Optimal-Brain-Resotration - a HangGuo Collection

HangGuo 's Collections

Optimal-Brain-Resotration

Optimal-Brain-Resotration

updated Sep 26

The model collection of paper: Optimal Brain Restoration for Joint Sparsification and Quantization of LLMs. Github: https://github.com/csguoh/OBR

HangGuo/Llama2-70B-QuaRot-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 22 • 1
HangGuo/Llama2-70B-SpinQuant-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 3
HangGuo/Llama3-70B-SpinQuant-OBR-RTN-W4A4KV4S50

Text Generation • Updated Sep 26 • 4
HangGuo/Llama2-70B-SpinQuant-OBR-RTN-W4A4KV4S50

Text Generation • Updated Sep 26 • 3
HangGuo/Llama2-70B-QuaRot-OBR-RTN-W4A4KV4S50

Text Generation • Updated Sep 26 • 12
HangGuo/Llama3-70B-SpinQuant-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 3
HangGuo/Llama2-7B-QuaRot-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 12
HangGuo/Llama3-70B-QuaRot-OBR-GPTQ-W4A4KV16S50

Text Generation • Updated Sep 26 • 11
HangGuo/Llama3-70B-QuaRot-OBR-RTN-W4A4KV16S50

Text Generation • Updated Sep 26 • 11
HangGuo/QWen2.5-7B-FlatQuant-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 9
HangGuo/QWen2.5-32B-FlatQuant-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 8
HangGuo/QWen2.5-3B-FlatQuant-OBR-GPTQ-W4A8KV16S50

Text Generation • Updated Sep 26 • 13
HangGuo/QWen2.5-1.5B-FlatQuant-OBR-GPTQ-W4A8KV16S50

Text Generation • Updated Sep 26 • 6
HangGuo/QWen2.5-3B-FlatQuant-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 10
HangGuo/QWen2.5-1.5B-FlatQuant-OBR-GPTQ-W4A4KV4S50

Text Generation • Updated Sep 26 • 12
Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

Paper • 2509.11177 • Published Sep 14 • 2