Upload 5 files

README.md

@@ -0,0 +1,55 @@
+# Sentinel-D DistilBERT Intent Classifier v1
+
+## Model Details
+- **Base Model**: distilbert-base-uncased
+- **Task**: Sequence Classification (4 classes)
+- **Training Date**: 2026-03-04T03:36:30.927788
+- **Classes**: VERSION_PIN, API_MIGRATION, MONKEY_PATCH, FULL_REFACTOR
+
+## Intent Classes
+1. **VERSION_PIN**: Pinning or locking dependency versions
+2. **API_MIGRATION**: Migrating between API versions or protocols
+3. **MONKEY_PATCH**: Quick/temporary fixes via runtime patching
+4. **FULL_REFACTOR**: Complete rewriting or structural redesign
+
+## Usage
+
+```python
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
+import torch
+import json
+
+tokenizer = DistilBertTokenizer.from_pretrained("./distilbert-intent-classifier-v1")
+model = DistilBertForSequenceClassification.from_pretrained("./distilbert-intent-classifier-v1")
+
+text = "I updated my package.json to lock the Express version to 4.18.0"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+
+with torch.no_grad():
+    outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class_id = logits.argmax(-1).item()
+
+# Map ID back to label
+label_config = json.load(open("label_config.json"))
+predicted_label = label_config["id_to_label"][str(predicted_class_id)]
+print(f"Predicted Intent: {predicted_label}")
+```
+
+## Files
+- `pytorch_model.bin`: Fine-tuned model weights
+- `config.json`: Model configuration
+- `vocab.txt`: Tokenizer vocabulary
+- `label_config.json`: Intent class mappings
+- `README.md`: This file
+
+## Training Configuration
+- Epochs: 6
+- Batch Size: 16
+- Learning Rate: Dynamic tuning from 1e-05 to 5e-05
+- Optimizer: AdamW with weighted cross-entropy loss
+- Class Imbalance Handling: Random oversampling + weighted loss
+
+## Performance Targets
+- Accuracy: >= 0.80
+- Macro F1: >= 0.80

config.json

@@ -0,0 +1,39 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 30522
+}

label_config.json

@@ -0,0 +1,22 @@
+{
+  "label_to_id": {
+    "VERSION_PIN": 0,
+    "API_MIGRATION": 1,
+    "MONKEY_PATCH": 2,
+    "FULL_REFACTOR": 3
+  },
+  "id_to_label": {
+    "0": "VERSION_PIN",
+    "1": "API_MIGRATION",
+    "2": "MONKEY_PATCH",
+    "3": "FULL_REFACTOR"
+  },
+  "intent_classes": [
+    "VERSION_PIN",
+    "API_MIGRATION",
+    "MONKEY_PATCH",
+    "FULL_REFACTOR"
+  ],
+  "model_name": "distilbert-base-uncased",
+  "training_date": "2026-03-04T03:36:30.926809"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}