17 comments

[ 0.28 ms ] story [ 17.1 ms ] thread
[flagged]
Woah cool idea. So it's almost a drop-in replacement for a typical Jev setup that just reduces your jev bill over time ?
Thanks.

Drop-in yes: point TYPESAFE_BASE_URL at it and nothing else changes.

Isn't this against their ToS? Useful for hobby stuff.
It would be great if we could correct Jev's incorrect answers, even on a separate endpoint. Let me tell it what Jev got wrong.

What type of head is that? What type of model is that head part of?

[dead]
Yeah, I kinda figured that head was the whole model, the way you phrased it. scikit-learn?
I am struggling to see how this page could become less informative. It contains absolutely 0 useful information. What does it actually train?
Is the local model similar to model2vec?
(comment deleted)
This will only work for simple text classification tasks, which is the least interesting possible use of Jev.
Obviously it only helps when the same question is asked many times, but that's the case it's built for, and the case I have, every Jev question in my other project repeats thousands of times, and most Jev uses I've seen online look the same