This model is a fine-tune of the excellent tasksource/ModernBERT-large-nli, trained on the dleemiller/FineCat-NLI dataset—a compilation of several high-quality NLI data sources with quality screening and reduction of easy samples in the training split. The training also incorporates logit distillation from MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli, a top-performing NLI model, particularly on ANLI benchmarks.

Distillation loss looks like this: $$ \begin{equation} \mathcal{L} = \alpha \cdot \mathcal{L}{\text{CE}}(z^{(s)}, y) + \beta \cdot \mathcal{L}{\text{MSE}}(z^{(s)}, z^{(t)}) \end{equation} $$

where $z^{(s)}$ and $z^{(t)}$ are the student and teacher logits, $y$ are the ground truth labels, and $\alpha$ and $\beta$ are equally weighted at 0.5.

By combining the broad NLI training of the tasksource model (which excels on traditional MNLI/SNLI benchmarks) with the ANLI strengths of the MoritzLaurer model and the high-quality FineCat-NLI dataset, this model achieves strong performance across major NLI benchmarks while retaining the efficiency advantages of the ModernBERT architecture.

This model and dataset specifically targets improving NLI, through high quality sources. The tasksource models are the best checkpoints to start from, although training from ModernBERT is also competitive.

NLI Evaluation Results

F1-Micro scores (equivalent to accuracy) for each dataset. Performance was measured at bs=32 using a Nvidia Blackwell PRO 6000 Max-Q.

Model	finecat	mnli	mnli_mismatched	snli	anli_r1	anli_r2	anli_r3	wanli	lingnli	Throughput (samples/s)	Peak GPU Mem (MB)
`MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli`	0.8233	0.9121	0.9079	0.8898	0.7960	0.6830	0.6400	0.7700	0.8821	454.96	3250.44
`dleemiller/finecat-nli-l`	0.8227	0.9152	0.9265	0.9162	0.7480	0.5700	0.5433	0.7706	0.8742	539.04	1838.06
`tasksource/ModernBERT-large-nli`	0.7959	0.8983	0.9229	0.9188	0.7260	0.5110	0.4925	0.6978	0.8504	543.44	1838.06
`dleemiller/ModernCE-large-nli`	0.7811	0.9088	0.9205	0.9273	0.6630	0.4860	0.4408	0.6576	0.8566	540.74	1838.06
`cross-encoder/nli-deberta-v3-large`	0.7618	0.9019	0.9049	0.9220	0.5300	0.4170	0.3758	0.6548	0.8466	448.35	3250.44

Usage

Label Map:

entailment: 0
neutral: 1
contradiction: 2

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load the model and run inference.

python

from sentence_transformers import CrossEncoder
import numpy as np

model = CrossEncoder("dleemiller/finecat-nli-l")
id2label = model.model.config.id2label  # {0:'entailment', 1:'neutral', 2:'contradiction'}

pairs = [
    ("The glass fell off the counter and shattered on the tile.",
     "The glass broke when it hit the floor."),          # E
    ("The store opens at 9 a.m. every day.",
     "The store opens at 7 a.m. on weekdays."),          # C
    ("A researcher presented results at the conference.",
     "The presentation won the best paper award."),       # N
    ("It started raining heavily, so the match was postponed.",
     "The game was delayed due to weather."),             # E
    ("Every seat on the flight was taken.",
     "There were several empty seats on the plane."),     # C
]

logits = model.predict(pairs)  # shape: (5, 3)

for (prem, hyp), row in zip(pairs, logits):
    pred_idx = int(np.argmax(row))
    pred = id2label[pred_idx]
    print(f"[{pred}]  Premise: {prem}  |  Hypothesis: {hyp}")

Acknowledgments

We thank the creators and contributors of tasksource and MoritzLaurer for making their work available. This model would not be possible without their efforts and open source contributions.

Citation

bibtex

@misc{nli-compiled-2025,
  title = {FineCat NLI Dataset},
  author = {Lee Miller},
  year = {2025},
  howpublished = {Refined compilation of 6 major NLI datasets}
}