Scaling Diffusion Language Models via Adaptation from Autoregressive Models
This work addresses the problem of inefficient scaling for diffusion language models, offering a practical solution for researchers and practitioners by leveraging pre-trained models, though it is incremental as it builds on existing autoregressive frameworks.
The authors tackled the challenge of scaling diffusion language models by adapting existing autoregressive models, showing that converted models like DiffuGPT and DiffuLLaMA outperform earlier diffusion models and are competitive with their autoregressive counterparts using less than 200B tokens for training.
Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models. However, current DLMs have been studied at a smaller scale compared to their AR counterparts and lack fair comparison on language modeling benchmarks. Additionally, training diffusion models from scratch at scale remains challenging. Given the prevalence of open-source AR language models, we propose adapting these models to build text diffusion models. We demonstrate connections between AR and diffusion modeling objectives and introduce a simple continual pre-training approach for training diffusion models. Through systematic evaluation on language modeling, reasoning, and commonsense benchmarks, we show that we can convert AR models ranging from 127M to 7B parameters (GPT2 and LLaMA) into diffusion models DiffuGPT and DiffuLLaMA, using less than 200B tokens for training. Our experimental results reveal that these models outperform earlier DLMs and are competitive with their AR counterparts. We release a suite of DLMs (127M-355M-7B) capable of generating fluent text, performing in-context learning, filling in the middle without prompt re-ordering, and following instructions https://github.com/HKUNLP/DiffuLLaMA.