# Autoregressive text generation

This SMT model was fine-tuned on the Camera GrandStaff piano sheet dataset for piano sheet image transcription tasks.

A 7B-parameter open-source large language model developed by Meta AI, based on Transformer architecture, supporting multilingual processing including Chinese and English

Donut is an OCR-free document understanding Transformer model that combines a visual encoder and text decoder for document visual question answering tasks.

GPT-2 is an autoregressive language model based on the Transformer architecture. It is pre-trained on a large-scale English corpus through self-supervised learning and excels at text generation tasks.

CPM is a Transformer-based 2.6 billion-parameter Chinese pre-trained language model, trained on 100GB of Chinese corpus, supporting various natural language processing tasks.

Norwegian fine-tuned version based on GPT-J 6B, Transformer model with 6 billion parameters