AventIQ-AI/English-To-Vietnamese

English to Vietnamese Translation (Quantized Model)

This repository contains a quantized English-To-Vietnamese translation model fine-tuned on the "HelloWorld2307/eng_viet_translation" dataset and optimized using dynamic quantization for efficient CPU inference.

🔧 Model Details

• Base model: Helsinki-NLP/opus-mt-en-vi
• Dataset: HelloWorld2307/eng_viet_translation
• Training platform: Kaggle (CUDA GPU)
• Fine-tuned: On English-Vietnamese 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

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_vi", model=model, tokenizer=tokenizer, device=-1)

text = "Hello, How are you?"
print("English:", translator(text)[0]['translation_text'])

Model Training Summary

• Loaded dataset: HelloWorld2307/eng_viet_translation

• Mapped translation data: {"en": ..., "vi": ...} 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