Show HN: Backprop – a library to easily finetune and use state-of-the-art models

This is a Python library I've been co-authoring for the last few months, with the goal being to make finetuning and using models as easy as possible for devs, even without extensive ML experience.

We've currently got support for text and image-based tasks, with wrappers around models like Google's T5, OpenAI's CLIP, and Facebook's BART, among others (with more on the way).

We've got some features that make deployment for production easy, but for full transparency, deployment is through a paid platform [0] we've developed that is by no means necessary to use the library.

We're happy with the progress we've made, but we're curious to hear what people think so we can improve it in the future.

[0] https://backprop.co

This looks pretty slick! Can you give any sort of average number of seconds your pre-trained models run for? Just curious approximately how many API calls one could make on each tier given the per second usage pricing.