Upload 10 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,97 @@
----
-license: mit
----
+---
+language: bn
+tags:
+- hate-speech-detection
+- bangla
+- bert
+- binary-classification
+license: mit
+---
+
+# Bangla Hate Speech Detection Model
+
+This model is fine-tuned for binary hate speech detection in Bangla text.
+
+## Model Description
+
+- **Base Model**: FacebookAI/xlm-roberta-base
+- **Task**: Binary Classification (Hate Speech vs Non-Hate Speech)
+- **Language**: Bangla (Bengali)
+- **Training Method**: Baseline training only (original behavior)
+
+## Training Details
+
+### Training Hyperparameters
+
+- **Batch Size**: 32
+- **Learning Rate**: 3e-05
+- **Epochs**: 30
+- **Max Sequence Length**: 128
+- **Dropout**: 0.1
+- **Weight Decay**: 0.01
+- **Warmup Ratio**: 0.1
+
+### Training Data
+
+- **K-Fold Cross-Validation**: 5 folds
+- **Stratification**: binary
+
+## Performance
+
+*Add your metrics here after training*
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch
+import torch.nn as nn
+import json
+
+# Load model components
+encoder = AutoModel.from_pretrained("path/to/model")
+
+with open("path/to/model/classifier_config.json", 'r') as f:
+    c_config = json.load(f)
+
+classifier = nn.Sequential(
+    nn.Linear(c_config['hidden_size'], 256),
+    nn.ReLU(),
+    nn.Dropout(0.1),
+    nn.Linear(256, c_config['num_labels'])
+)
+classifier.load_state_dict(torch.load("path/to/model/classifier.pt"))
+
+tokenizer = AutoTokenizer.from_pretrained("path/to/model")
+
+# Predict
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
+    with torch.no_grad():
+        outputs = encoder(**inputs)
+        cls_embedding = outputs.last_hidden_state[:, 0, :]
+        logits = classifier(cls_embedding)
+        prob = torch.sigmoid(logits).item()
+    return prob
+
+text = "আপনার বাংলা টেক্সট এখানে"
+prob = predict(text)
+print(f"Hate Speech Probability: {prob:.4f}")
+```
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{bangla-hate-speech-model,
+  author = {Nabil},
+  title = {Bangla Hate Speech Detection Model},
+  year = {2026},
+  publisher = {HuggingFace},
+}
+```
+
+## License
+
+MIT License

classifier.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccee955253bd0bc56ab980049a6e1f7676b3a7d00e5d0a507b6ed0e2abcf2602
+size 790568

classifier_config.json

@@ -0,0 +1,6 @@
+{
+  "type": "sequential",
+  "layers": "Sequential(\n  (0): Linear(in_features=768, out_features=256, bias=True)\n  (1): ReLU()\n  (2): Dropout(p=0.1, inplace=False)\n  (3): Linear(in_features=256, out_features=1, bias=True)\n)",
+  "num_labels": 1,
+  "hidden_size": 768
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_states": true,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

how_to_load.py

@@ -0,0 +1,44 @@
+# How to load this model:
+
+from transformers import AutoModel, AutoTokenizer
+import torch
+import torch.nn as nn
+import json
+
+# Load encoder
+encoder = AutoModel.from_pretrained("./outputs/final_baseline_best")
+
+# Load classifier config
+with open("./outputs/final_baseline_best/classifier_config.json", 'r') as f:
+    c_config = json.load(f)
+
+num_labels = c_config.get('num_labels', 1)
+hidden_size = c_config.get('hidden_size', 768)
+
+# Reconstruct classifier
+classifier = nn.Sequential(
+    nn.Linear(hidden_size, 256),
+    nn.ReLU(),
+    nn.Dropout(0.1),
+    nn.Linear(256, num_labels)
+)
+classifier.load_state_dict(torch.load("./outputs/final_baseline_best/classifier.pt"))
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("./outputs/final_baseline_best")
+
+# Inference function
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
+    with torch.no_grad():
+        outputs = encoder(**inputs)
+        cls_embedding = outputs.last_hidden_state[:, 0, :]
+        logits = classifier(cls_embedding)
+        probs = torch.sigmoid(logits)
+    return probs.item()
+
+# Example
+text = "আপনার বাংলা টেক্সট এখানে"
+prob = predict(text)
+print(f"Hate Speech Probability: {prob:.4f}")
+print(f"Prediction: {'Hate Speech' if prob > 0.5 else 'Non-Hate Speech'}")

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb73c2a2db553e18038726794a9881ff09daad7d3b555dea7be64098f51f88c2
+size 1112197096

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}