Update license: Apache-2.0 → CC-BY-4.0

README.md

@@ -1,38 +1,35 @@
 ---
+license: cc-by-4.0
+license_link: https://creativecommons.org/licenses/by/4.0/
 language:
-- ar
-- en
-pipeline_tag: text-generation
+  - ar
+  - en
+library_name: transformers
 tags:
-- arabic
-- hayula-rushd
-- qwen2
-- instruct
-- hayula
-- mlx
-license: apache-2.0
+  - arabic
+  - hayula
+  - Hayula-Rushd-Q-7B
 ---
 
-# Hayula-Rushd-Q-7B
+# hayulalab/Hayula-Rushd-Q-7B
 
-> 🌟 **The rebranded flagship model of Hayula Labs** — formerly Averroes-Q-Instruct.
+Hayula-Rushd-Q-7B - Arabic reasoning model
 
-Arabic instruction-tuned model on 55K human-curated data, rebranded to establish a clean identity under **Hayula Labs** without naming conflicts.
+## License
 
-**Base:** Qwen2.5-7B-Instruct
-**Data:** 55,174 human-curated Arabic instruction-conversation pairs
-**LoRA:** rank=8, scale=0.5, lr=1e-5, iters=5000
-**Train Loss:** 1.434 (final)
-**Training:** ~45 min on M2 Ultra
+This model is licensed under **CC-BY-4.0** (Creative Commons Attribution 4.0 International).
 
-## Why the rebrand?
+**You must attribute** the original creator when using, sharing, or adapting this model:
+- *"Based on hayulalab/Hayula-Rushd-Q-7B by Hayula Lab (https://huggingface.co/hayulalab)"*
 
-The Averroes name had naming conflicts with unrelated models on Hugging Face. Hayula-Rushd-Q-7B (رُشد = guidance/maturity) preserves the intellectual roots of Averroes (Ibn Rushd) while establishing a clean, independent identity under Hayula Labs.
+## Citation
 
-## Usage
-
-
-
-## Links
-- 🔄 **Old repo (redirect):** [hayulalab/Averroes-Q-Instruct](https://huggingface.co/hayulalab/Averroes-Q-Instruct)
-- 🏠 **Hayula Labs:** [hayula.xyz](https://hayula.xyz)
+```bibtex
+@misc{hayulalab-hayula_rushd_q_7b,
+  author = {Hayula Lab},
+  title = {hayulalab/Hayula-Rushd-Q-7B},
+  year = {2026},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/hayulalab/Hayula-Rushd-Q-7B}
+}
+```