Can i get the API for this so I can make an app with it?
Hey all, I am pretty new to the field of AI app development, and I am mainly targeting the method of getting an AI API and implementing it within the app I make. Can I do the same with this particular model?
https://huggingface.co/google/gemma-2-2b-it/discussions/21?inference_api=true should be able to help you out :)
Just note that the free Inference API is subject to rate limits and usage demands. If you need an inference solution for production, check out Inference Endpoints instead.
Very few models are "plug and play" with inference endpoints and usually need a sample "handler.py" file after cloning the repository for it to work properly. Is this documentation you can provide to support more seamless deployments? Qwen models are the only ones that deploy seamlessly that I've tried.