---
base_model: unsloth/Mistral-Nemo-Base-2407-bnb-4bit
library_name: transformers
language:
- ar
pipeline_tag: text-generation
datasets:
- MahmoudIbrahim/Arabic_NVIDIA
---



- **Developed by:** Mahmoud Ibrahim

- 
**How to use :**

``` bush
! pip install transformers bitsandbytes
```

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from IPython.display import Markdown
import textwrap 

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("MahmoudIbrahim/Mistral_12b_Arabic")
model = AutoModelForCausalLM.from_pretrained("MahmoudIbrahim/Mistral_12b_Arabic",load_in_4bit =True)

alpaca_prompt = """فيما يلي تعليمات تصف مهمة، إلى جانب مدخل يوفر سياقاً إضافياً. اكتب استجابة تُكمل الطلب بشكل مناسب.

### التعليمات:
{}

### الاستجابة:
{}"""

# Format the prompt with instruction and an empty output placeholder
formatted_prompt = alpaca_prompt.format(
    "كيف يمكن للحكومة المصرية والمجتمع ككل أن يعززوا من قدرة البلاد على تحقيق التنمية المستدامة؟ "   ,  # instruction
    ""  # Leave output blank for generation
)

# Tokenize the formatted string directly
input_ids = tokenizer.encode(formatted_prompt, return_tensors="pt")  # Use 'cuda' if you want to run on GPU

def to_markdown(text):
    text = text.replace('•','*')
    return Markdown(textwrap.indent(text, '>', predicate=lambda _: True))

# Generate text
output = model.generate(
    input_ids,
    max_length=128,            # Adjust max length as needed
    num_return_sequences=1,     # Number of generated responses
    no_repeat_ngram_size=2,     # Prevent repetition
    top_k=50,                   # Filter to top-k tokens
    top_p=0.9,                  # Use nucleus sampling
    temperature=0.7 ,            # Control creativity level
  
)

generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
to_markdown(generated_text)

```

**The model response  :**

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f36b5377b0eb97ea124e32/DPdKT-kQiDtfulJ-qQ8DX.png)