numen-tech
/

gemma-2-2b-it-w4a16g128asym

Text Generation

4-bit precision

Model card Files Files and versions

4-bit OmniQuant quantized version of gemma-2-2b-it.

Downloads last month: -

Model tree for numen-tech/gemma-2-2b-it-w4a16g128asym

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Quantized

(170)

this model

Paper for numen-tech/gemma-2-2b-it-w4a16g128asym

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Paper • 2308.13137 • Published Aug 25, 2023 • 19