LOCUS-Opacity / README.md
jbarrow's picture
Upload opacity weights, tokenizer, and model card
1d4802c verified
metadata
base_model: answerdotai/ModernBERT-base
library_name: transformers
pipeline_tag: text-classification
tags:
  - text-classification
  - regression
  - legal
  - locus
  - modernbert
license: apache-2.0
datasets:
  - LocalLaws/LOCUS-v1.0

LocalLaws/LOCUS-Opacity

A ModernBERT regression model that scores local-ordinance text along the Opacity axis of the LOCUS (Local Ordinances Corpus, United States) dataset.

Fine-tuned from answerdotai/ModernBERT-base. The target is a TrueSkill mu distilled from pairwise LLM comparisons on the opacity axis, then z-score normalized across the training corpus.

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tok = AutoTokenizer.from_pretrained("LocalLaws/LOCUS-Opacity")
model = AutoModelForSequenceClassification.from_pretrained("LocalLaws/LOCUS-Opacity")
model.eval()

text = "No person shall keep any swine within the city limits."
enc = tok(text, return_tensors="pt", truncation=True, max_length=2048)
with torch.no_grad():
    score = model(**enc).logits.squeeze(-1).item()
print(score)