onnx-community/Llama-3.2-3B-instruct-hexagon-npu-assets

By onnx-community · ↓ 0 · ♥ 2 · Updated 2025-03-05

What's in this repo

This page lists the files in onnx-community/Llama-3.2-3B-instruct-hexagon-npu-assets, including dequantizer.onnx, position-processor.onnx, position-shifter.onnx and more.

4 ONNX models (.onnx files)
10 files, including 4 .onnx, 4 .json, 1 .md
Last updated 2025-03-05

ONNX files

File	Size	Download
dequantizer.onnx	—	Download
position-processor.onnx	—	Download
position-shifter.onnx	—	Download
quantizer.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

Assets to run Llama 3.2 3B on Hexagon NPU

Add QNN context binaries and ONNX wrapper models to these assets to run on Hexagon NPU

Model info

onnx license:mit region:us

↓ 0 ♥ 2

Created: 2025-03-05

Updated: 2025-03-05

View on Hugging Face

Files (10)

.gitattributes

README.md

dequantizer.onnx ONNX

genai_config.json

position-processor.onnx ONNX

position-shifter.onnx ONNX

quantizer.onnx ONNX

special_tokens_map.json

tokenizer.json

tokenizer_config.json

Related models

More models

No task type declared.