Downloads · 30 days
11
4% of all-time downloads
GLM-4-32B-0414-antislop
sam-paech/GLM-4-32B-0414-antislop
GLM-4-32B-0414-antislop is a machine learning model from sam-paech. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
A fine-tune of THUDM/GLM-4-32B-0414 using the antislop method described in this paper: https://arxiv.org/abs/2510.15061
All-time downloads
255
Public
Parameters
32.6B
65.2 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors65.1 GB · 100%
At a glance
- Model type
- glm4
- Access
- Public
- Created
- Jun 20, 2025
- Updated
- Oct 25, 2025
- SHA
- cb1ad173
Model card
From the Hugging Face model README
A fine-tune of THUDM/GLM-4-32B-0414 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.
- Type
- glm4
- Created
- Jun 20, 2025
- Updated
- Oct 25, 2025