Upload 7 files

README.md

@@ -0,0 +1,94 @@
+---
+language: en
+license: apache-2.0
+tags:
+- text-classification
+- spam-detection
+- distilbert
+- sms
+datasets:
+- sms_spam
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+widget:
+- text: "Congratulations! You've won a FREE prize. Call now!"
+- text: "Hey, are we still meeting for lunch tomorrow?"
+- text: "URGENT: Your account has been compromised!"
+- text: "Can you pick up milk on the way home?"
+---
+
+# SMS Spam Detector
+
+## Model Description
+
+Fine-tuned DistilBERT model for detecting spam SMS messages.
+
+**Performance:**
+- Accuracy: 0.9916 (99.16%)
+- Precision: 0.9730
+- Recall: 0.9643
+- F1-Score: 0.9686
+- ROC-AUC: 0.9990
+
+## Quick Start
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="YOUR_USERNAME/sms-spam-detector")
+result = classifier("Win a free prize now!")
+print(result)
+```
+
+## Detailed Usage
+
+```python
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
+import torch
+
+tokenizer = DistilBertTokenizer.from_pretrained("YOUR_USERNAME/sms-spam-detector")
+model = DistilBertForSequenceClassification.from_pretrained("YOUR_USERNAME/sms-spam-detector")
+
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
+    outputs = model(**inputs)
+    probs = torch.softmax(outputs.logits, dim=1)
+    return "SPAM" if probs[0][1] > 0.5 else "HAM"
+
+print(predict("Free prize!"))
+```
+
+## Training Data
+
+- Dataset: SMS Spam Collection (5,574 messages)
+- Train/Val/Test split: 70/15/15
+- Ham: 86.6%, Spam: 13.4%
+
+## Training Details
+
+- Base model: distilbert-base-uncased
+- Epochs: 3
+- Batch size: 16
+- Learning rate: 2e-05
+- Optimizer: AdamW
+
+## Limitations
+
+- Trained on English SMS messages only
+- May not generalize well to other languages
+- Performance may degrade on heavily obfuscated spam
+
+## Citation
+
+```bibtex
+@misc{sms-spam-detector,
+  author = {Isuru Didulantha},
+  title = {SMS Spam Detector},
+  year = {2025},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/didulantha/sms-spam-detector}
+}
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vocab_size": 30522
+}

metadata.json

@@ -0,0 +1,19 @@
+{
+  "model_name": "sms-spam-detector",
+  "base_model": "distilbert-base-uncased",
+  "task": "text-classification",
+  "language": "en",
+  "dataset": "SMS Spam Collection",
+  "metrics": {
+    "accuracy": 0.9916267942583732,
+    "precision": 0.972972972972973,
+    "recall": 0.9642857142857143,
+    "f1_score": 0.968609865470852,
+    "roc_auc": 0.9990380820836622
+  },
+  "training_params": {
+    "epochs": 3,
+    "batch_size": 16,
+    "learning_rate": 2e-05
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cab3d0cfcfad0aea145d597d0a15334efcf897fb696605fcadba28a4b5c603
+size 267832560

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}