| # English to Chinese Translation (Quantized Model) |
|
|
| This repository contains a **quantized English-to-Chinese translation model** fine-tuned on the ['wlhb/Transaltion-Chinese-2-English'] dataset and optimized using **dynamic quantization** for efficient CPU inference. |
|
|
| ## 🔧 Model Details |
|
|
| - **Base model**: Helsinki-NLP/opus-mt-en-zh |
| - **Dataset**: ['wlhb/Transaltion-Chinese-2-English'] |
| - **Training platform**: Kaggle (CUDA GPU) |
| - **Fine-tuned**: On English-Chinese pairs from the Hugging Face dataset |
| - **Quantization**: PyTorch Dynamic Quantization (`torch.quantization.quantize_dynamic`) |
| - **Tokenizer**: Saved alongside the model |
|
|
| ## 📁 Folder Structure |
|
|
| quantized_model/ |
| ├── config.json |
| ├── pytorch_model.bin |
| ├── tokenizer_config.json |
| ├── tokenizer.json |
| ├── vocab.json / merges.txt |
| |
| |
| --- |
| |
| ## 🚀 Usage |
| |
| ### 🔹 1. Load Quantized Model for Inference |
| |
| ```python |
| import torch |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline |
| |
| # Load tokenizer |
| tokenizer = AutoTokenizer.from_pretrained("./quantized_model") |
| |
| # Load quantized model |
| model = AutoModelForSeq2SeqLM.from_pretrained("./quantized_model") |
| model.eval() |
| |
| # Run translation |
| translator = pipeline("translation_en_to_zh", model=model, tokenizer=tokenizer, device=-1) |
|
|
| text = "How are you?" |
| print("English:", translator(text)[0]['translation_text']) |
| ``` |
| |
| ## Model Training Summary |
| |
| - Loaded dataset: wlhb/Transaltion-Chinese-2-English |
| |
| - Mapped translation data: {"en": ..., "zh": ...} before training |
| |
| - Training: 3 epochs using GPU |
| |
| - Disabled: wandb logging |
| |
| - Skipped: Evaluation phase |
| |
| - Saved: Trained + Quantized model and tokenizer |
| |
| - Quantization: torch.quantization.Quantize_dynamic is used for efficient CPU inference |
| |
| |
