ahmedheakl's picture
Update README.md
c532c7b verified
metadata
language:
  - en
  - ar
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - gguf
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
datasets:
  - ahmedheakl/arzen-llm-dataset
metrics:
  - bleu
  - meteor
  - bertscore
library_name: transformers

Please see paper & code for more information:

Citation

BibTeX:

@article{heakl2024arzen,
  title={ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs},
  author={Heakl, Ahmed and Zaghloul, Youssef and Ali, Mennatullah and Hossam, Rania and Gomaa, Walid},
  journal={arXiv preprint arXiv:2406.18120},
  year={2024}
}

Model Card Authors

Uploaded model

  • Developed by: ahmedheakl
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.