Downloads · 30 days
10
13% of all-time downloads
gemma-dseparation-baseline
ludwigw/gemma-dseparation-baseline
gemma-dseparation-baseline is a machine learning model from ludwigw. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Standard fine-tuned Gemma 270M-IT on d-separation task without semantic loss. Exhibits model collapse — predicts near-constant "No" (7.6% F1). Provided for reproducibility and as a negative baseline.
All-time downloads
76
Public
Parameters
271M
426 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors388 MB · 91%
Parameter types
How the weights are stored.
BF16168M · 62%
Base models
Model card
From the Hugging Face model README
Gemma D-Separation Baseline (Collapsed)
Standard fine-tuned Gemma 270M-IT on d-separation task without semantic loss. Exhibits model collapse — predicts near-constant "No" (7.6% F1). Provided for reproducibility and as a negative baseline.
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ludwigw/gemma-dseparation-baseline")
tokenizer = AutoTokenizer.from_pretrained("ludwigw/gemma-dseparation-baseline")
Citation
@article{deshmukh2026semantic,
title={On Semantic Loss Fine-Tuning Approach for Preventing Model Collapse in Causal Reasoning},
author={Deshmukh, Pratik and Gupta, Atirek},
journal={arXiv preprint arXiv:2605.05438},
year={2026}
}
- Type
- gemma3_text
- License
- mit
- Languages
- en
- Created
- Mar 19, 2026
- Updated
- May 8, 2026