EttinX Cross-Encoder: Natural Language Inference (NLI)

This cross encoder performs sequence classification for contradiction/neutral/entailment labels. This has drop-in compatibility with comparable sentence transformers cross encoders.

To train this model, I added teacher logits to the all-nli dataset dleemiller/all-nli-distill from the dleemiller/ModernCE-large-nli model. This significantly improves performance above standard training.

This 17m architecture is based on ModernBERT and is an excellent candidate for lightweight CPU inference.

Features

High performing: Achieves 80.47% and 86.95% (Micro F1) on MNLI mismatched and SNLI test.
Efficient architecture: Based on the Ettin-17m encoder design (17M parameters), offering faster inference speeds.
Extended context length: Processes sequences up to 8192 tokens, great for LLM output evals.

Performance

Model	MNLI Mismatched	SNLI Test	Context Length	# Parameters
`dleemiller/ModernCE-large-nli`	0.9202	0.9110	8192	395M
`dleemiller/ModernCE-base-nli`	0.9034	0.9025	8192	149M
`cross-encoder/deberta-v3-large`	0.9049	0.9220	512	435M
`cross-encoder/deberta-v3-base`	0.9004	0.9234	512	184M
`cross-encoder/nli-distilroberta-base`	0.8398	0.8838	512	82M
`dleemiller/EttinX-nli-xxs`	0.8047	0.8695	8192	17M

Usage

To use EttinX for NLI tasks, you can load the model with the Hugging Face sentence-transformers library:

from sentence_transformers import CrossEncoder

# Load EttinX model
model = CrossEncoder("dleemiller/EttinX-nli-xxs")

scores = model.predict([
    ('A man is eating pizza', 'A man eats something'),
    ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')
])

# Convert scores to labels
label_mapping = ['contradiction', 'entailment', 'neutral']
labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
# ['entailment', 'contradiction']

Training Details

Pretraining

We initialize the `` weights.

Details:

Batch size: 512
Learning rate: 1e-4
Attention Dropout: attention dropout 0.1

Fine-Tuning

Fine-tuning was performed on the dleemiller/all-nli-distill dataset.

Validation Results

The model achieved the following test set micro f1 performance after fine-tuning:

MNLI Unmatched: 0.8047
SNLI: 0.8695

Model Card

Architecture: Ettin-encoder-17m
Fine-Tuning Data: dleemiller/all-nli-distill

Thank You

Thanks to the Johns Hopkins team for providing the ModernBERT models, and the Sentence Transformers team for their leadership in transformer encoder models.

Citation

If you use this model in your research, please cite:

@misc{moderncenli2025,
  author = {Miller, D. Lee},
  title = {EttinX NLI: An NLI cross encoder model},
  year = {2025},
  publisher = {Hugging Face Hub},
  url = {https://huggingface.co/dleemiller/EttinX-nli-xxs},
}