News for hackers. Stuff that matters.
Re:Web LLM – WebGPU Powered Inference of Large Language Models by dwheeler on Saturday April 15, 2023 @08:33PM (#35586068)
That is for code to download the model, not for the model itself.
Re:Web LLM – WebGPU Powered Inference of Large Language Models by jerpint on Sunday April 16, 2023 @07:11AM (#35588976)
They actually reimplemented the code to load the model. But it’s not clear if the weights of the model are free to use or not
Re:Web LLM – WebGPU Powered Inference of Large Language Models by Tepix on Sunday April 16, 2023 @02:50PM (#35593103)
What do you mean, it's not clear?

https://github.com/facebookresearch/llama links to

https://forms.gle/jk851eBVbX1m5TAv5 which contains LLaMA license agreement below the form.

Re:Web LLM – WebGPU Powered Inference of Large Language Models by dwheeler on Sunday April 16, 2023 @03:50PM (#35593666)
Ok, all evidence I can find is that the LLaMA model is not open source, and the article is just wrong. Software != model. If someone has evidence otherwise, please post.