ColModernVBERT is a late interaction version of ModernVBERT, specifically fine - tuned for the visual document retrieval task and is the best - performing model on this task. It is a compact vision - language encoder with 250 million parameters, achieving performance close to that of models with 10 times more parameters in visual document benchmark tests, while having a considerable inference speed on the CPU.

MultimodalSafetensorsEnglish

Isaac 0.1 is the first perceptual language model launched by PerceptronAI. It has 2 billion parameters and is designed for real-world applications. This model sets a new standard in efficiency, with performance reaching or exceeding that of models more than 50 times larger. It has powerful visual understanding and spatial reasoning capabilities.

MultimodalTransformers

CHURRO is an open-weight visual language model with 3 billion parameters, specifically designed for historical document transcription. It can recognize handwritten and printed text spanning 22 centuries and 46 language clusters, including historical and extinct languages, achieving higher accuracy than large commercial models at a significantly reduced cost.

MultimodalSafetensors

TowerVision is an open-source family of multilingual visual language models with powerful multimodal understanding capabilities. It performs excellently in 20 languages and dialects and is particularly good at multimodal multilingual translation and culture-aware tasks.

MultimodalTransformersMultiple Languages

GLM-4.5V-AWQ-4bit is a quantized multimodal model built on Zhipu AI's next-generation flagship text foundation model. Optimized by AWQ-4bit quantization technology, it significantly reduces the computational resource requirements while maintaining excellent performance. This model achieves SOTA performance among models of the same scale in 42 public visual language benchmark tests and has powerful visual reasoning capabilities.

MultimodalTransformersMultiple Languages

Llama3-MS-CLIP is the first visual language model in the CLIP family that can understand multispectral images. It is trained on one million image-text pairs from the SSL4EO-S12-v1.1 dataset and the generated descriptions, and outperforms other RGB-based models in most benchmark tests.

VisualPRM-8B-v1.1 is an advanced multimodal process reward model with 8 billion parameters, which enhances the reasoning ability of large multimodal language models through the Best-of-N evaluation strategy.

MultimodalTransformersmultilingual

A multimodal large language model developed based on the paper 'Task Preference Optimization: Improving Multimodal Large Language Models through Visual Task Alignment'

MultimodalTransformers

LLM2CLIP is an innovative approach that enhances CLIP's cross-modal capabilities through large language models, significantly improving the discriminative power of visual and text representations.

MultimodalSafetensors

LLM2CLIP is a method that enhances CLIP model capabilities using large language models (LLMs) by fine-tuning LLMs through contrastive learning and employing them as teacher models for CLIP's visual encoder, significantly improving cross-modal task performance.

MultimodalSafetensors

LLM2CLIP is an innovative approach that enhances CLIP's visual representation capabilities through large language models (LLMs), significantly improving cross-modal task performance

MultimodalPytorch

Llama 3.2-Vision is a series of multimodal large language models developed by Meta, available in 11B and 90B scales, supporting image + text input and text output, optimized for visual recognition, image reasoning, image captioning, and visual question answering tasks.

MultimodalTransformersMultiple Languages

Eagle is a series of vision-centric high-resolution multimodal large language models, enhancing the perception capabilities of multimodal LLMs by hybridizing visual encoders from different architectures and knowledge domains.

MultimodalTransformers

Eagle is a vision-centric high-resolution multimodal large language model family that enhances the perception ability of multimodal large language models by fusing multiple visual encoders and different input resolutions.

MultimodalTransformers

MoVA-8B is an open-source multimodal large language model that uses a coarse-to-fine mechanism to adaptively route and fuse visual expert modules for specific tasks. It can be used for research on multimodal models and chatbots.

MultimodalTransformers

Cephalo is a series of vision-based large language models (V-LLMs) focused on multimodal materials science, designed to integrate visual and linguistic data to facilitate advanced understanding and interaction in human-computer or multi-agent AI frameworks.

MultimodalTransformersOther

Cephalo is a series of vision-based large language models (V-LLMs) focused on multimodal materials science, designed to integrate visual and linguistic data to facilitate advanced understanding and interaction in human-computer or multi-agent AI frameworks.

MultimodalTransformersOther

Kosmos-2 is a multimodal large language model capable of grounding language models to real-world visual elements, supporting various vision-language tasks.

MultimodalTransformers

DePlot is a visual-language reasoning model capable of converting chart images into linearized tables, enabling few-shot reasoning when combined with large language models

MultimodalTransformersMultiple Languages