Modelpublic

amd/gemma-2-2b-onnx-ryzenai-hybrid

sourceHugging Facegemmaupdated 1y agoView on Hugging Face

0likes13downloads

Model Card

amd/gemma-2-2b

—## Introduction This model was created using Quark Quantization, followed by OGA Model Builder, and finalized with post-processing for NPU deployment.
—## Quantization Strategy
—AWQ / Group 128 / Asymmetric / BFP16 activations / UINT4 weights

—## Quick Start For quickstart, refer to Ryzen AI doucmentation

Evaluation scores

The MMLU scores are, astronomy: 55.26, philosophy: 56.91 and management: 69.9.

License

Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.