mika6996

This model any good?

Why is this better than rsync?

Then recommend a better explanation?

But you can't just switch between installed models like in ollama, can you?

You sure this works? inline_completion and chat_panel give me "Property inline_completion is not allowed." - not sure if this works regardless?

What would tinygrad replace if they continue to proceed like this?

Who likes this bullshit of ads anyway?

Did you try this method on any model? What do benchmarks say?

Somebody with an archive of this article?

I really love the recommended background music while reading this article. More blogs should adopt that - really quirky.

Does anybody really think this is a plausible theory?

Which LLM is running with Harper?

I do not like this. Visiting the site automatically downloads an executable - seriously?

The site returns: "Sorry, you don't have access to this page. This is usually because the post in question has been removed by the author."

This. Your work is very likely to be unintentionally ignored by the mass of work on this topic.

Has your paper been peer-reviewed by leading scientists?

Are the tenstorrent blackhole cards anyhow competitive?

AMD is finally starting to make progress with their software stack. Who would have thought?

I think it should be taught, not thought.

What is a good introduction for this topic?

What are use cases for such long cables?

Is this site using Uptime Kuma?

Servus! Englisches README hilft bestimmt für mehr Reichweite.

What is this used for?

Any future plans for linux support?

I tried the example provided but it is not working. Are AMD GPUs supported?

Thanks man!

How can I flag this post?

Thanks alot for your article! Do you know by any chance how to train FLUX.1 LORA locally?

When does one need to use this?