Downloads · 30 days
0
gpt-oss-20b-onnx-ryzenai-npu
amd/gpt-oss-20b-onnx-ryzenai-npu
gpt-oss-20b-onnx-ryzenai-npu is a machine learning model from amd. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is based on the optimized versions of gpt-oss-20b available here gpt-oss-20b-onnx, followed by necessary post-processing.
Access
Public
Updated Dec 13, 2025
Repo size
13.4 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin12.2 GB · 91%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 13, 2025
- Updated
- Dec 13, 2025
- SHA
- dc9ddd19
Base models
Model card
From the Hugging Face model README
amd/gpt-oss-20b ONNX Models
Introduction
This model is based on the optimized versions of gpt-oss-20b available here gpt-oss-20b-onnx, followed by necessary post-processing.
Evaluation scores
The perplexity measurement is run on the wikitext-2-raw-v1 (raw data) dataset provided by Hugging Face. Perplexity score measured for prompt length 2k is 201.6482.
Base Model Information
See HF link gpt-oss-20b for details.
License
Modifications copyright(c) 2025 Advanced Micro Devices,Inc. All rights reserved.
MIT License
Copyright (c) 2025 Advanced Micro Devices, Inc
- License: Apache-2.0
- License Description: Use of this model is subject to the terms of the Apache License, Version 2.0, available at https://www.apache.org/licenses/LICENSE-2.0.
- License
- apache-2.0
- Languages
- en
- Created
- Dec 13, 2025
- Updated
- Dec 13, 2025