Upload 7 files

README.md

@@ -0,0 +1,119 @@
+
+# RoBERTa-Base Quantized Model for Topic Classification
+
+This repository hosts a quantized version of the RoBERTa model, fine-tuned for topic classification using the AG News dataset. The model has been optimized using FP16 quantization for efficient deployment without significant accuracy loss.
+## Model Details
+
+- **Model Architecture:** RoBERTa Base  
+- **Task:** Multi-class Topic Classification (4 classes)  
+- **Dataset:** AG News (Hugging Face Datasets)  
+- **Quantization:** Float16  
+- **Fine-tuning Framework:** Hugging Face Transformers  
+
+---
+
+## Installation
+
+```bash
+pip install transformers torch datasets 
+```
+
+---
+
+## Loading the Model
+
+```python
+
+from transformers import RobertaTokenizer
+from transformers import RobertaForSequenceClassification
+
+import torch
+
+# Load tokenizer and model
+
+tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
+model = RobertaForSequenceClassification.from_pretrained("roberta-base", num_labels=4).to(device)
+# Define test sentences
+samples = [
+    "Tensions rise in the Middle East as diplomats gather for emergency talks to prevent further escalation.",
+"Tesla reports a 25% increase in quarterly revenue, driven by strong demand for its Model Y vehicles in Asia.",
+
+"Researchers develop a new quantum computing chip that significantly reduces energy consumption.",
+    "Argentina defeats Brazil 2-1 in the Copa América final, securing their 16th continental title.",
+    "Meta unveils its latest AI model capable of generating 3D virtual environments from text prompts."
+]
+
+
+
+from transformers import pipeline
+
+# Load pipeline for inference
+classifier = pipeline("text-classification", model=trainer.model, tokenizer=tokenizer, device=0)  # device=-1 if using CPU
+
+predictions = classifier(samples)
+
+# Print results
+for text, pred in zip(samples, predictions):
+    print(f"\nText: {text}\nPredicted Topic: {pred['label']} (Score: {pred['score']:.4f})")
+```
+
+---
+
+## Performance Metrics
+
+- **Accuracy:** 0.9471  
+- **Precision:** 0.9471  
+- **Recall:** 0.9471  
+- **F1 Score:** 0.9471 
+
+---
+
+## Fine-Tuning Details
+
+### Dataset
+
+The dataset is sourced from Hugging Face’s ag_news dataset. It contains 120,000 training samples and 7,600 test samples, with each news article labeled into one of four categories: World, Sports, Business, or Sci/Tech. The original dataset was used as provided, and input texts were tokenized using the RoBERTa tokenizer and truncated/padded to a maximum length of 128 tokens.
+
+### Training
+
+- **Epochs:** 3  
+- **Batch size:** 8  
+- **Learning rate:** 2e-5  
+- **Evaluation strategy:** `epoch`  
+
+---
+
+## Quantization
+
+Post-training quantization was applied using PyTorch’s `half()` precision (FP16) to reduce model size and inference time.
+
+---
+
+## Repository Structure
+
+```python
+.
+├── config.json                   # Model configuration
+├── merges.txt                   # Byte Pair Encoding (BPE) merge rules for tokenizer
+├── model.safetensors            # Quantized model weights
+├── README.md                    # Model documentation
+├── special_tokens_map.json      # Tokenizer special tokens
+├── tokenizer_config.json        # Tokenizer configuration
+├── vocab.json                   # Tokenizer vocabulary
+
+├── README.md                      # Model documentation
+```
+
+---
+
+## Limitations
+
+- The model is trained specifically for binary topic classification on ag news dataset.
+- FP16 quantization may result in slight numerical instability in edge cases.
+
+
+---
+
+## Contributing
+
+Feel free to open issues or submit pull requests to improve the model or documentation.

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 sha256:140e9e7cd268315932ffb1de35b9c63eb654da8d45811c9b70aa850db5c2e71d
+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>"
+}