Upload 9 files

README (1).md

@@ -0,0 +1,73 @@
+---
+license: afl-3.0
+language:
+- en
+- te
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: transformers
+tags:
+- toxic-comment-classification
+- roberta
+- text-classification
+---
+# Toxic Comment Classification Using RoBERTa
+
+## Overview
+
+This project provides a toxic comment classification model based on RoBERTa (Robustly optimized BERT approach). The model is designed to classify comments as toxic or non-toxic, helping in moderating online discussions and improving community interactions.
+
+## Model Details
+
+- **Model Name**: RoBERTa for Toxic Comment Classification
+- **Architecture**: RoBERTa
+- **Fine-tuning Task**: Binary classification (toxic vs. non-toxic)
+- **Evaluation Metrics**:
+  - Accuracy
+  - F1 Score
+  - Precision
+  - Recall
+
+## Files
+
+- `pytorch_model.bin`: The trained model weights.
+- `config.json`: Model configuration file.
+- `merges.txt`: BPE tokenizer merges file.
+- `model.safetensors`: Model weights in safetensors format.
+- `special_tokens_map.json`: Tokenizer special tokens mapping.
+- `tokenizer_config.json`: Tokenizer configuration file.
+- `vocab.json`: Tokenizer vocabulary file.
+- `roberta-toxic-comment-classifier.pkl`: Serialized best model state dictionary (for PyTorch).
+- `README.md`: This documentation file.
+
+## Model Performance
+
+- **Accuracy**: 0.9599
+- **F1 Score**: 0.9615
+- **Precision**: 0.9646
+- **Recall**: 0.9599
+
+## Load the model
+```
+from transformers import pipeline
+
+# Load the model and tokenizer
+model_name = "prabhaskenche/pk-toxic-comment-classification-using-RoBERTa"
+classifier = pipeline("text-classification", model=model_name)
+
+# Example usage
+text = "You're the worst person I've ever met."
+result = classifier(text)
+print(result)
+
+```
+
+## Usage
+
+### Installation
+
+Install the required packages:
+
+```bash
+pip install torch transformers sklearn

app (2).py

@@ -0,0 +1,22 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the model using the correct identifier
+classifier = pipeline('text-classification', model='prabhaskenche/toxic-comment-classification-using-RoBERTa')
+
+def classify(text):
+    results = classifier(text)
+    # Adjust the label names based on your model's label mapping
+    non_toxic_score = next((item['score'] for item in results[0] if item['label'] == 'LABEL_0'), 0)
+    toxic_score = next((item['score'] for item in results[0] if item['label'] == 'LABEL_1'), 0)
+    return f"{non_toxic_score:.3f} non-toxic, {toxic_score:.3f} toxic"
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=classify,
+    inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
+    outputs="text"
+)
+
+# Launch the interface
+interface.launch()

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae7732394eb090294e53d529b75236c40bacf9927cdde6f70ffbe375120e210
+size 1421495416

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9813a554fe148818b949baeb3b80e4f5114c58a17491a65582ecf251e4b30211
+size 1421612078

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config (1).json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}