Recent submissions

Comment · 5 years ago
Thanks for your feedback! Indeed we tested it mostly for firefox & chrome compatibility for now
Comment · 5 years ago
As stated in readme, the dataset is downloadable from our website
Comment · 5 years ago
yes, we got quite a long queue :D
Comment · 5 years ago
Comment · 5 years ago
Hi, after gathering the model and tokenizer, you can use the generic huggingface tutorial for text generation: https://huggingface.co/blog/how-to-generate

We use custom control tokens, so you have to provide the specific structure of the recipe, simply typing it in the huggingface prompt won't work. The details are available in our papers about the solution.

Comment · 5 years ago
Good question! I'd say, ultimate task is to achieve both, but what is fully achievable atm is to get the right recipe structure. The idea of "validity" is very hard to evaluate and often has high regional and personal variance, but many teams around the world are working on this problem at the moment!
Comment · 5 years ago
Hard to say per recipe, as in the current setup they are generated on demand and not pre-generated. But as you can see, we're hosting the solution in academia so it's basically for free vs around 2$/hour with GPU on AWS

Yes, you might be right about the timer, we'll think about changing it!

Comment · 5 years ago
Comment · 8 years ago
I'm truly impressed how wide the response is. It makes me sure that this project is truly worth continuing. Thanks HN!
Comment · 8 years ago
I agree, I don't claim it's ready Please, treat it as interesting project to follow that has just started, and is surely not meant to be deployed in production environments, at least not in this state
Comment · 8 years ago
Currently we have only what CapacitorSet prepared: https://github.com/Glorf/lear/issues/1 I'll try to fix HTTP/1.0 support and post some more detailed benchmark in few hours

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton