Apache - 2.0 - Commercial License about lit-llama HOT 5 CLOSED

The goal of the project is to end up with weights trained from scratch yes. The license on this repo is for the source code, we don't distribute the checkpoints from Meta. So yes users need to get them through the form and can use it only for research purposes as stated there in the agreement. This is temporary until there are checkpoints trained from scratch using the apache code.

from lit-llama.

@Rock-Anderson on top of what @awaelchli said:

if we're still loading official Llama weights (under GPL License)

note that the LLaMA weights from Meta are not GPL licensed. They are released under a custom Meta license:

To maintain integrity and prevent misuse, we are releasing our model under a noncommercial license focused on research use cases. Access to the model will be granted on a case-by-case basis to academic researchers; those affiliated with organizations in government, civil society, and academia; and industry research laboratories around the world. People interested in applying for access can find the link to the application in our research paper.

from https://ai.facebook.com/blog/large-language-model-llama-meta-ai/

from lit-llama.

Got it, thanks for educating, and for this repo contribution.

The Readme mentioned truly open-sourced at the beginning and jumped to the section where we load official Llama weights, so I was confused a bit.

Maybe adding that loading-weights and conversion to Lit-Llama for inference is only for research purposes, would help.
But I guess that is meant to be understandable.
Thanks anyway, closing this.

from lit-llama.

Maybe adding that loading-weights and conversion to Lit-Llama for inference is only for research purposes, would help.

@lantiga Do we want to change the wording in the "use the model" section to mention "for research purposes only" as suggested?

from lit-llama.

Yes for sure, we want there to be no misunderstandings. I’ll change it shortly, thank you @Rock-Anderson for the input

from lit-llama.