Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
This addresses deployment challenges for large generative language models by reducing model size with minimal performance loss, though it is incremental as it builds on existing quantization-aware training methods.
The paper tackles the accuracy loss in quantized generative language models by proposing token-scaled logit distillation, achieving less than 1.0 degradation in perplexity and improved accuracy in tasks like common-sense QA and arithmetic reasoning.
Generative Language Models (GLMs) have shown impressive performance in tasks such as text generation, understanding, and reasoning. However, the large model size poses challenges for practical deployment. To solve this problem, Quantization-Aware Training (QAT) has become increasingly popular. However, current QAT methods for generative models have resulted in a noticeable loss of accuracy. To counteract this issue, we propose a novel knowledge distillation method specifically designed for GLMs. Our method, called token-scaled logit distillation, prevents overfitting and provides superior learning from the teacher model and ground truth. This research marks the first evaluation of ternary weight quantization-aware training of large-scale GLMs with less than 1.0 degradation in perplexity and achieves enhanced accuracy in tasks like common-sense QA and arithmetic reasoning as well as natural language understanding. Our code is available at https://github.com/aiha-lab/TSLD.