Upload 8 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

@@ -0,0 +1,51 @@
+
+---
+language: multilingual
+license: apache-2.0
+tags:
+- text-classification
+- cyberbullying
+- offensive-language
+- multi-label
+---
+
+# Advanced Cyberbullying & Offensive Language Detector
+
+This is a multilingual, multi-label text classification model fine-tuned on a combined dataset of `cyberbullying_tweets` and the OLID (Offensive Language Identification Dataset). It is designed to detect both general offensive language and specific, targeted types of cyberbullying.
+
+This model was trained using the `xlm-roberta-base` architecture.
+
+## Model Labels
+
+The model predicts six independent labels for any given text. A `1` indicates the presence of the category, and a `0` indicates its absence.
+
+1.  **`is_offensive`**: The text contains generally offensive, toxic, or profane language.
+2.  **`is_gender_harassment`**: The text contains attacks based on gender, sexism, or sexual orientation.
+3.  **`is_religious_harassment`**: The text contains attacks targeting religious beliefs.
+4.  **`is_ethnic_harassment`**: The text contains attacks based on race or ethnicity.
+5.  **`is_age_harassment`**: The text contains attacks targeting a person's age (ageism).
+6.  **`is_other_cyberbullying`**: The text contains general insults or bullying that doesn't fit the other specific categories.
+
+A text is considered **"Not Cyberbullying"** when all labels are predicted as `0`.
+
+## Performance
+
+The model achieved the following performance on its validation set after two epochs of training:
+
+-   **F1 Score (Weighted):** 0.908
+-   **ROC AUC (Weighted):** 0.961
+
+## How to Use
+
+Once you upload this model to your Hugging Face account, you can use it directly with a `pipeline`:
+
+```python
+from transformers import pipeline
+
+# Replace "your-username/your-repo-name" with your actual model name on the Hub
+pipe = pipeline("text-classification", model="your-username/your-repo-name", return_all_scores=True)
+
+# Example usage
+text = "You are such an idiot, I can't believe you said that."
+results = pipe(text)
+print(results)```

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241613ff9edffcbd8f1580ac2fdf9a3ce9c204a636f6119d4da813ee3759f56c
+size 1112266930

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 sha256:4c08c80d1df11b82ada2fd707562f86a9ebd5b7de04f51ebd2b49f2cd5906d00
+size 17082925

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d539438cc429e0c981984f2d41586273073ab249d4372731448ab2366f2dc8a7
+size 4344