feat: 🚀 add YOLOE-11S model deployment for replicate

[onuralpszr]

• Text Prompt added
• Text Prompt free added (no class names will be enough, description also added)

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

This update adds support for deploying the new YOLOE-11S model on Replicate, making it easier to run real-time object detection demos using Ultralytics models. 🚀🖼️

📊 Key Changes

• Added deployment files and documentation for the YOLOE-11S model, including:
  • A new yoloe11s directory with README.md, cog.yaml, download.py, and predict.py.
  • Instructions and configuration for running YOLOE-11S on Replicate (CPU-only, Python 3.12, PyTorch 2.3.1+).
  • Support for custom class names and output formats (image and optional JSON).
• Updated the GitHub Actions workflow to include YOLOE-11S in the test matrix.
• Expanded .gitignore to exclude additional file types and Replicate deployment files.
• Minor docstring improvement in yolo11n/predict.py for clarity.

🎯 Purpose & Impact

• Broader Model Access: Users can now easily deploy and test the YOLOE-11S model on Replicate, expanding the range of available Ultralytics models. 🌍
• Flexible Inference: Supports custom class filtering and both image/JSON outputs, making it suitable for diverse use cases.
• Streamlined Deployment: Automated weight downloading and clear setup instructions simplify the deployment process.
• Improved Workflow: Enhanced CI/CD ensures YOLOE-11S is tested alongside other models, maintaining reliability.

Overall, this PR makes it easier for users and developers to experiment with and deploy the latest Ultralytics models in cloud environments.

[UltralyticsAssistant]

👋 Hello @onuralpszr, thank you for submitting a PR to ultralytics/replicate 🚀! This is an automated response to help streamline the review process. An Ultralytics engineer will review and assist you soon.

Please review the checklist below to ensure your PR is ready for integration:

• ✅ Define a Purpose: Clearly explain the purpose of your fix or feature in your PR description, and link to any relevant issues. Make sure your commit messages are clear, concise, and follow our conventions.
• ✅ Synchronize with Source: Confirm your PR is up-to-date with the main branch of ultralytics/replicate. If it is out of sync, update by clicking the 'Update branch' button or by running git pull and git merge main locally.
• ✅ Ensure CI Checks Pass: Verify that all Ultralytics Continuous Integration (CI) checks are passing. Please address any issues if checks fail.
• ✅ Update Documentation: Update the documentation for any new or modified features as needed.
• ✅ Add Tests: If applicable, include or update tests to cover your changes, and confirm all tests pass.
• ✅ Sign the CLA: Please ensure you have signed our Contributor License Agreement (CLA) if this is your first PR to Ultralytics. To sign, write "I have read the CLA Document and I sign the CLA" in a new message.
• ✅ Minimize Changes: Limit your changes to the minimum necessary for your bug fix or feature addition. "It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is." — Bruce Lee

For more information, please see our Contributing Guide. If you have any questions, feel free to leave a comment below.

Thank you for helping improve Ultralytics! 🚀🤖

[onuralpszr]

@glenn-jocher it is ready for you to check

URL : https://replicate.com/ultralytics/yoloe-11s

I also include filled informations in replicate and added examples mostly it should be complete

[onuralpszr]

@glenn-jocher are you working on it ? shall I finish it ?

[glenn-jocher]

@onuralpszr cleaned it up a bit. Done now!

Please make any additional changes and then we can merge.

[onuralpszr]

@onuralpszr cleaned it up a bit. Done now!

Please make any additional changes and then we can merge.

Okay thank you. Let me quickly finish up

[onuralpszr]

@glenn-jocher all done, fix the small typo in CI and rest fine. Thank you in advance :)

[glenn-jocher]

@onuralpszr merged!

[UltralyticsAssistant]

Fantastic work, @onuralpszr and @glenn-jocher! 🚀 Your efforts bringing YOLOE-11S deployment to Replicate mark a big step forward for Ultralytics models in the cloud. As Helen Keller said, "Alone we can do so little; together we can do so much." This collaboration empowers our community to access and experiment with state-of-the-art real-time object detection more easily than ever. Thank you both for your dedication and for making Ultralytics HUB even more accessible and impactful! 👏

[onuralpszr]

@onuralpszr merged!

Thank you ! :)