Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,51 @@
+---
+license: other
+license_name: hayula-research-license-v1
+license_link: https://hayula.xyz/license
+language:
+- en
+- ar
+tags:
+- code
+- programming
+- python
+- lora
+- qwen2.5
+- averroes
+- hayula
+pipeline_tag: text-generation
+base_model: hayulalab/Averroes-Q-Instruct
+---
+
+# Hayula-Algorithm-7B-LoRA
+
+Code Development Specialist — LoRA adapter for code generation and analysis.
+
+Named after Al-Khwarizmi, father of algebra and algorithms.
+
+## Model Details
+
+- **Base Model:** Averroes-Q-Instruct (Qwen2.5-7B)
+- **Method:** LoRA (rank 8, scale 20, 16 layers)
+- **Data:** 19,962 code instruction pairs
+- **Adapter:** 44MB
+- **Val Loss:** 1.389
+
+## Training
+
+- 500 iterations, batch size 2, lr 1e-5
+- max_seq_length: 1024
+- Hardware: Apple M2 Ultra (192GB)
+
+## Usage
+
+```python
+from mlx_lm import load, generate
+from mlx_lm.lora import load_adapters
+model, tokenizer = load("hayulalab/Averroes-Q-Instruct")
+load_adapters(model, "hayulalab/Hayula-Algorithm-7B-LoRA")
+```
+
+## License
+
+Hayula Research License v1.0