MyanmarGPT-Big

• Multi-language model with Burmese Text and 1.42 Billion Parameters.
• Supports 61 Languages.

Everyone can fine-tune this model. Designed primarily for Burmese text completion, this model serves as a foundational framework for fine-tuning various natural language processing tasks specific to the Burmese language context.

About the project

Everyone has the right to create AI in Myanmar.

As Myanmar embarks on its journey towards AI democratization, a strategic and collaborative approach is crucial. Addressing challenges and seizing opportunities in sectors such as agriculture, healthcare, and education can position Myanmar as a regional leader in harnessing the benefits of AI for the betterment of its people and the advancement of its economy. With careful planning and investment, Myanmar has the potential to create a vibrant AI ecosystem that empowers individuals, businesses, and the nation as a whole.

MyanmarGPT

There is already MyanmarGPT which 125 M parameters. But people in Myanmar has been asking me for More precise model with more weights, Here is the MyanmarGPT-Big Model now.

You can use the MyanmarGPT model 125 M which is lightweight and free to use.

Model Description

• Developed by: Min Si Thu
• Model type: [GPT2]
• Language(s) (NLP): MultiLanguage, But especially Burmese Language
• License: CreativeML-OpenRail-M
• Finetuned from model [optional]: [mGPT]

How to use

Using pipeline

pip install transformers

from transformers import pipeline

pipe = pipeline("text-generation", model="jojo-ai-mst/MyanmarGPT-Big")
outputs = pipe("အီတလီ",do_sample=False)
print(outputs)

Using Model Generator

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jojo-ai-mst/MyanmarGPT-Big")
model = AutoModelForCausalLM.from_pretrained("jojo-ai-mst/MyanmarGPT-Big")


input_ids = tokenizer.encode("ချစ်သား", return_tensors='pt')
output = model.generate(input_ids, max_length=50)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Applied Uses

MyanmarGPT-Big can be used for the following use cases.

Text generation, Chatbots and Virtual Assistants, Content Summarization, Translations, Question-Answering System, and Sentiment Analysis.

Direct Use

Originally crafted for text completion in Burmese, this model functions as a fundamental asset for various Natural Language Processing (NLP) tasks. Although its primary role is presently centered on aiding in text generation and completion, it harbors considerable potential for broader applications. Researchers and developers have the option to refine this model using specialized datasets, thereby expanding its utility to other NLP domains, including summarization and instruction-based tasks. Nevertheless, it is crucial to acknowledge that when dealing with high-stakes decisions or comprehending domain-specific terminology, additional specialized training for the model is advised to ensure optimal accuracy and reliability.

Out-of-Scope Use

Users need to recognize the inherent limitations and biases present in language models. Responsible usage is crucial, particularly in sensitive contexts, as this model is not designed to generate misleading or harmful content.

Bias, Risks, and Limitations

While the MyanmarGPT-Big excels in handling general Burmese text, its effectiveness might be limited when dealing with daily-life spoken burmese words. Users are encouraged to perform comprehensive testing tailored to their specific use cases.

mGPT

Special thanks to mGPT Project by ai-forever. Without mGPT, MyanmarGPT-Big would have taken a long time to move on from building from scratch.

Contact

Reach me via

• LinkedIn - Min Si Thu
• GitHub - Min Si Thu
• Medium - Min Si Thu
• Hashnode - Min Si Thu