caudwell-9b-v0 / README.md
steinzer-narayan's picture
Update README.md
7b6f46b verified
metadata
license: cc-by-nc-sa-4.0

Experimental de-slopped, de-aligned, EQ-tuned model trained via ORPO on 4k synthetic pairs on a single A100 for 3 epochs; inspired by Gutenberg-DPO.

Despite success on the de-slopping front, I seem to have totalled the model's prefrontal cortex in the process. So it goes. Training data is everything.