| # DistilBERT Quantized Model for LinkedIn Post Sentiment Analysis | |
| This repository hosts a quantized version of the DistilBERT model, fine-tuned for LinkedIn post sentiment analysis tasks. The model has been optimized for efficient deployment while maintaining high accuracy, making it suitable for resource-constrained environments. | |
| ## Model Details | |
| - **Model Architecture:** DistilBERT Base Uncased | |
| - **Task:** LinkedIn Post Sentiment Analysis | |
| - **Dataset:** Stanford Sentiment Treebank v2 (SST2) | |
| - **Quantization:** Float16 | |
| - **Fine-tuning Framework:** Hugging Face Transformers | |
| ## Usage | |
| ### Installation | |
| ```sh | |
| pip install transformers torch | |
| ``` | |
| ### Loading the Model | |
| ```python | |
| from transformers import DistilBertForSequenceClassification, DistilBertTokenizer | |
| import torch | |
| # Load quantized model | |
| quantized_model_path = "/kaggle/working/distilbert_finetuned_fp16" | |
| quantized_model = DistilBertForSequenceClassification.from_pretrained(quantized_model_path) | |
| quantized_model.eval() # Set to evaluation mode | |
| quantized_model.half() # Convert model to FP16 | |
| # Load tokenizer | |
| tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased") | |
| # Define a test sentence | |
| test_sentence = "This update has received great engagement!" | |
| # Tokenize input | |
| inputs = tokenizer(test_sentence, return_tensors="pt", padding=True, truncation=True, max_length=128) | |
| # Ensure input tensors are in correct dtype | |
| inputs["input_ids"] = inputs["input_ids"].long() # Convert to long type | |
| inputs["attention_mask"] = inputs["attention_mask"].long() # Convert to long type | |
| # Make prediction | |
| with torch.no_grad(): | |
| outputs = quantized_model(**inputs) | |
| # Get predicted class | |
| predicted_class = torch.argmax(outputs.logits, dim=1).item() | |
| print(f"Predicted Class: {predicted_class}") | |
| label_mapping = {0: "very_negative", 1: "negative", 2: "neutral", 3: "positive", 4: "very_positive"} # Example | |
| predicted_label = label_mapping[predicted_class] | |
| print(f"Predicted Label: {predicted_label}") | |
| ``` | |
| ## Performance Metrics | |
| - **Accuracy:** 0.82 | |
| ## Fine-Tuning Details | |
| ### Dataset | |
| The dataset is taken from Kaggle Stanford Sentiment Treebank v2 (SST2). | |
| ### Training | |
| - Number of epochs: 3 | |
| - Batch size: 8 | |
| - Evaluation strategy: epoch | |
| - Learning rate: 2e-5 | |
| ### Quantization | |
| Post-training quantization was applied using PyTorch's built-in quantization framework to reduce the model size and improve inference efficiency. | |
| ## Repository Structure | |
| ``` | |
| . | |
| ├── model/ # Contains the quantized model files | |
| ├── tokenizer_config/ # Tokenizer configuration and vocabulary files | |
| ├── model.safensors/ # Fine Tuned Model | |
| ├── README.md # Model documentation | |
| ``` | |
| ## Limitations | |
| - The model may not generalize well to domains outside the fine-tuning dataset. | |
| - Quantization may result in minor accuracy degradation compared to full-precision models. | |
| ## Contributing | |
| Contributions are welcome! Feel free to open an issue or submit a pull request if you have suggestions or improvements. | |