Model Card for odia-t5-base

Model Details

Model Description

odia-t5-base is a multilingual Text-To-Text Transfer Transformer fine-tuned to perform downstream tasks in the Odia language.

• Developed by: Mohammed Ashraf
• Model type: Language model
• Language(s) (NLP): Odia, English, Hindi
• License: CC BY-NC-SA 4.0
• Related Models: All MT5 Checkpoints

Uses

Direct Use and Downstream Use

• Translate English to Odia.
• Translate Hind to Odia.
• Odia Sentence Summarization.
• Question Answering in Odia.
• Context-Based Question answering in Odia.

How to use

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("mrSoul7766/odia-t5-base")
model = AutoModelForSeq2SeqLM.from_pretrained("mrSoul7766/odia-t5-base")

# Set maximum generation length
max_length = 512

# Generate response with question as input
input_ids = tokenizer.encode("answer: ଓଡ଼ିଶାରେ ଅଟ୍ଟାଳିକା ପାଇଁ ସର୍ବାଧିକ ଆସନ ସୀମା କ’ଣ?</s>", return_tensors="pt")
output_ids = model.generate(input_ids, max_length=max_length)

# Decode response
response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(response)

Licensing Information

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Citation Information

Dataset

@misc{OdiaGenAI,
  author = {Shantipriya Parida and Sambit Sekhar and Subhadarshi Panda and Soumendra Kumar Sahoo and Swateek Jena and Abhijeet Parida and Arghyadeep Sen and Satya Ranjan Dash and Deepak Kumar Pradhan},
  title = {OdiaGenAI: Generative AI and LLM Initiative for the Odia Language},
  year = {2023},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/OdiaGenAI}},
}

Model

@misc{mrSoul7766,
  author = {Mohammed Ashraf},
  title = {odia-t5-base},
  year = {2024},
  note = {Licensed under Attribution-NonCommercial-ShareAlike 4.0 International},
}