YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Azhar Model v0.3 (Academic Fine-Tuned)
This model is a domain-specific fine-tuned version of Qwen2.5-7B-Instruct, optimized for Islamic Jurisprudence (Fiqh) and Aqidah based on the Shamela Library corpus.
📊 Training Statistics & Metrics
| Metric | Initial Value | Final Value | Improvement |
|---|---|---|---|
| Cross-Entropy Loss | 3.8489 | 2.0326 | 47.19% |
| Perplexity (PPL) | 46.94 | 7.63 | 83.74% |
📚 Dataset Details
- Source: Shamela Full Merged (Subset of 230 Scientific Titles).
- Total Processed Tokens: 24,576,000 Tokens.
- Reference List: See
Azhar_Model_v0.3_Dataset_Metadata.xlsxin the files section.
📉 Visual Analysis
🎓 Citation & Thesis
Developed by Dr. Shamil Al-Mohammedi as part of a doctoral research project.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support