Upload banking-bert-turkish final model (5-fold CV micro-F1 0.667)

README.md

@@ -0,0 +1,89 @@
+---
+language:
+- tr
+license: mit
+library_name: transformers
+tags:
+- legal
+- text-classification
+- multi-label-classification
+- banking
+- turkish
+- contract-analysis
+base_model: dbmdz/bert-base-turkish-cased
+metrics:
+- f1
+pipeline_tag: text-classification
+---
+
+# Agreemind/banking-bert-turkish
+
+Turkish BERT fine-tuned for multi-label risk classification in Turkish consumer banking contracts.
+Detects 14 risk categories including hidden fees, collateral clauses, default escalation, and more.
+
+## Performance
+
+Evaluated via **5-fold document-level cross-validation** on 80 Turkish banking contracts (7,020 clauses).
+
+| Metric | Score |
+|--------|-------|
+| Micro-F1 (CV) | **0.6657** |
+| Macro-F1 (CV) | **0.6226** |
+
+### Per-Class F1
+
+| Category | F1 |
+|----------|----|
+| hidden_fees | 0.76 |
+| broad_collateral | 0.74 |
+| unilateral_rate_change | 0.72 |
+| default_escalation | 0.71 |
+| data_sharing | 0.69 |
+| currency_risk | 0.68 |
+| account_freeze | 0.65 |
+| early_payment_penalty | 0.64 |
+| dispute_limitation | 0.61 |
+| bundled_insurance | 0.59 |
+| unilateral_terms_change | 0.57 |
+| overdraft_penalty | 0.51 |
+| cross_default | 0.44 |
+| auto_enrollment | 0.42 |
+
+## Training
+
+- **Base:** dbmdz/bert-base-turkish-cased
+- **Loss:** Multi-label Focal Loss (gamma=2.0, alpha=0.75)
+- **Optimizer:** AdamW, lr=2e-5, weight_decay=0.01, epochs=10
+- **Data:** 80 Turkish banking contracts, 7,020 clauses, 18 banks
+- **Threshold:** Fixed 0.5 per label
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+LABELS = [
+    "hidden_fees", "dispute_limitation", "broad_collateral", "default_escalation",
+    "account_freeze", "currency_risk", "unilateral_terms_change", "unilateral_rate_change",
+    "data_sharing", "auto_enrollment", "cross_default", "overdraft_penalty",
+    "early_payment_penalty", "bundled_insurance",
+]
+
+tokenizer = AutoTokenizer.from_pretrained("Agreemind/banking-bert-turkish")
+model = AutoModelForSequenceClassification.from_pretrained("Agreemind/banking-bert-turkish")
+model.eval()
+
+text = "Banka, hesap işletim ücretini önceden bildirmeksizin değiştirme hakkını saklı tutar."
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+
+with torch.no_grad():
+    probs = torch.sigmoid(model(**inputs).logits).squeeze()
+
+for label, prob in zip(LABELS, probs):
+    if prob > 0.5:
+        print(f"{label}: {prob:.3f}")
+```
+
+## License
+MIT

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

label_schema.json

@@ -0,0 +1,35 @@
+{
+  "label_names": [
+    "hidden_fees",
+    "dispute_limitation",
+    "broad_collateral",
+    "default_escalation",
+    "account_freeze",
+    "currency_risk",
+    "unilateral_terms_change",
+    "unilateral_rate_change",
+    "data_sharing",
+    "auto_enrollment",
+    "cross_default",
+    "overdraft_penalty",
+    "early_payment_penalty",
+    "bundled_insurance"
+  ],
+  "label2id": {
+    "hidden_fees": 0,
+    "dispute_limitation": 1,
+    "broad_collateral": 2,
+    "default_escalation": 3,
+    "account_freeze": 4,
+    "currency_risk": 5,
+    "unilateral_terms_change": 6,
+    "unilateral_rate_change": 7,
+    "data_sharing": 8,
+    "auto_enrollment": 9,
+    "cross_default": 10,
+    "overdraft_penalty": 11,
+    "early_payment_penalty": 12,
+    "bundled_insurance": 13
+  },
+  "num_labels": 14
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77f3b94eaee821381961f15bf7b9002b3c3d8d1caccafd26d25feb63eae16eb
+size 442535976

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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "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]"
+}