sam-paech's picture
Create README.md
ecd2ddb verified
|
raw
history blame
414 Bytes

A fine-tune of google/gemma-3-12b-it using a new experimental technique for automatic unslopping.

The intention is to make the most common slop words & phrases much less frequent, with minimal impact to the model otherwise.

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.