Marxish / README.md
ericpolewski's picture
Update README.md
e79f13c
|
raw
history blame
300 Bytes
metadata
license: mit

This is a frankensteined Marx3b-v2 model (https://huggingface.co/acrastt/Marx-3B-V2)

It is approximately 4.5b. Just testing things out.

bfloat16

Used the same model 4 times. I fine-tuned it at r 256 but used the wrong alpaca format so I'll need to re-upload that merged model.