Comparison of Weight-Only Quantization (WOQ) models in Large Language Models
收藏数据链接:
官方服务:
资源简介:
This comparison explored 10 Weight-Only Quantization (WOQ) models and compared their specific characteristics such as main LLMs, bit widths, perplexity differences. Weight-Only Quantization concentrated on compressing model weights for enhancing the efficiency.
创建时间:
2025-04-30



