NuExtract 2.0 is a series of multimodal models specifically trained by NuMind for structured information extraction tasks. This 4B version is built on Qwen2.5-VL-3B-Instruct, supports text and image input, has multilingual processing capabilities, and can extract structured information from unstructured data.

MultimodalTransformers

Owlet Safety 1 is a multi-label safety event detection model fine-tuned based on Qwen2.5-VL-3B-Instruct. It is specifically designed for safety activity recognition in video surveillance and can simultaneously detect multiple safety-related events such as fires, smoke, falls, and assaults.

MultimodalTransformers

A visual OCR model fine-tuned based on Qwen2.5-VL-3B-Instruct, focusing on document-level OCR, long-context visual language understanding, and mathematical LaTeX format conversion.

MultimodalTransformersEnglish

UI-R1-E-3B is an efficient GUI positioning model fine-tuned based on Qwen2.5-VL-3B-Instruct, specializing in visual question-answering tasks, particularly excelling at locating and identifying operational elements in user interface screenshots.

MultimodalSafetensorsEnglish

Qwen2.5-VL is the latest vision-language model in the Qwen family, featuring powerful visual understanding and multimodal processing capabilities.

MultimodalGgufEnglish

QwenGuard-v1.2-3B is a visual security protection model developed based on Qwen/Qwen2.5-VL-3B-Instruct, designed for assessing the safety of image content.

MultimodalTransformers

A multimodal language model fine-tuned by Tencent PCG Basic Algorithm Center, optimized based on Qwen2.5-VL-3B-Instruct, achieving state-of-the-art performance in multiple multimodal reasoning benchmarks among models of the same scale

MultimodalSafetensorsEnglish

Fine-tuned version based on Qwen2.5-VL-3B model, trained using Unsloth and Huggingface TRL library, achieving 2x inference speed improvement

MultimodalTransformersEnglish

Qwen2.5-VL-3B-Instruct is a 3B-parameter multimodal model supporting image-text generation tasks, specifically optimized for vision capabilities in llama.cpp.

MultimodalGgufEnglish

Qwen2.5-VL-3B-Instruct is a 3B-parameter vision-language model that supports image-to-text generation tasks.

MultimodalGguf

A zero-shot object detection model based on Qwen2.5-VL-3B-Instruct, enhanced with VLM-R1 reinforcement learning, supporting open vocabulary detection tasks.

MultimodalSafetensorsEnglish

The GPTQ-Int3 quantized version of Qwen2.5-VL-3B-Instruct, suitable for multimodal image-text processing tasks with reduced VRAM usage and faster inference speed.

MultimodalTransformersMultiple Languages

UI-R1 is a vision-language model enhanced by reinforcement learning for GUI agent action prediction, built upon Qwen2.5-VL-3B-Instruct.

MultimodalSafetensorsEnglish

A multilingual visual retrieval model based on Qwen2.5-VL-3B-Instruct and ColBERT strategy, supporting dynamic input image resolution and multilingual document retrieval.

MultimodalSafetensorsMultiple Languages

A multilingual visual retrieval model based on Qwen2.5-VL-3B-Instruct and ColBERT strategy, supporting dynamic input image resolution and generating ColBERT-style multi-vector text and image representations.

MultimodalTransformersMultiple Languages

A vision-language model based on Qwen2.5-VL-3B-Instruct, enhanced with mathematical capabilities and trained using VLM-R1 reinforcement learning, specializing in solving math-related visual question answering tasks.

MultimodalSafetensorsEnglish

This is the GPTQ-Int4 quantized version of the Qwen2.5-VL-3B-Instruct model, suitable for multimodal tasks involving image-to-text and text-to-text, supporting both Chinese and English.

MultimodalTransformersMultiple Languages

A vision-language model based on Qwen2.5-VL-3B-Instruct, enhanced with VLM-R1 reinforcement learning, focusing on referring expression comprehension tasks.

MultimodalSafetensorsEnglish

A multilingual visual retriever based on Qwen2.5-VL-3B-Instruct with ColBERT strategy, excelling in Vidore benchmark tests

MultimodalSafetensorsMultiple Languages

Quantized version of Qwen/Qwen2.5-VL-3B-Instruct, supporting visual-text input and text output, with weights quantized to INT8 and activations quantized to INT8.

MultimodalTransformersEnglish