This is a large language model with 24B parameters based on the Mistral architecture, converted to the GGUF format via llama.cpp. The model supports multilingual interaction and is specially optimized for instruction following capabilities, suitable for various text generation and understanding tasks.

Natural Language ProcessingGgufMultiple Languages

A LORA model trained on Flux.1 [Dev Version] (Dev2Pro edition) for generating images of popular Malaysian actress Chacha Maembong in text-to-image tasks.

Computer VisionDiffusers

Italian chat model based on Mistral-7b, pre-trained and fine-tuned on a large Italian corpus

Natural Language ProcessingTransformersOther

Italian conversation model based on Mistral-7b, fine-tuned in three stages with supervised learning and KTO alignment

Natural Language ProcessingTransformersOther

Hiera is an efficient hierarchical Transformer architecture that optimizes spatial bias characteristics through MAE training, significantly improving parameter utilization efficiency

Computer VisionTransformers

This is a VAE decoder fine-tuned based on stabilityai/sd-vae-ft-mse, specifically optimized for e621 image data. It employs a mixed loss function of MAE and MSE, calculating the loss in the Oklab color space to enhance image reconstruction quality.

Computer VisionDiffusers

A Vision Transformer (ViT)-based audio processing model, pre-trained on AudioSet-2M using self-supervised masked autoencoder (MAE) method and fine-tuned on AudioSet-20k

Audio ProcessingTimm

This is a classical piano music generation model based on Byte Pair Encoding (BPE) technology, trained on the Maestro dataset. The model uses an autoregressive Transformer with a GPT2 architecture and can generate subsequent classical piano music content based on musical prompts.

Audio ProcessingTransformers

MAEST is a series of Transformer models based on PASST, focusing on music analysis applications, particularly excelling in music genre classification tasks.

Audio ProcessingTransformers

MAEST is a series of Transformer models based on PASST, focusing on music analysis applications, capable of classifying 400 music genres

Audio ProcessingTransformers

MAEST is a series of Transformer models based on PASST, focusing on music analysis applications, particularly music genre classification tasks.

Audio ProcessingTransformers

MAEST is a Transformer model family based on PASST, focusing on music analysis applications, particularly excelling in music genre classification tasks.

Audio ProcessingTransformers

Large-scale image feature extraction model based on Vision Transformer (ViT), pre-trained on ImageNet-1k dataset using self-supervised Masked Autoencoder (MAE) method

Computer VisionTransformers

A large-scale image feature extraction model based on Vision Transformer (ViT), pre-trained on the ImageNet-1k dataset using the self-supervised masked autoencoder (MAE) method

Computer VisionTransformers

Vision Transformer (ViT) based image feature extraction model, pre-trained on ImageNet-1k dataset using self-supervised masked autoencoder (MAE) method

Computer VisionTransformers

VideoMAE is a self-supervised pretrained video model based on Masked Autoencoder (MAE), fine-tuned on the Something-Something V2 dataset for video classification tasks.

Computer VisionTransformers

VideoMAE is a video pretraining model based on Masked Autoencoder (MAE), fine-tuned on the Kinetics-400 dataset through self-supervised learning, suitable for video classification tasks.

Computer VisionTransformers

VideoMAE is a video self-supervised pretraining model based on Masked Autoencoder (MAE), which learns internal video representations by predicting pixel values of masked video patches.

Computer VisionTransformers

VideoMAE is a video self-supervised pretraining model based on Masked Autoencoder (MAE), fine-tuned on the Something-Something-v2 dataset for video classification tasks.

Computer VisionTransformers

VideoMAE is a self-supervised pretraining model for videos based on Masked Autoencoder (MAE), pretrained for 800 epochs on the Something-Something-v2 dataset.

Computer VisionTransformers