The 4-bit AWQ quantized version of the DeepSeek-R1-0528 671B model, suitable for use on high-end GPU nodes

Natural Language ProcessingTransformers

A LoRA adapter based on the Wan2.1-T2V-14B text-to-video model, specifically designed for generating video content in the style of ancient book illustrations

MultimodalDiffusers

A legal domain sentence embedding model fine-tuned based on ModernBERT, supporting multi-level dimensional output, suitable for legal text similarity calculation and information retrieval tasks.

Natural Language ProcessingSafetensorsEnglish

A lightweight face detection model based on the YOLO architecture, specifically designed for efficient face detection, trained on the WIDERFACE dataset.

Computer VisionPytorch

This model is a fine-tuned LLM router classifier based on ModernBERT-large, used to distinguish between complex queries (using large language models) and simple queries (using small language models).

Natural Language ProcessingTransformers

A text-to-image model based on Multimodal Diffusion Transformer (MMDiT), utilizing Adversarial Diffusion Distillation (ADD) technology to optimize image quality, typography, and complex prompt understanding while reducing inference steps.

MultimodalDiffusersEnglish

An advanced text-to-image model based on Multimodal Diffusion Transformer (MMDiT), with significant improvements in image quality, text layout, and prompt understanding

MultimodalDiffusersEnglish

Action Chunking Transformer (ACT) model trained on the AdamLucek/koch_block dataset, suitable for Koch v1.1 low-cost robots

Computer VisionSafetensors

fermi-bert-1024 is a pre-trained BERT model specifically optimized for the nuclear energy field. This model is trained on data from Wikipedia, Books3, and the US Nuclear Regulatory Commission's ADAMS database, and it is specially optimized for handling technical terms and regulatory languages in the nuclear energy industry. It was trained on the Frontier supercomputer at Oak Ridge National Laboratory using 128 AMD MI250X GPUs for 10 hours, providing a solid foundation for nuclear energy applications.

Natural Language ProcessingTransformersEnglish

KAT is a novel vision model that replaces the traditional Transformer's channel mixer with Grouped Rational Kolmogorov-Arnold Networks (GR-KAN), trained on the ImageNet-1k dataset.

Computer VisionTimm

A Polish dialogue model fine-tuned on Mistral-7B-v0.2, focused on delivering smooth and natural conversational experiences

Natural Language ProcessingGguf

A specialized receipt text extraction model based on the Donut architecture, achieving OCR-free document understanding through visual encoder and text decoder

MultimodalTransformers

An image classification model based on Vision Transformer (ViT) architecture, specifically designed to detect whether images contain NSFW (Not Safe For Work) content.

Computer VisionTransformers

This is a lightweight sentiment classification model based on the BERT-tiny architecture, fine-tuned on a balanced sentiment dataset. While maintaining efficient inference, the model achieves an accuracy of 93.54%, making it particularly suitable for scenarios requiring rapid sentiment analysis.

Natural Language ProcessingTransformers

A dialogue summarization generation model fine-tuned on the SAMSum dataset based on the BART-large architecture

Natural Language ProcessingTransformers

HPSv2-hf is the Huggingface CLIPModel version of the HPSv2 model, designed to predict human preferences for AI-generated images.

MultimodalTransformers

A Vision Transformer model fine-tuned on a flower image dataset based on Google's ViT-Base-Patch16-224 model

Computer VisionTransformers

An AI model for generating cyberpunk anime characters, based on fine-tuned Waifu Diffusion V1.3 model, using Stable Diffusion V1.5 new VAE, trained in Dreambooth

Computer VisionDiffusersEnglish

2D-Mix is a text-to-image generation model based on stable diffusion technology, specifically optimized for anime style and Genshin Impact characters.

Computer VisionDiffusersEnglish

A stable diffusion model designed to generate high-quality, high-detail anime-style images with simple prompts

Computer VisionDiffusersEnglish