BitNet shows that 1-bit Transformers can match the performance of 8-bit and FP16 models on language modeling with much smaller memory footprint and energy use, while following a similar scaling law.
XNOR-Net: imagenet classification using binary convolutional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BitNet: Scaling 1-bit Transformers for Large Language Models
BitNet shows that 1-bit Transformers can match the performance of 8-bit and FP16 models on language modeling with much smaller memory footprint and energy use, while following a similar scaling law.