README.md

---
license: cc-by-nc-4.0
language:
- ar
- en
base_model:
- google/gemma-2-9b
extra_gated_fields:
  First Name: text
  Last Name: text
  Date of birth: date_picker
  Country: country
  Affiliation: text
  Job title:
    type: select
    options:
      - Student
      - Research Graduate
      - AI researcher
      - AI developer/engineer
      - Reporter
      - Other
  geo: ip_location
  By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
---

# **DALLA Gemma**

**dalla-gemma-it** is an Arabic-focused adaptation of `google/gemma-2-9b`, built using the [DALLA suite](https://github.com/U4RASD/dalla-model-training). 
The model uses a tokenizer modified through our [sentencepiece token reuse method](https://github.com/U4RASD/dalla-sentencepiece) to improve Arabic coverage without increasing vocabulary size. 
It was further trained on curated, culturally grounded Arabic data to support more fluent Arabic generation and better value alignment with Arab communities. 
This model serves as a demonstration of the DALLA pipeline for adapting open-weight models to Arabic.

## Intended Use

This model is released for research purposes and general experimentation with Arabic language tasks. 
It is not designed for deployment in high-risk settings, and its outputs should not be relied on for factual, legal, medical, or sensitive decisions.

## Getting Started

```sh
pip install -U transformers
```

### Running with the `pipeline` API

```python
import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="dru-ac/dalla-gemma-it",
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="cuda",  # replace with "mps" to run on a Mac device
)

messages = [
    {"role": "user", "content": "من أنت؟"},
]
outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)
# أنا دلّة، نموذج لغوي ضخم تم تدريبي على مجموعة واسعة من البيانات في مختلف المجالات للإجابة على أسئلة المستخدمين. تم تطويري من قبل باحثي ومهندسي المركز العربي للأبحاث ودراسة السياسات الذي يقع مقره الرئيسي في الدوحة، قطر. يمكنك سؤالي عن مختلف المواضيع خاصة المتعلقة بالثقافة واللغة العربية
```

#### Running the model on a single / multi GPU

```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("dru-ac/dalla-gemma")
model = AutoModelForCausalLM.from_pretrained(
    "dru-ac/dalla-gemma-it",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
messages = [
    {"role": "user", "content": "من أنت؟"},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))

```