Search Results for author:
Found 3 papers, 2 papers with code
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
Generative Language Models (GLMs) have shown impressive performance in tasks such as text generation, understanding, and reasoning.
Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders
In particular, KD has been employed in quantization-aware training (QAT) of Transformer encoders like BERT to improve the accuracy of the student model with the reduced-precision weight parameters.
NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference
Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
