# Small-scale training

This is a Vision Transformer (ViT) model fine-tuned on an image classification task based on the tiny-random-vit architecture, achieving 66.47% accuracy on the evaluation set.

This is a small randomly initialized model based on the BERT architecture, processed using sharding technology.

This model is a speech recognition model fine-tuned on an unknown dataset based on facebook/wav2vec2-base, primarily used for Automatic Speech Recognition (ASR) tasks.

This is a Reformer language model trained on Dostoevsky's novel 'Crime and Punishment', capable of generating text in a style similar to the original work.