Upload 7 files

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Cog-Evaluate",
+    "1": "Cog-Explain",
+    "2": "Cog-Generate",
+    "3": "Cog-Reason",
+    "4": "Meta-Monitor",
+    "5": "Meta-Orient",
+    "6": "Meta-Plan",
+    "7": "Socio-Coordinate",
+    "8": "Socio-Encourage",
+    "9": "Socio-Feedback",
+    "10": "TE-Act",
+    "11": "TE-Report"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Cog-Evaluate": 0,
+    "Cog-Explain": 1,
+    "Cog-Generate": 2,
+    "Cog-Reason": 3,
+    "Meta-Monitor": 4,
+    "Meta-Orient": 5,
+    "Meta-Plan": 6,
+    "Socio-Coordinate": 7,
+    "Socio-Encourage": 8,
+    "Socio-Feedback": 9,
+    "TE-Act": 10,
+    "TE-Report": 11
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

example_usage.py

@@ -0,0 +1,68 @@
+"""
+Regulatory Capacity Classifier - Usage Example
+
+This script demonstrates how to use the trained model for inference.
+"""
+
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification
+
+# Configuration
+MODEL_PATH = "./final_model"
+LABELS = ['Cog-Evaluate', 'Cog-Explain', 'Cog-Generate', 'Cog-Reason', 'Meta-Monitor', 'Meta-Orient', 'Meta-Plan', 'Socio-Coordinate', 'Socio-Encourage', 'Socio-Feedback', 'TE-Act', 'TE-Report']
+
+def load_model():
+    """Load the trained model and tokenizer."""
+    tokenizer = BertTokenizer.from_pretrained(MODEL_PATH)
+    model = BertForSequenceClassification.from_pretrained(MODEL_PATH)
+    model.eval()
+    return tokenizer, model
+
+def predict(text, tokenizer, model, threshold=0.5):
+    """Predict regulatory capacity labels for a given text."""
+    # Tokenize
+    inputs = tokenizer(
+        text, 
+        return_tensors="pt", 
+        truncation=True, 
+        max_length=128,
+        padding=True
+    )
+    
+    # Predict
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probs = torch.sigmoid(outputs.logits)
+        predictions = (probs > threshold).int()
+    
+    # Map to labels
+    predicted_labels = [LABELS[i] for i in range(len(LABELS)) if predictions[0][i] == 1]
+    confidences = {LABELS[i]: float(probs[0][i]) for i in range(len(LABELS))}
+    
+    return predicted_labels, confidences
+
+def main():
+    print("Loading model...")
+    tokenizer, model = load_model()
+    
+    # Example texts
+    test_texts = [
+        "I think we should evaluate our approach before moving forward.",
+        "Let's coordinate our tasks and divide the work equally.",
+        "Good job everyone! We're making great progress.",
+        "Can you explain why you chose that option?",
+        "I'll write down our conclusions in the report."
+    ]
+    
+    print("\n" + "="*60)
+    print("Regulatory Capacity Predictions")
+    print("="*60)
+    
+    for text in test_texts:
+        labels, confidences = predict(text, tokenizer, model)
+        print(f"\nText: {text}")
+        print(f"Predicted Labels: {labels}")
+        print(f"Top Confidences: {{k: f'{v:.3f}' for k, v in sorted(confidences.items(), key=lambda x: -x[1])[:3]}}")
+
+if __name__ == "__main__":
+    main()

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71978a2b7d8de081978379d2b0cb6d3170ab88f3554ae95bf9f4d73532022efc
+size 437989408

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}