Vietnamese-gpt2-medium Open-source Model - Free Deployment to Support Vietnamese Text Generation Tasks

Vietnamese Gpt2 Medium

Developed by chronopt-research

This is a pre - trained GPT2 - Medium model for Vietnamese, trained with the causal language modeling objective, which can effectively handle Vietnamese - related text generation tasks.

Large Language Model

Transformers

OtherOpen Source License:Apache-2.0 #Vietnamese text generation #Moderate scale with 380 million parameters #Multi - domain pre - training

Downloads 705

Release Time : 8/6/2023

Model Overview

A medium - scale pre - trained Vietnamese model based on the GPT - 2 architecture, with 380 million parameters, suitable for natural language processing tasks such as Vietnamese text generation.

Model Features

Pre - training advantages

Inherits the powerful language understanding and generation capabilities of GPT - 2 and is pre - trained on large - scale Vietnamese data.

Moderate parameter scale

The medium version has 380 million parameters, achieving a good balance between performance and resource consumption.

Training on multiple datasets

Pre - trained using a combination of multiple Vietnamese datasets such as news and encyclopedias to enhance the model's generalization ability.

Model Capabilities

Vietnamese text generation

Language understanding

Natural language processing

Use Cases

Text generation

News content generation

Generate Vietnamese news content based on the input keywords or beginnings.

Encyclopedia Q&A

Generate answers to questions based on Vietnamese encyclopedia knowledge.

🚀 Vietnamese `gpt2-medium`

This is a pretrained gpt2-medium model for the Vietnamese language, trained with the casual language modeling (CLM) objective, offering high - quality text generation capabilities.

🚀 Quick Start

This is a pretrained gpt2-medium for Vietnamese language using casual language modeling (CLM) objective. It was introduced in this paper and first released at this page.

✨ Features

GPT-2 (at first) is a transformers model pretrained on a very large corpus of English data in a self - supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences.

This is the medium version of GPT-2, with 380M parameters.

You could've found other pretrained version from here: gpt2-base, gpt2-large

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

📚 Documentation

Dataset used for pretraining

This is a combination of multiple Vietnamese dataset for pretraining CLMs such as GPT, GPT2, etc.

The dataset consists of:

You can find out the combined version here: duongttr/vi-dataset-for-pretrain

Hyperparamters & Results

We trained the model ~100k steps, with lr = 1e-4, bs = 1920, optimizer = adamw on TPU-VM-3.8 from TRC Program. The training costs around 2.5 days.

Model	Eval Loss	Eval Perplexity
gpt2-base	3.939	51.35
gpt2-medium	2.8676	17.5948
gpt2-large	-	-

📄 License

The model is licensed under the Apache-2.0 license.

🔧 Technical Details

No specific technical details beyond what's already covered are provided, so this section is skipped.

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

📞 Contacts

Feel free to contact us via: email

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご