PikachuXiaoWang/llama-3.1-8b-smoothquant-w8a8

LLaMA-3 8B SmoothQuant W8A8

This is a quantized version of Meta's LLaMA-3 8B model using SmoothQuant technique.

Model Details

• —Base model: Meta-Llama-3.1-8B-Instruct
• —Quantization: SmoothQuant (W8A8)
• —Smooth factor: 0.85