Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
Paper
• 2510.15061 • Published
• 1
EXL3 4.0bpw H6 quant (quatized with exllamav3 0.0.12)
Original: sam-paech/Mistral-Small-3_2-24B-Instruct-2506-antislop
A fine-tune of Mistral-Small-3_2-24B-Instruct-2506 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.
https://github.com/sam-paech/auto-antislop
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.
- Downloads last month
- -