Update README.md

README.md

@@ -1,5 +1,6 @@
 ---
-license: apache-2.0
+language:
+- ar
 tags:
 - llama
 - text-generation
@@ -9,7 +10,9 @@ tags:
 - fine-tuned
 datasets:
 - Jr23xd23/Arabic_LLaMA_Math_Dataset
+license: apache-2.0
 base_model: meta-llama/Llama-3.2-3B-Instruct
+pipeline_tag: text-generation
 inference: true
 ---
 
@@ -21,7 +24,7 @@ inference: true
 
 ## Model Details
 
-- **Model Type**: Transformer-based language model fine-tuned for text generation.
+- **Model Type**: Transformer-based language model fine-tuned for text generation
 - **Languages**: Arabic
 - **Base Model**: [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
 - **Dataset**: [Arabic LLaMA Math Dataset](https://github.com/jaberjaber23/Arabic-LLaMA-Math-Dataset)
@@ -31,6 +34,7 @@ inference: true
 ## Training Data
 
 The model was fine-tuned on the **Arabic LLaMA Math Dataset**, which consists of 12,496 examples covering various mathematical topics, such as:
+
 - Basic Arithmetic
 - Algebra
 - Geometry
@@ -38,12 +42,13 @@ The model was fine-tuned on the **Arabic LLaMA Math Dataset**, which consists of
 - Combinatorics
 
 Each example in the dataset includes:
-- **Instruction**: The problem statement in Arabic.
-- **Solution**: The solution to the problem in Arabic.
+- **Instruction**: The problem statement in Arabic
+- **Solution**: The solution to the problem in Arabic
 
 ## Intended Use
 
 ### Primary Use Cases:
+
 - Solving mathematical problems in Arabic
 - Educational applications
 - Tutoring systems for Arabic-speaking students
@@ -51,7 +56,7 @@ Each example in the dataset includes:
 
 ### How to Use
 
-You can use the model in Python with the Hugging Face `transformers` library:
+You can use the model in Python with the Hugging Face transformers library:
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -60,7 +65,36 @@ tokenizer = AutoTokenizer.from_pretrained("Jr23xd23/Math_Arabic_Llama-3.2-3B-Ins
 model = AutoModelForCausalLM.from_pretrained("Jr23xd23/Math_Arabic_Llama-3.2-3B-Instruct")
 
 # Example: Solving a math problem in Arabic
-input_text = "ما هو مجموع الزوايا في مثلث؟"  # What is the sum of angles in a triangle?
+input_text = "ما هو مجموع الزوايا في مثلث؟" # What is the sum of angles in a triangle?
 inputs = tokenizer(input_text, return_tensors="pt")
-output = model.generate(**inputs)
+output = model.generate(**inputs, max_length=100)
 print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+## Limitations
+
+- The model is not designed for non-mathematical language tasks.
+- Performance may degrade when applied to highly complex mathematical problems beyond the scope of the training dataset.
+- The model's outputs should be verified for critical applications.
+
+## License
+
+This model is licensed under the **Apache 2.0 License**.
+
+## Citation
+
+If you use this model in your research or projects, please cite it as follows:
+
+```bibtex
+@model{Math_Arabic_Llama_3.2_3B_Instruct,
+  title={Math_Arabic_Llama-3.2-3B-Instruct},
+  author={Jr23xd23},
+  year={2024},
+  publisher={Hugging Face},
+  url={https://huggingface.co/Jr23xd23/Math_Arabic_Llama-3.2-3B-Instruct},
+}
+```
+
+## Acknowledgements
+
+Special thanks to the creators of the **Arabic LLaMA Math Dataset** for providing a rich resource for fine-tuning the model.