Upload README.md

README.md

@@ -1,3 +1,84 @@
----
-license: mit
----
+---
+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
+thumbnail: "https://media.licdn.com/dms/image/v2/D4E12AQH-g6TfVlad0g/article-cover_image-shrink_720_1280/article-cover_image-shrink_720_1280/0/1724391684857?e=1729728000&v=beta&t=e3ggmXGVKaVU6e72wjsc9Ppgd0rigQqjeA1Od9fyFDk"
+base_model: "bert-base-uncased"
+co2_eq_emissions:
+  emissions: 8
+  training_type: "fine-tuning"
+  geographical_location: "Phoenix, AZ"
+  hardware_used: "T4"
+---
+
+# Social Bias NER 
+
+This NER model is fine-tuned from BERT, for *multi-label* token classification of:
+
+- (GEN)eralizations
+- (UNFAIR)ness
+- (STEREO)types
+
+You can [try it out in spaces](https://huggingface.co/spaces/maximuspowers/bias-detection-ner) :).
+
+## How to Get Started with the Model
+
+Transformers pipeline doesn't have a class for multi-label token classification, but you can use this code to load the model, and run it, and format the output.
+
+```
+import json
+import torch
+from transformers import BertTokenizerFast, BertForTokenClassification
+import gradio as gr
+
+# init important things
+tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')
+model = BertForTokenClassification.from_pretrained('maximuspowers/bias-detection-ner')
+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'
+}
+
+# predict function you'll want to use if using in your own code
+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 > 0.5).int() # remember to try your own threshold
+
+    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)
+```
+