Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

云队友AI ·

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Source:Hugging Face

Read original ↗
Share