Upload model - F1: 0.8502

README.md

@@ -0,0 +1,114 @@
+---
+language:
+  - bn
+license: mit
+tags:
+  - text-classification
+  - multi-label-classification
+  - bangla
+  - cyberbullying
+  - bert
+  - pytorch
+datasets:
+  - custom
+metrics:
+  - f1
+  - accuracy
+pipeline_tag: text-classification
+---
+
+# Bangla Cyberbullying Detection Model
+
+This model is fine-tuned for multi-label classification to detect cyberbullying in Bangla text.
+
+## Model Details
+
+- **Base Model:** sagorsarker/bangla-bert-base
+- **Task:** Multi-label text classification
+- **Labels:** bully, sexual, religious, threat, spam
+- **Number of Labels:** 5
+- **Classifier Hidden Size:** 256
+- **Dropout:** 0.1
+
+## Usage
+
+### Installation
+
+```bash
+pip install torch transformers
+```
+
+### Loading and Inference
+
+```python
+from model import TransformerMultiLabelClassifier
+from transformers import AutoTokenizer
+import torch
+
+# Load the model
+model = TransformerMultiLabelClassifier.from_pretrained("path/to/saved/model")
+tokenizer = AutoTokenizer.from_pretrained("path/to/saved/model")
+
+# Prepare input
+text = "আপনার বাংলা টেক্সট এখানে"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+
+# Get predictions
+outputs = model.predict(inputs['input_ids'], inputs['attention_mask'])
+    
+probabilities = outputs['probabilities'][0]
+predictions = outputs['predictions'][0]
+
+labels = ['bully', 'sexual', 'religious', 'threat', 'spam']
+for label, prob, pred in zip(labels, probabilities, predictions):
+    status = "✓ Detected" if pred else "✗ Not detected"
+    print(f"{label}: {prob:.4f} ({status})")
+```
+
+### Using with Pipeline (Alternative)
+
+```python
+# For batch inference
+texts = ["টেক্সট ১", "টেক্সট ২", "টেক্সট ৩"]
+inputs = tokenizer(texts, return_tensors="pt", truncation=True, padding=True, max_length=128)
+outputs = model.predict(inputs['input_ids'], inputs['attention_mask'])
+```
+
+## Labels
+
+| Label | Description |
+|-------|-------------|
+| bully | General bullying content |
+| sexual | Sexual harassment or inappropriate content |
+| religious | Religious hate or discrimination |
+| threat | Threatening content |
+| spam | Spam or irrelevant content |
+
+## Training
+
+This model was trained using:
+- K-fold cross-validation with multi-label stratification
+- AdamW optimizer with linear warmup
+- Mixed precision training (AMP)
+- Early stopping based on weighted F1 score
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{bangla-cyberbullying-detection,
+  author = {Your Name},
+  title = {Bangla Cyberbullying Detection Model},
+  year = {2024},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/your-username/your-model}
+}
+```
+
+## Limitations
+
+- Trained specifically on Bangla text
+- Performance may vary on out-of-domain text
+- Multi-label threshold of 0.5 used by default (can be adjusted)
+- May not generalize well to code-mixed text (Bangla + English)

classifier_config.json

@@ -0,0 +1,17 @@
+{
+  "base_model_name": "sagorsarker/bangla-bert-base",
+  "num_labels": 5,
+  "dropout": 0.1,
+  "classifier_hidden_size": 256,
+  "label_names": [
+    "bully",
+    "sexual",
+    "religious",
+    "threat",
+    "spam"
+  ],
+  "model_type": "transformer_multilabel_classifier",
+  "architectures": [
+    "TransformerMultiLabelClassifier"
+  ]
+}

classifier_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f087d49a597a4c142dd0cf37e899689272985359b8cce3bfcc3ece7a6afbef
+size 794768

encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 102025
+}

encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad08faf84c223df62933df7a2275a1a17559388675b29079b2ea71a0b530856
+size 657608552

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff6ed3e1bed0f5ebe49a603408aba177a2ee6376d2053efba6687f9e121dc5c
+size 658460790

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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_config.json

@@ -0,0 +1,28 @@
+{
+  "batch": 32,
+  "lr": 2e-05,
+  "epochs": 20,
+  "dataset_path": "/kaggle/working/finetuning_framework_for_cyberbullying/data/1_Multilablel_Cyberbully_Data.csv",
+  "model_path": "sagorsarker/bangla-bert-base",
+  "max_length": 128,
+  "num_folds": 5,
+  "freeze_base": false,
+  "seed": 42,
+  "stratification_type": "multilabel",
+  "author_name": "saif_siddique",
+  "mlflow_experiment_name": "Bangla-Cyberbullying-Detection",
+  "dropout": 0.1,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.1,
+  "gradient_clip_norm": 1.0,
+  "early_stopping_patience": 5,
+  "no_amp": false,
+  "no_cache": false,
+  "save_model_dir": "./saved_models",
+  "no_save_model": false,
+  "push_to_hub": true,
+  "hub_repo_name": "Saif-Siddique/bangla-cyberbully-sagor-bangla-bert-base",
+  "hub_private": false,
+  "output_dir": "./outputs",
+  "cache_dir": "./cache"
+}

training_metrics.json

@@ -0,0 +1,23 @@
+{
+  "accuracy": 0.7134316460741331,
+  "per_label_accuracy": 0.9321642088481467,
+  "hamming_loss": 0.06783579115185333,
+  "precision_weighted": 0.8444694079506561,
+  "recall_weighted": 0.8576449912126538,
+  "f1_weighted": 0.8501896616089782,
+  "precision_macro": 0.8203965353566014,
+  "recall_macro": 0.8277283024881914,
+  "f1_macro": 0.8226322889088447,
+  "loss": 0.25361040277005753,
+  "train_accuracy": 0.8971804324001196,
+  "train_per_label_accuracy": 0.9784198465676995,
+  "train_hamming_loss": 0.02158015343230049,
+  "train_precision_weighted": 0.9500541236360307,
+  "train_recall_weighted": 0.95634223471539,
+  "train_f1_weighted": 0.9526477489757674,
+  "train_precision_macro": 0.9379394400632052,
+  "train_recall_macro": 0.9760201529990115,
+  "train_f1_macro": 0.9561884089351944,
+  "train_loss": 0.07912977215400926,
+  "best_epoch": 11
+}