AmbatronBERTa

AmbatronBERTa is a Thai language model fine-tuned specifically for text classification tasks, built upon the WangchanBERTa architecture.

Model Description

AmbatronBERTa is designed to handle the complexities of the Thai language. It has been fine-tuned on a dataset of over 3,000 research papers to improve classification accuracy. Leveraging the transformer-based WangchanBERTa, it efficiently captures the nuances of Thai text, making it suitable for classifying documents across multiple fields.

Developers

AmbatronBERTa was developed by students at King Mongkut's University of Technology North Bangkok:

• Peerawat Banpahan
• Waris Thongpho

Use Cases

AmbatronBERTa can be applied to a wide range of tasks, such as:

• Research Classification: Categorizing academic papers into relevant topics.
• Document Organization: Classifying articles, blogs, and other documents by themes.
• Sentiment Analysis: Analyzing sentiment in Thai-language texts across various contexts.

How to Use

To use AmbatronBERTa with the transformers library:

from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("Peerawat2024/AmbatronBERTa")
model = AutoModelForSequenceClassification.from_pretrained("Peerawat2024/AmbatronBERTa")