DeBERTa-v3-base -- Hallucination Detection
Fine-tuned for hallucination detection as part of Director-AI.
Smaller variant (184M params) of the large model. Lower accuracy but faster inference — suitable for CPU deployments.
Training
- Base: MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli-ling-wanli
- Data: ~100K examples from HaluEval, FEVER, VitaminC, ANLI R3
- Epochs: 3, lr 2e-5, batch 32 (effective), class-weighted CE loss
- Labels: 0 = entailment, 1 = neutral, 2 = contradiction
Usage
from director_ai.core import NLIScorer
scorer = NLIScorer(model_name="anulum/deberta-v3-base-hallucination")
score = scorer.score("The capital of France is Paris.", "Paris is in Germany.")
License
AGPL-3.0 | Commercial licensing: anulum.li
- Downloads last month
- 17