Efficient-ML/LLaMA-3-8B-GPTQ-4bit-b128
Updated
•
3
LLaMA3-Quantization
This is the official quantized models collection of “How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study”
-
-
Efficient-ML/LLaMA-3-8B-SmoothQuant-4bit-4bit
Text Generation • Updated • 10 -
Efficient-ML/LLaMA-3-8B-AWQ-4bit-b128
Text Generation • Updated • 8 -
Efficient-ML/LLaMA-3-8B-SmoothQuant-8bit-8bit
Text Generation • Updated • 12 -
Efficient-ML/LLaMA-3-8B-QuIP-2bit
Text Generation • Updated • 9 • 3 -
Efficient-ML/LLaMA-3-8B-DB-LLM-2bit-fake
Text Generation • Updated • 12 • 2 -
Efficient-ML/LLaMA-3-8B-PB-LLM-1.7bit-fake
Text Generation • Updated • 10 • 1 -
Efficient-ML/LLaMA-3-8B-BiLLM-1.1bit-fake
Updated -
How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study
Paper • 2404.14047 • Published • 46