---
license: mit
language:
- en
library_name: transformers
pipeline_tag: token-classification
tags:
- Social Bias
metrics:
- name: F1
  type: F1
  value: 0.7864
- name: Recall
  type: Recall
  value: 0.7617
base_model: bert-base-uncased
co2_eq_emissions:
  emissions: 8
  training_type: fine-tuning
  hardware_used: T4
---

## How to Get Started with the Model

```py
import json
import torch
from transformers import AutoTokenizer, AutoModelForTokenClassification

# Load model directly
tokenizer = AutoTokenizer.from_pretrained("bhavan2410/bias-lens-detection-model")
model = AutoModelForTokenClassification.from_pretrained("bhavan2410/bias-lens-detection-model")

model.eval()
model.to('cuda' if torch.cuda.is_available() else 'cpu')

# ids to labels we want to display
id2label = {
    0: "O",
    1: "B-STEREO",
    2: "I-STEREO",
    3: "B-GEN",
    4: "I-GEN",
    5: "B-UNFAIR",
    6: "I-UNFAIR",
    7: "B-EXCL",
    8: "I-EXCL",
    9: "B-FRAME",
    10: "I-FRAME",
    11: "B-ASSUMP",
    12: "I-ASSUMP",
}

def predict_ner_tags(sentence):
    inputs = tokenizer(sentence, return_tensors="pt", padding=True, truncation=True, max_length=128)
    input_ids = inputs['input_ids'].to(model.device)
    attention_mask = inputs['attention_mask'].to(model.device)

    with torch.no_grad():
        outputs = model(input_ids=input_ids, attention_mask=attention_mask)
        logits = outputs.logits
        probabilities = torch.sigmoid(logits)
        predicted_labels = (probabilities > 0.3).int()

    result = []
    tokens = tokenizer.convert_ids_to_tokens(input_ids[0])
    for i, token in enumerate(tokens):
        if token not in tokenizer.all_special_tokens:
            label_indices = (predicted_labels[0][i] == 1).nonzero(as_tuple=False).squeeze(-1)
            labels = [id2label[idx.item()] for idx in label_indices] if label_indices.numel() > 0 else ['O']
            result.append({"token": token, "labels": labels})

    return json.dumps(result, indent=4)
```