Skip to content

Qwen QA Android example using ONNX Runtime #521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 11 commits into
base: main
Choose a base branch
from

Conversation

dineshsoudagar
Copy link

This pull request adds a basic Android example for running Qwen2.5 and Qwen3 models using ONNX Runtime.

  • Uses Hugging Face-style tokenizer.json with BPE.
  • Includes a simple UI for question answering.
  • Supports streaming inference with past key/value cache.
  • Handles special tokens and prompt formatting for Qwen models.
  • Designed to be easy to test and modify.

Tested on Android 14 with Qwen2.5-0.5B and Qwen3 ONNX models.

Let me know if any changes are needed, happy to improve it.

@dineshsoudagar
Copy link
Author

@microsoft-github-policy-service agree

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant