metadata
license: gpl-3.0
language:
- en
These are just a couple of LoRAs you can use with https://huggingface.co/Neko-Institute-of-Science/LLaMA-7B-4bit-128g to make sure that 4bit LoRAs are loading the way you expect them to.
These models do what is on the label AAAAAAA will almost always ouput nothing but a stream of the letter "A". BBBBBBB will do the same for "B".
I decided to make these because it was frustrating trying to figure out whether models were actually loading the way I expected them to. You could obviously set your parameters and seed to the same thing and do a couple generations to test, but this is a lot easier to see.