EfficientQAT - a ChenMnZ Collection

ChenMnZ 's Collections

EfficientQAT(w/o E2E-FT)

EfficientQAT(GPTQ format)

EfficientQAT (BitBLAS format)

EfficientQAT

updated Jul 18

The official prequantized EfficientQAT models.

ChenMnZ/Llama-3-8b-instruct-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 2
ChenMnZ/Llama-3-8b-instruct-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 3
ChenMnZ/Llama-3-8b-instruct-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 7
ChenMnZ/Llama-3-8b-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 10
ChenMnZ/Llama-3-8b-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 7
ChenMnZ/Llama-3-8b-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 8
ChenMnZ/Llama-3-8b-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 10
ChenMnZ/Llama-3-70b-instruct-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 4
ChenMnZ/Llama-3-70b-instruct-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 5
ChenMnZ/Llama-3-70b-instruct-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 8
ChenMnZ/Llama-3-70b-instruct-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 4
ChenMnZ/Llama-2-7b-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 9
ChenMnZ/Llama-2-7b-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 9
ChenMnZ/Llama-2-7b-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 8
ChenMnZ/Llama-2-7b-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 16
ChenMnZ/Llama-2-70b-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 5
ChenMnZ/Llama-2-70b-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 6
ChenMnZ/Llama-2-13b-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 2
ChenMnZ/Llama-2-13b-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 5
ChenMnZ/Llama-2-13b-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 5
ChenMnZ/Llama-2-13b-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 3
ChenMnZ/Llama-3-8b-instruct-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 3
ChenMnZ/Llama-3-70b-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 5 • 1
ChenMnZ/Llama-3-70b-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 6 • 1
ChenMnZ/Llama-3-70b-EfficientQAT-w2g64

Text Generation • Updated Jul 22 • 11 • 1
ChenMnZ/Llama-2-70b-EfficientQAT-w4g128

Text Generation • Updated Jul 22 • 4 • 1
ChenMnZ/Llama-2-70b-EfficientQAT-w3g128

Text Generation • Updated Jul 22 • 4 • 1
ChenMnZ/Llama-3-70b-EfficientQAT-w2g128

Text Generation • Updated Jul 22 • 6 • 1
EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Paper • 2407.11062 • Published Jul 10 • 8