dankle

What is the benefit of this lib over hf transformers?

This is fucking amazing!! Love to see it, very interesting future for folks with t1d now, both re tools like this and new potential cures in the pipe.

”451: Unavailable due to legal reasons

We recognize you are attempting to access this website from a country belonging to the European Economic Area (EEA) including the EU which enforces the General Data Protection Regulation (GDPR) and therefore access cannot be granted at this time. For any issues, contact support@wvgazettemail.com or call 304-348-5140.”

Sounds like an amazing site

Good

All solid tumors or all solid tumors with a specific mutation in PCNA? Big difference…

At the current rate, nothing will outlast the Russaian govt.

Right

Yes, but in consumer hardware, their silicon outperforms the competition.

So if you feed the model weird shit, you get weird shit back. Great.

Let's hope this one never gets completed. This is ancient tech the world no longer needs. Assuming that it can't be converted into a modern nuclear plant, that is.

Cant reach the site. Alt link available?

Is it good?

Very cool, well done ! Are model code & weights open source?

But why????

Develop on a tiny slice of you dataset locally of you must. Then train properly elsewhere (in the cloud of your choice)

Nice, looking forward to trying it.

Better than streamlit??

Sourceforge is still around?

> There is a significant gap between how software is currently developed in this space versus how it should be developed. The vast majority of genomics-related software is not written with speed or reliability in mind.

True, but working in academia is very VERY different working in a tech/product company.

”National” meaning US, yet again.

Will this enable tensorflow in docker on apple silicon?

Same. I have an ’alias fgr=”find|grep”. Stupid but gets the job done.

IRR means… what?

Mine has 5G now!

Is there anything new about this? It's been out for ages.

I'm not particularly concerned about this tbh. What I mean is that ML is highly relevant with less resources as well, and the fact the only a handful companies or research groups have the financial power to push the state of the art isn't really a problem.

Oh my, that’s just terrible. Really hoping this pep wont make it all the way. 100% unreadable.

Yuck, python is losing its zen and gets uglier and uglier.

Getting 403 Forbidden. Did my isp block it, or it this an error on their end?

> Anyways, I plan to eventually open source it. There's a lot of stuff in the code I want to clean up (things like setting up the build environment, some of the uglier hacks, etc.) before I feel comfortable releasing it to the public

I hate seeing this. We all write some ugly hacks. Just release it and work on it in public, it's fine.