QaemLLaMA: A Persian Language Model

Overview

QaemLLaMA is a Persian language model fine-tuned from the LLaMA architecture. It has been enhanced with 20,000 new Persian tokens to improve its understanding and generation capabilities in the Persian language.

Key Features

  • Enhanced Persian Vocabulary: The addition of 20,000 Persian tokens allows QaemLLaMA to comprehend and generate a broader range of Persian texts with greater accuracy.

  • State-of-the-Art Performance: Evaluations indicate that QaemLLaMA achieves leading results on Persian language benchmarks, demonstrating its effectiveness in various natural language processing tasks.

Model Details

  • Base Architecture: LLaMA

  • Language Supported: Persian

  • Additional Tokens: 20,000 Persian tokens

  • License: CC BY-NC-SA 4.0 (non-commercial use only)

Contributors

Developed by:

  • Reza Mahdi Hadi
  • Mojtaba Madadyar
  • Foad Asef
  • Mohsen Mollafarajzadeh

License

This model is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. For non-commercial use only.

References

For more detailed information, please refer to the QaemLLaMA Model Card.

Disclaimer

QaemLLaMA is intended for research and educational purposes. Users are responsible for ensuring compliance with applicable laws and regulations when deploying the model.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .