Comment by rayiner
8 days ago
Weights being open isn't like code being open. With code, you can inspect the code to see what it will do. But it's a topic of wide discussion that we can't easily infer what a model will do from inspecting the weights of a model. The process has emergent behaviors we can't predict.
Perhaps something like
"Open weights" is just a binary blob you are allowed to copy.
The equivalent of a gratis non-open source app.
Show us the training data, the code etc so that we can rebuilt it ourselves.
Unfortunately even if you had all that you still wouldn't be rebuilding it yourself.
The ?? Is training recipes & datasets
Maybe, but it's a lot of data and the er, compiling process is not necessarily easy to reproduce.
1 reply →
Everyone's saying LLMs are like lossy zips. tar should support GGUF compression someday.