Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+language: multilingual
+license: apache-2.0
+tags:
+- toxicity-detection
+- content-moderation
+- text-classification
+- multi-label-classification
+datasets:
+- jigsaw-toxic-comment-classification
+metrics:
+- f1
+base_model: FacebookAI/xlm-roberta-base
+widget:
+- text: "This is a normal comment."
+- text: "I hate you, you're stupid!"
+- text: "Let's discuss this respectfully."
+---
+
+# XLM-RoBERTa Toxicity Classifier
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) for multi-label toxicity classification.
+
+## Model Description
+
+This model can classify text into the following toxicity categories:
+- Toxic
+- Severe Toxic
+- Obscene
+- Threat
+- Insult
+- Identity Hate
+- None (for non-toxic content)
+
+## Usage
+
+```python
+from transformers import XLMRobertaForSequenceClassification, XLMRobertaTokenizer
+import torch
+
+# Load model and tokenizer
+model = XLMRobertaForSequenceClassification.from_pretrained("oleksiizirka/xlm-roberta-toxicity-classifier")
+tokenizer = XLMRobertaTokenizer.from_pretrained("oleksiizirka/xlm-roberta-toxicity-classifier")
+
+# Prepare input
+text = "Your text here"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
+
+# Get predictions
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.sigmoid(outputs.logits)
+
+# Print results
+labels = ['toxic', 'severe_toxic', 'obscene', 'threat', 'insult', 'identity_hate', 'none']
+for label, score in zip(labels, predictions[0]):
+    if score > 0.5:
+        print(f"{label}: {score:.3f}")
+```
+
+## Training Data
+
+The model was trained on the Jigsaw Toxic Comment Classification dataset.
+
+## Training Procedure
+
+- Base model: FacebookAI/xlm-roberta-base
+- Training approach: Multi-label classification with BCEWithLogitsLoss
+- Optimization: AdamW with learning rate 2e-5
+- Batch size: 16
+- Epochs: 3-5 with early stopping
+
+## Limitations
+
+- Trained primarily on English text
+- May exhibit biases present in the training data
+- Should be used as part of a larger content moderation system

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "./toxicity_classifier",
+  "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": "toxic",
+    "1": "severe_toxic",
+    "2": "obscene",
+    "3": "threat",
+    "4": "insult",
+    "5": "identity_hate",
+    "6": "none"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "toxic": 0,
+    "severe_toxic": 1,
+    "obscene": 2,
+    "threat": 3,
+    "insult": 4,
+    "identity_hate": 5,
+    "none": 6
+  },
+  "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": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cd434a26c2e654d0047f9905a0e70a5016daaff1e92404b2d92dcf2ecf6c60
+size 1112220388

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}