--- license: apache-2.0 --- # ALLaM-Thinking-GGUF ## Description ALLaM-Thinking-GGUF is an Arabic language model optimized for step-by-step reasoning and mathematical problem-solving. The model has been quantized to the GGUF format for efficient inference on consumer hardware. ## Model Details - **Model Name**: ALLaM-Thinking-GGUF - **Author**: [almaghrabima](https://huggingface.co/almaghrabima) - **Languages**: Arabic (primary) - **Format**: GGUF (GPU/CPU inference optimized) - **Quantization**: q4_k_m ## Features - Specialized in step-by-step reasoning for mathematical problems - Optimized for Arabic language comprehension and generation - Efficient inference through GGUF quantization - Suitable for educational applications and mathematical assistance ## Installation ```bash # Clone or download the repository git clone https://huggingface.co/almaghrabima/ALLaM-Thinking-GGUF # Navigate to the downloaded directory cd ALLaM-Thinking-GGUF ``` ## Usage The model can be used with [llama.cpp](https://github.com/ggerganov/llama.cpp) for local inference: ```bash ./build/bin/llama-cli -m ./ALLaM-Thinking-q4_k_m.gguf -cnv -p "Your prompt in Arabic" ``` ### Example ```bash ./build/bin/llama-cli -m ./ALLaM-Thinking-q4_k_m.gguf -cnv -p "في فريق مكون من 15 لاعباً، 40% منهم يسجلون الأهداف. إذا سجل كل لاعب من اللاعبين الذين يسجلون الأهداف في المتوسط 5 أهداف خلال الموسم، فكم عدد الأهداف الكلي التي سجلها اللاعبون الذين يسجلون الأهداف؟" ``` ### Sample Output ``` [INST] في فريق مكون من 15 لاعباً، 40 % منهم يسجلون الأهداف. إذا سجل كل لاعب من اللاعبين الذين يسجلون الأهداف في المتوسط 5 أهداف خلال الموسم، فكم عدد الأهداف الكلي التي سجلها اللاعبون الذين يسجلون الأهداف؟ [/INST] لحساب عدد الأهداف الكلي التي سجلها اللاعبون الذين يسجلون الأهداف في الفريق المكون من 15 لاعباً، نبدأ بحساب عدد اللاعبين الذين يسجلون الأهداف. عدد اللاعبين الذين يسجلون الأهداف = إجمالي عدد اللاعبين * نسبة اللاعبين الذين يسجلون الأهداف = 15 * 0.40 = 6 لاعبين ثم نضرب عدد اللاعبين الذين يسجلون الأهداف في متوسط عدد الأهداف التي يسجلها كل لاعب منهم خلال الموسم. الأهداف الكلي المسجلة = عدد اللاعبين الذين يسجلون الأهداف * متوسط عدد الأهداف لكل لاعب = 6 * 5 = 30 هدفاً لذا، سجل اللاعبون الذين يسجلون الأهداف إجمالي 30 هدفاً خلال الموسم. ``` ## Advanced Options You can customize inference parameters with additional options: ```bash ./build/bin/llama-cli -m ./ALLaM-Thinking-q4_k_m.gguf -cnv -p "Your prompt" \ --ctx_size 2048 \ --temp 0.7 \ --top_p 0.9 \ --repeat_penalty 1.1 ``` ## Hardware Requirements - **Minimum**: 8GB RAM - **Recommended**: 16GB RAM, High-end CPU or GPU with at least 8GB VRAM ## License This model is released under the [Apache 2.0 License](https://opensource.org/licenses/Apache-2.0). ## Citations If you use this model in your research or applications, please cite: ```bibtex @misc{almaghrabima2025allam, author = {Mohammed Al-Maghrabi Research}, title = {ALLaM-Thinking: Arabic Large Language Model with Enhanced Reasoning Capabilities}, year = {2025}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/almaghrabima/ALLaM-Thinking}} } ``` ## Acknowledgements - This model utilizes the GGUF format developed by the [llama.cpp](https://github.com/ggerganov/llama.cpp) team - Special thanks to contributors and the Arabic NLP community