Upload 7 files

README.md

@@ -0,0 +1,99 @@
+# RoBERTa-Based Topic Classification Model Using AG News Dataset
+
+This repository hosts a RoBERTa-based transformer model fine-tuned for topic classification on the AG News dataset. The model identifies topics such as World, Sports, Business, and Science/Technology in a given news text.
+
+## Model Details
+
+- **Model Architecture:** RoBERTa (roberta-base)
+- **Task:** Topic Classification
+- **Dataset:** AG News (from Hugging Face Datasets)
+- **Fine-tuning Framework:** Hugging Face Transformers
+
+## Usage
+
+### Installation
+
+```sh
+pip install transformers datasets torch
+```
+
+### Loading and Predicting
+
+```python
+from transformers import RobertaTokenizer, RobertaForSequenceClassification
+import torch
+
+# Load model and tokenizer
+model = RobertaForSequenceClassification.from_pretrained("your-saved-model-directory")
+tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
+model.eval()
+
+# Sample prediction
+def predict_topic(texts, model, tokenizer, device='cpu'):
+    import re
+    if isinstance(texts, str):
+        texts = [texts]
+
+    def preprocess(text):
+        text = text.lower()
+        text = re.sub(r"http\S+|www\S+|https\S+", '', text)
+        text = re.sub(r'\@\w+|\#', '', text)
+        text = re.sub(r"[^a-zA-Z0-9\s.,!?']", '', text)
+        text = re.sub(r'\s+', ' ', text).strip()
+        return text
+
+    cleaned_texts = [preprocess(t) for t in texts]
+    inputs = tokenizer(cleaned_texts, padding=True, truncation=True, return_tensors="pt").to(device)
+
+    model.to(device)
+    model.eval()
+    with torch.no_grad():
+        outputs = model(**inputs)
+        preds = torch.argmax(outputs.logits, dim=1).tolist()
+
+    label_map = {0: "World", 1: "Sports", 2: "Business", 3: "Sci/Tech"}
+    return [label_map[p] for p in preds]
+
+# Example
+sample_texts = [
+    "The stock market witnessed a major crash today due to inflation concerns.",
+    "The new space telescope has captured unprecedented images of distant galaxies."
+]
+results = predict_topic(sample_texts, model, tokenizer)
+for text, label in zip(sample_texts, results):
+    print(f"Text: {text}\nPredicted Topic: {label}\n")
+```
+
+## Performance Metrics
+
+- **Accuracy:** ~0.96 on AG News test split
+
+## Fine-Tuning Details
+
+### Dataset
+
+The dataset is sourced from the AG News dataset available via Hugging Face Datasets.
+
+### Training
+
+- Number of epochs: 3
+- Batch size: 8
+- Evaluation strategy: epoch
+- Learning rate: 2e-5
+
+## Repository Structure
+
+```
+.
+├── model/               # Contains the fine-tuned model files
+├── tokenizer/           # Tokenizer configuration and vocab
+├── README.md            # Model documentation
+```
+
+## Limitations
+
+- The model is trained specifically for AG News-style texts and may not generalize well to informal or unrelated domains.
+
+## Contributing
+
+Contributions are welcome! Please open an issue or submit a PR for suggestions or improvements.

config.json

@@ -0,0 +1,39 @@
+{
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.3",
+  "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 sha256:5f9a9ada76280e737a482c2bc9391d8334408ea67a6a83827faea171d85f1d8e
+size 249321504

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.json

@@ -0,0 +1,57 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}