amd/gpt-oss-20b-onnx-ryzenai-npu

By amd · ↓ 0 · ♥ 1 · Updated 2025-12-13

What's in this repo

This page lists the files in amd/gpt-oss-20b-onnx-ryzenai-npu, including GPT-OSS-npu.onnx.

1 ONNX models (.onnx files)
13 files, including 4 .json, 2 .bin, 1 .onnx, 1 .data, 1 .md, 1 .jinja
Last updated 2025-12-13

ONNX files

File	Size	Download
GPT-OSS-npu.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

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

MIT License

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.

Model info

onnx amd ONNX ONNXRuntime en base_model:onnxruntime/gpt-oss-20b-onnx base_model:quantized:onnxruntime/gpt-oss-20b-onnx license:apache-2.0 region:us

↓ 0 ♥ 1

Created: 2025-12-13

Updated: 2025-12-13

View on Hugging Face

Files (13)

.gitattributes

GPT-OSS-npu.bin

GPT-OSS-npu.onnx ONNX

GPT-OSS-npu.onnx.data

GPT-OSS-npu.pb.bin

LICENSE

README.md

chat_template.jinja

genai_config.json

model_benchmark.exe

special_tokens_map.json

tokenizer.json

tokenizer_config.json

Related models

More models

No task type declared.