conftrace_

ultra-low precision

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model compression (3) quantization-aware training (2) knowledge distillation (2) large language model (1) transformer model (1) group-wise quantization (1) mix-precision quantization (1) hessian analysis (1) parameter compression (1) weight quantization (1)

Papers

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation ACL 2024 Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers EACL 2023 Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT AAAI 2020