numen-tech
/

Gemma-2-9B-It-SPPO-Iter3-w4a16g128asym

Text Generation

4-bit precision

Model card Files Files and versions

4-bit OmniQuant quantized version of Gemma-2-9B-It-SPPO-Iter3.

Downloads last month: -

Model tree for numen-tech/Gemma-2-9B-It-SPPO-Iter3-w4a16g128asym

Base model

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

Quantized

(26)

this model

Paper for numen-tech/Gemma-2-9B-It-SPPO-Iter3-w4a16g128asym

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Paper • 2308.13137 • Published Aug 25, 2023 • 20