ahmedheakl/arazn-gemma1.1-7B-eng-extra

How to use

Just install peft, transformers and pytorch first.

pip install peft transformers torch

Then login with your huggingface token to get access to base models

huggingface-cli login --token <YOUR_HF_TOKEN>

Then load the model.

from peft import PeftConfig, PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

peft_model_id = "ahmedheakl/arazn-gemma1.1-7B-eng-extra"
peft_config = PeftConfig.from_pretrained(peft_model_id)
base_model_name = peft_config.base_model_name_or_path
base_model = AutoModelForCausalLM.from_pretrained(base_model_name)
model = PeftModel.from_pretrained(base_model, peft_model_id)
model = model.to("cuda")
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)

Then do inference

import torch

raw_prompt = """<bos><start_of_turn>user
Translate the following code-switched Arabic-English-mixed text to English only.
{source}<end_of_turn>
<start_of_turn>model
"""
def inference(prompt) -> str:
    prompt = raw_prompt.format(source=prompt)
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    generated_ids = model.generate(
        **inputs,
        use_cache=True,
        num_return_sequences=1,
        max_new_tokens=100,
        do_sample=True,
        num_beams=1,
        temperature=0.7,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id,
    )
    outputs = tokenizer.batch_decode(generated_ids)[0]
    torch.cuda.empty_cache()
    torch.cuda.synchronize()
    return outputs.split("<start_of_turn>model\n")[-1].split("<end_of_turn>")[0]

print(inference("أنا أحب الbanana")) # I like bananas.

Please see paper & code for more information:

• https://github.com/ahmedheakl/arazn-llm
• https://arxiv.org/abs/2406.18120

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

• Email: [email protected]
• Linkedin: https://linkedin.com/in/ahmed-heakl