Nimbz/

sam-paech_gemma-3-27b-it-antislop_4.0bpw_H6_EXL3

EXL3 4.0bpw H6 quant (quatized with exllamav3 0.0.12)

Original: sam-paech/gemma-3-27b-it-antislop

A fine-tune of google/gemma-3-27b-it using the antislop method described in this paper: https://arxiv.org/abs/2510.15061

The pipeline identifies the model's unique slop (over-represented words and phrases compared to human writing), generates a preference training set, and trains out the slop with our FTPO training algorithm.

This process alters the model to make the most common slop words & phrases much less frequent, with minimal impact or degradation to the model.

It won't remove slop entirely. The technique only targets over-represented words & phrases, not stylistic or thematic slop.

This model should serve as a good base for further fine-tuning.