts and queries. Outputs Text**: The model generates text responses to user prompts and queries, leveraging its multimodal understanding. Extracted text**: The model can perform full-text OCR extraction from images, converting printed or handwritten text into editable markdown. Structured data**: The model can convert tabular information in images into markdown format. Capabilities MiniCPM-Llama3-V-2_5 exhibits trustworthy multimodal behavior, achieving a 10.3% hallucination rate on Object HalBench, lower than GPT-4V-1106 (13.6%). The model also supports over 30 languages, including German, French, Spanish, Italian, and Russian, through the VisCPM cross-lingual generalization technology. Additionally, the model has been optimized for efficient deployment on edge devices, realizing a 150-fold acceleration in multimodal large model image encoding on mobile phones with Qualcomm chips. What can I use it for? MiniCPM-Llama3-V-2_5 can be used for a variety of multimodal tasks, such as visual question answering, document understanding, and image-to-text generation. Its strong OCR capabilities make it particularly useful for tasks involving text extraction and structured data processing from images, such as digitizing forms, receipts, or whiteboards. The model's multilingual support also enables cross-lingual applications, allowing users to interact with the system in their preferred language. Things to try Experiment with MiniCPM-Llama3-V-2_5's capabilities by providing it with a diverse set of images and prompts. Test its ability to accurately extract and convert text from high-resolution, complex images. Explore its cross-lingual functionality by interacting with the model in different languages. Additionally, assess the model's trustworthiness by monitoring its behavior on potential hallucination tasks.
Updated Invalid Date
🌀
MiniCPM-V
112
MiniCPM-V is an efficient and high-performing multimodal language model developed by the OpenBMB team. It is an improved version of the MiniCPM-2.4B model, with several notable features. Firstly, MiniCPM-V can be efficiently deployed on most GPUs and even mobile phones, thanks to its compressed image representation. It encodes images into just 64 tokens, significantly fewer than other models that typically use over 512 tokens. This allows MiniCPM-V to operate with much less memory and higher inference speed. Secondly, MiniCPM-V demonstrates state-of-the-art performance on multiple benchmarks, such as MMMU, MME, and MMBench, surpassing existing models of comparable size. It even achieves comparable or better results than the larger 9.6B Qwen-VL-Chat model. Lastly, MiniCPM-V is the first end-deployable large language model that supports bilingual multimodal interaction in both English and Chinese. This is enabled by a technique from the VisCPM ICLR 2024 paper that generalizes multimodal capabilities across languages. Model inputs and outputs Inputs Images**: MiniCPM-V can accept images as inputs for tasks such as visual question answering and image description generation. Text**: The model can also take text inputs, allowing for multimodal interactions and conversations. Outputs Text**: Based on the provided inputs, MiniCPM-V can generate relevant text responses, such as answering questions about images or describing their contents. Capabilities MiniCPM-V demonstrates strong multimodal understanding and generation capabilities. For example, it can accurately caption images, as shown in the provided GIFs of a mushroom and a snake. The model is also able to answer questions about images, as evidenced by its high performance on benchmarks like MMMU and MMBench. What can I use it for? Given its strong multimodal abilities, MiniCPM-V can be useful for a variety of applications, such as: Visual question answering**: The model can be used to build applications that allow users to ask questions about images and receive relevant responses. Image captioning**: MiniCPM-V can be integrated into systems that automatically generate descriptions for images. Multimodal conversational assistants**: The model's bilingual support and multimodal capabilities make it a good candidate for building conversational AI assistants that can understand and respond to both text and images. Things to try One interesting aspect of MiniCPM-V is its efficient visual encoding technique, which allows the model to operate with much lower memory requirements compared to other large multimodal models. This could enable the deployment of MiniCPM-V on resource-constrained devices, such as mobile phones, opening up new possibilities for on-the-go multimodal interactions. Additionally, the model's bilingual support is a noteworthy feature, as it allows for seamless multimodal communication in both English and Chinese. Developers could explore building applications that leverage this capability, such as cross-language visual question answering or image-based translation services.
Updated Invalid Date
🌀
MiniCPM-2B-sft-bf16
113
MiniCPM-2B-sft-bf16 is a large language model developed by OpenBMB and TsinghuaNLP, with only 2.4 billion parameters excluding embeddings. It is an "end-side" LLM, meaning it is designed for efficient deployment even on resource-constrained devices like smartphones. Compared to larger models like Mistral-7B, Llama2-13B, MPT-30B, and Falcon-40B, MiniCPM-2B-sft-bf16 achieves very close performance on open-source benchmarks, with better abilities in Chinese, mathematics, and coding after supervised fine-tuning (SFT). Its overall performance exceeds that of these larger models. After further training using data-prompted optimization (DPO), the MiniCPM-2B model outperforms even larger models like Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, and Zephyr-7B-alpha on the MTBench evaluation. The MiniCPM-V variant, based on the MiniCPM-2B architecture, achieves the best overall performance among multimodal models of a similar scale, surpassing existing large multimodal models like Phi-2 and even matching the performance of the 9.6B Qwen-VL-Chat model on some tasks. Model inputs and outputs Inputs Text input for language understanding and generation tasks Outputs Generated text based on the input Multimodal outputs (e.g. image captions, VQA) for the MiniCPM-V variant Capabilities MiniCPM-2B-sft-bf16 demonstrates strong performance across a variety of benchmarks, including open-domain language understanding, mathematics, coding, and Chinese language tasks. The MiniCPM-V variant extends these capabilities to multimodal tasks like image captioning and visual question answering. One key advantage of the MiniCPM models is their efficient deployment. They can be run on devices as small as smartphones, with the MiniCPM-V being the first multimodal model that can be deployed on mobile phones. The models also have a low cost of development, requiring only a single 1080/2080 GPU for parameter-efficient fine-tuning and a 3090/4090 GPU for full parameter fine-tuning. What can I use it for? The MiniCPM models are well-suited for a variety of natural language processing and multimodal applications, such as: General language understanding and generation Domain-specific applications (e.g. legal, medical, mathematical) Multimodal tasks like image captioning and visual question answering Conversational AI and virtual assistants Mobile and edge computing applications Thanks to their efficient design and deployment, the MiniCPM models can be particularly useful in resource-constrained environments or for applications that require low latency, such as on-device inference. Things to try One interesting aspect of the MiniCPM models is their ability to perform well on Chinese language tasks, in addition to their strengths in English. This makes them a compelling choice for multilingual applications or for users who require Chinese language capabilities. Additionally, the MiniCPM-V variant's strong multimodal performance, combined with its efficient deployment, opens up opportunities for novel applications that integrate vision and language, such as mobile-based visual question answering or image-guided dialogue systems. Researchers and developers may also be interested in exploring the technical details of the MiniCPM models, such as the use of supervised fine-tuning and data-prompted optimization, to better understand how to build performant and efficient large language models.
Updated Invalid Date