Modelpublic

amd/SmolLM-135M-Instruct-onnx-ryzenai-1.7-hybrid

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

0likes

Model Card

amd/SmolLM-135M-Instruct-onnx-ryzenai-1.7-hybrid

—## Introduction This model was prepared using the AMD Quark Quantization tool, followed by necessary post-processing.

—## Quantization Strategy
—AWQ / Group 128 / Asymmetric / UINT4 Weights / BFP16 activations
—Excluded Layers: None

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

License

Modifications copyright(c) 2026 Advanced Micro Devices,Inc. All rights reserved.

MIT License

Copyright (c) 2026 Advanced Micro Devices, Inc