Beyond Language Models: Byte Models are Digital World Simulators
This provides a new approach for simulating digital systems, potentially impacting fields like hardware diagnostics and algorithm analysis, though it builds incrementally on token prediction methods.
The paper tackled the problem of simulating the digital world by predicting bytes, introducing bGPT which matches specialized models across modalities and achieves a 0.0011 bits per byte error rate in music conversion and over 99.99% accuracy in CPU simulation.
Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format. Inspired by the success of next token prediction in natural language processing, we introduce bGPT, a model with next byte prediction to simulate the digital world. bGPT matches specialized models in performance across various modalities, including text, audio, and images, and offers new possibilities for predicting, simulating, and diagnosing algorithm or hardware behaviour. It has almost flawlessly replicated the process of converting symbolic music data, achieving a low error rate of 0.0011 bits per byte in converting ABC notation to MIDI format. In addition, bGPT demonstrates exceptional capabilities in simulating CPU behaviour, with an accuracy exceeding 99.99% in executing various operations. Leveraging next byte prediction, models like bGPT can directly learn from vast binary data, effectively simulating the intricate patterns of the digital world.