Terjman Large V2.0

🚀 🇲🇦 Terjman-Large-v2.0 (240M)

Terjman-Large-v2.0 is an enhanced version of atlasia/Terjman-Large-v1.2. Built on the robust Transformer architecture, it's fine-tuned for delivering high-quality and accurate translations. This model is trained on a larger and more refined dataset, leading to improved translation performance. It achieves results comparable to gpt-4o-2024-08-06 on TerjamaBench, an evaluation benchmark for English-Moroccan darija translation models that emphasizes the cultural aspect.

🚀 Quick Start

You can use the model with the Hugging Face Transformers library:

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model_name = "BounharAbdelaziz/Terjman-Large-v2.0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

def translate(text):
    inputs = tokenizer(text, return_tensors="pt")
    output = model.generate(**inputs)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Example translation
text = "Hello there! Today the weather is so nice in Geneva, couldn't ask for more to enjoy the holidays :)"
translation = translate(text)
print("Translation:", translation)
# prints: صباح الخير! اليوم الطقس زوين بزاف فجنيف، ما قدرتش نطلب المزيد باش نستمتعو بالعطل:)

✨ Features

• ✅ Fine-tuned specifically for English to Moroccan darija translation.
• ✅ Achieves state-of-the-art performance among open-source models.
• ✅ Compatible with 🤗 Transformers and can be easily deployed on various hardware setups.

🔥 Performance Comparison

The following table compares Terjman-Large-v2.0 with proprietary and open-source models using BLEU, chrF, and TER scores. Higher BLEU/chrF scores and lower TER scores indicate better translation quality.

🔧 Technical Details

• Base Model: atlasia/Terjman-Large-v1.2
• Architecture: Transformer-based sequence-to-sequence model
• Training Data: High-quality parallel corpora with high-quality translations
• Training Precision: FP16 for efficient inference

📦 Installation

Run in a Hugging Face Space

Try the model interactively in the Terjman-Large Space 🤗

Use with Text Generation Inference (TGI)

For fast inference, use Hugging Face TGI:

pip install text-generation
text-generation-launcher --model-id BounharAbdelaziz/Terjman-Large-v2.0

Run Locally with Transformers & PyTorch

pip install transformers torch
python -c "from transformers import pipeline; print(pipeline('translation', model='BounharAbdelaziz/Terjman-Large-v2.0')('Hello there!'))"

Deploy on an API Server

Use FastAPI to serve translations as an API:

from fastapi import FastAPI
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

app = FastAPI()
model_name = "BounharAbdelaziz/Terjman-Large-v2.0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

@app.get("/translate/")
def translate(text: str):
    inputs = tokenizer(text, return_tensors="pt")
    output = model.generate(**inputs)
    return {"translation": tokenizer.decode(output[0], skip_special_tokens=True)}

📚 Documentation

Training Details Hyperparameters

The model was fine-tuned using the following training settings:

• Learning Rate: 0.001
• Training Batch Size: 16
• Evaluation Batch Size: 16
• Seed: 42
• Gradient Accumulation Steps: 8
• Total Effective Batch Size: 128
• Optimizer: AdamW (Torch) with betas=(0.9,0.999), epsilon=1e-08
• Learning Rate Scheduler: Linear
• Warmup Ratio: 0.1
• Epochs: 2
• Precision: Mixed FP16 for efficient training

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.21.0

📄 License

This model is released under the CC BY-NC (Creative Commons Attribution-NonCommercial) license, which means it can be used for research and personal projects but not for commercial purposes. For commercial use, please get in touch :)

@misc{terjman-v2,
  title = {Terjman-v2: High-Quality English-Moroccan Darija Translation Model},
  author={Abdelaziz Bounhar},
  year={2025},
  howpublished = {\url{https://huggingface.co/BounharAbdelaziz/Terjman-Large-v2.0}},
  license = {CC BY-NC}
}