I attempted to quantize ResNet18, a commonly used neural network for image recognition, using BitNetb158's quantization technique, reducing it to 1.58 bits.
github.com/yukiharada12...
github.com/yukiharada12...
GitHub - yukiharada1228/BitNetb158: Implemented various networks using quantization proposed in The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.
Implemented various networks using quantization proposed in The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits. - yukiharada1228/BitNetb158
github.com
April 5, 2024 at 9:56 PM
I attempted to quantize ResNet18, a commonly used neural network for image recognition, using BitNetb158's quantization technique, reducing it to 1.58 bits.
github.com/yukiharada12...
github.com/yukiharada12...
