This model is a joke rating model fine-tuned on multilingual text based on FacebookAI/xlm-roberta-large. It is specifically designed to evaluate the quality and humor level of jokes. It achieved an accuracy of 0.4005 and a root mean square error of 5.0327 on the evaluation set.

Natural Language ProcessingTransformers

SAM 3 is the third - generation promptable segmentation foundation model launched by Meta. It can use text or visual prompts (points, boxes, masks) to detect, segment, and track objects in images and videos. Compared with previous generations, SAM 3 introduces the ability to exhaustively segment all instances of open - vocabulary concepts, supports a large number of open - vocabulary prompts, and achieves 75 - 80% of human performance on the SA - CO benchmark.

Computer VisionTransformersEnglish

This model is an instance segmentation model fine-tuned on the qubvel-hf/ade20k-mini dataset based on facebook/mask2former-swin-tiny-coco-instance. This model is specifically optimized for the scene understanding task in the ADE20K-mini dataset and shows good performance in the instance segmentation task.

Computer VisionTransformers

This model is a fine-tuned version of Facebook's DETR-ResNet-50-DC5 object detection model on a fashion dataset, specifically designed for fashion item detection and classification. The model is optimized on the Fashionpedia dataset and can identify fashion items such as clothing and accessories.

Computer VisionTransformers

MobileLLM-Pro is a 1-billion-parameter efficient device-side language model launched by Meta, optimized for mobile devices, supporting a context length of 128k and providing high-quality inference capabilities. This model is trained using knowledge distillation technology, outperforming models of the same scale in multiple benchmark tests, and supporting nearly lossless 4-bit quantization.

Natural Language ProcessingTransformersEnglish

MobileLLM-R1 is an efficient inference model series released by Meta, including three scales of 140M, 360M, and 950M. This model is specifically optimized for mathematical, programming, and scientific problems, achieving comparable or even better performance than large-scale models with a smaller parameter scale.

Natural Language ProcessingTransformersEnglish

MobileLLM-R1 is a series of efficient inference language models released by Meta, focusing on solving mathematical, programming, and scientific problems. This model can still achieve excellent performance with a relatively small parameter scale, and provides a complete training recipe and data sources to support reproducible research.

Natural Language ProcessingTransformersEnglish

MobileLLM-R1 is a series of efficient inference models launched by Facebook, focusing on solving mathematical, programming, and scientific problems. This model has achieved excellent performance in multiple benchmark tests with only about 2T high-quality labels for pre-training.

Natural Language ProcessingTransformersEnglish

MobileLLM-R1 is a series of efficient inference models focused on mathematics, programming, and scientific problems, achieving excellent performance with less training data and providing a complete training recipe and data source.

Natural Language ProcessingTransformersEnglish

MobileLLM-R1 is a series of efficient reasoning models launched by Meta, focusing on solving mathematical, programming, and scientific problems. The model offers three scale versions of 140M, 360M, and 950M, with excellent reasoning ability and reproducibility.

Natural Language ProcessingTransformersEnglish

MobileLLM-R1 is an efficient inference model in the MobileLLM series, specifically optimized for mathematics, programming, and scientific problems. It achieves higher accuracy with a smaller parameter scale, featuring low training cost and high efficiency.

Natural Language ProcessingTransformersEnglish

MapAnything is an end-to-end trained Transformer model that can take multiple modalities as input and directly regress the decomposed metric 3D geometric structure of the scene. This model supports more than 12 different 3D reconstruction tasks, including multi-image SfM, multi-view stereo vision, and monocular metric depth estimation.

Computer VisionSafetensorsEnglish

DINOv3 is a series of general-purpose visual foundation models that can outperform specialized state-of-the-art techniques on a wide range of visual tasks without fine-tuning. This model can generate high-quality dense features and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly-supervised foundation models.

Computer VisionTransformersEnglish

DINOv3 is a series of general visual foundation models developed by Meta AI. Without fine-tuning, it can outperform specialized state-of-the-art models in a wide range of visual tasks. This model uses self-supervised learning to generate high-quality dense features and performs excellently in various tasks such as image classification, segmentation, and depth estimation.

Computer VisionTransformersEnglish

DINOv3 is a versatile visual foundation model developed by Meta AI. It can outperform specialized models in a wide range of visual tasks without fine-tuning. This model can generate high-quality dense features and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly supervised foundation models.

Computer VisionTransformersEnglish

DINOv3 is a series of general visual foundation models developed by Meta AI. It can outperform specialized advanced models in various visual tasks without fine-tuning. The model adopts the Vision Transformer architecture and is pre-trained on 1.689 billion web images. It can generate high-quality dense features and performs excellently in tasks such as image classification, segmentation, and retrieval.

Computer VisionTransformersEnglish

DINOv3 is a series of general-purpose visual foundation models that can outperform specialized state-of-the-art models on a wide range of visual tasks without fine-tuning. The model uses self-supervised learning to generate high-quality dense features and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly supervised foundation models.

Computer VisionTransformersEnglish

DINOv3 is a series of general visual foundation models that can outperform specialized state-of-the-art techniques in a wide range of visual tasks without fine-tuning. The model generates high-quality dense features through self-supervised learning and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly supervised foundation models.

Computer VisionTransformersEnglish

MetaCLIP 2 (worldwide) is a multilingual zero-shot image classification model based on the Transformer architecture. It supports visual language understanding tasks globally and can classify images without training.

MultimodalTransformersOther

ESM-2 is a protein language model optimized by NVIDIA using the TransformerEngine library based on the original ESM-2 model from Facebook Research. It has the same weights and outputs within the numerical precision range and is suitable for protein sequence analysis tasks.

Scientific ComputingTransformers