Show HN: Gradient – a web API for fine-tuning and deploying Llama2

by chrchang510on 8/29/23, 3:34 PMwith 8 comments
by azirbelon 8/29/23, 3:58 PM

This looks great. I found the docs helpful for getting a clear idea of what it does: https://docs.gradient.ai/docs/introduction

by yangboon 8/29/23, 4:28 PM

I am a developer from Gradient. I think the most interesting use case of our product is interactive few-shot fine-tuning in a Jupyter Notebook. When fine-tuning a model with less than 10 samples and around 3 epoch, it can learn knowledge in a couple of seconds, then you can immediately get the fine-tuned model.

The experience is like to be your model's private tutor. It just continuously learns new things you told it, like a life.

Be cautious about your learning rate, or it will go mad.

by ernest3on 8/29/23, 5:07 PM

As someone who has spent way too much time fine-tuning model parameters, I am grateful for this service!

by unicornsprinkleon 8/29/23, 5:10 PM

Amazing solution for API latency, love that the product comes with regulation compliance!

by Jp6hBY06on 8/29/23, 5:23 PM

Great stuff. Looking forward to learning more!

by xiaoqiao10on 8/30/23, 12:52 PM

Looks awesome! Congrats on the launch

by rchin57on 8/29/23, 4:11 PM

Great job!