Gpt Neo Vi Small

🚀 GPT-Neo-small for Vietnamese

The first GPT model tailored for the Vietnamese language, offering advanced text generation capabilities.

🚀 Quick Start

GPT-Neo-vi-small is a transformer model crafted using EleutherAI's replication of the GPT - 3 architecture. It's designed to generate high - quality Vietnamese text.

✨ Features

• Vietnamese Focus: Specifically designed for the Vietnamese language, enabling better text generation in Vietnamese contexts.
• Based on GPT - 3 Architecture: Leveraging the powerful GPT - 3 architecture replicated by EleutherAI.

📦 Installation

No specific installation steps were provided in the original document.

💻 Usage Examples

Basic Usage

This example generates a different sequence each time it's run:

from transformers import GPTNeoForCausalLM, GPT2Tokenizer
model = GPTNeoForCausalLM.from_pretrained("NlpHUST/gpt-neo-vi-small")
tokenizer = GPT2Tokenizer.from_pretrained("NlpHUST/gpt-neo-vi-small")
prompt = "Ngay sau Tết Nguyên đán Tân Sửu, hiện tượng giá đất tăng tại nhiều địa phương. Thị trường nhộn nhịp, tạo ra những cơn sóng sốt đất khó tin khiến bộ ngành, địa phương đưa cảnh báo."
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
gen_tokens = model.generate(input_ids, do_sample=True, temperature=1.0, max_length=1024)
gen_text = tokenizer.batch_decode(gen_tokens)[0]
print(gen_text)

📚 Documentation

Model Description

GPT-Neo-vi-small is a transformer model designed using EleutherAI's replication of the GPT-3 architecture.

Training Data

GPT-Neo-vi-small was trained on the News datasets, a large - scale dataset created from News Websites for the purpose of training this model.

Contact Information

For personal communication related to this project, please contact Nha Nguyen Van (nha282@gmail.com).