We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The performance of neural networks improves when more parameters are used. However, the model sizes are constrained by the available on-device memory during training and inference. Although applying techniques like quantization can alleviate the constraint, they suffer from performance degradation. In this work, we introduce NeuZip, a new weight compression scheme based on the entropy of floating-point numbers in neural networks. With NeuZip, we are able to achieve memory-efficient training and inference without sacrificing performance. Notably, we significantly reduce the memory footprint of training a Llama-3 8B model from 31GB to less than 16GB, while keeping the training dynamics fully unchanged. In inference, our method can reduce memory usage by more than half while maintaining near-lossless performance. Our code is publicly available.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.20650")
get_code_for_paper("2410.20650")
have("2410.20650")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.20650.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.20650)
Connect an agent — have() is free.