# Autoregressive model

A symbolic audio model based on the Perceiver AR architecture, pre-trained on the GiantMIDI-Piano dataset for symbolic audio generation

CodeGen-HTML 350M is an autoregressive language model fine-tuned from CodeGen-Multi 350M, specifically designed for HTML code generation.

GPT-J 6B is a 6-billion-parameter autoregressive language model trained using the Mesh Transformer JAX framework, employing the same tokenizer as GPT-2/3.

GPT-Neo 125M is a Transformer model based on the GPT-3 architecture, developed by EleutherAI, with 125 million parameters, primarily used for English text generation tasks.