CoolFace
Modelpublic

qassim-university/qu-llm-assistant

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes19downloads
Model Card

QU-LLM Assistant — wesam3/qu-llm-assistant

A fine-tuned Qwen2.5-1.5B-Instruct model specialised in answering student advisory questions for Qassim University (جامعة القصيم). The model is distributed as a Q4\K\M GGUF file for efficient local inference with llama.cpp / Ollama.


Model Details

PropertyValue
Base modelQwen/Qwen2.5-1.5B-Instruct
Fine-tuning methodLoRA (MLX framework)
QuantisationQ4\K\M (GGUF)
File size~940 MB
LanguageArabic-primary, English-secondary
LicenseApache-2.0
DomainUniversity student advisory (academic rules, registration, scholarships, etc.)

Training Data

  • —Dataset: 15,903 curated Q&A pairs extracted from official Qassim University documents (bylaws, handbooks, academic calendars, policy circulars).
  • —Source: Publicly available PDFs and web pages from qu.edu.sa.
  • —Language split: ~80 % Arabic, ~20 % English.
  • —Date range: Multi-year corpus covering historical and current university policies.

Usage

Ollama (recommended)

bash
ollama run wesamhamad/qu-llm-assistant

Or pull the GGUF manually and create a local Modelfile:

FROM ./qassim-gpt-q4_k_m.gguf
SYSTEM "أنت مساعد ذكاء اصطناعي متخصص في الإجابة على استفسارات طلاب جامعة القصيم."
bash
ollama create qu-llm-assistant -f Modelfile
ollama run qu-llm-assistant

llama.cpp

bash
llama-cli -m qassim-gpt-q4_k_m.gguf \
  --chat-template qwen \
  -p "ما هي متطلبات التسجيل في الفصل الدراسي الأول؟"

Python (llama-cpp-python)

python
from llama_cpp import Llama

llm = Llama(model_path="qassim-gpt-q4_k_m.gguf", chat_format="qwen")
response = llm.create_chat_completion(messages=[
    {"role": "system",  "content": "أنت مساعد أكاديمي لجامعة القصيم."},
    {"role": "user",    "content": "كيف أتقدم لطلب إعادة تقييم الدرجات؟"},
])
print(response["choices"][0]["message"]["content"])

Intended Use & Limitations

  • —Intended use: Helping students navigate university regulations, registration procedures, scholarship requirements, and academic policies at Qassim University.
  • —Out-of-scope: General-purpose chat, medical/legal advice, topics unrelated to the university.
  • —Hallucinations: Like all LLMs the model may occasionally produce incorrect information. Always verify critical details with the official university portal.

Citation

bibtex
@misc{qu-llm-assistant-2025,
  author    = {Wesam Hamad},
  title     = {QU-LLM Assistant: Fine-tuned Qwen2.5-1.5B for Qassim University Advisory},
  year      = {2025},
  publisher = {HuggingFace},
  url       = {https://huggingface.co/wesam3/qu-llm-assistant}
}

License

Apache-2.0 — see LICENSE.