Add LICENSE-BASE.md with Gemma license attribution

- Links to official Gemma License Terms
- Clarifies derivative work components
- Provides proper attribution to Google and author

LICENSE-BASE.md

@@ -0,0 +1,35 @@
+# License Information
+
+This model is a **derivative work** based on [Google's Gemma 3 1B Instruction-Tuned model](https://huggingface.co/google/gemma-3-1b-it).
+
+## Base Model License
+
+The original Gemma 3 1B model is licensed under the **Gemma License** by Google.
+
+**You must review and comply with the official Gemma License Terms:**
+- **Official License**: https://ai.google.dev/gemma/terms
+- **Model Card**: https://huggingface.co/google/gemma-3-1b-it
+
+## Derivative Work
+
+This quantized and optimized version includes:
+- **Q4_0 and Q4_K_M quantization** using llama.cpp
+- **Bilingual configuration** (Italian/English) via Modelfile
+- **Raspberry Pi optimization** with tuned parameters
+
+**Quantization, optimization, and bilingual configuration** by Antonio (chill123).
+
+## Usage Restrictions
+
+By using this model, you agree to:
+1. Comply with Google's Gemma License Terms
+2. Review the prohibited use cases outlined in the official license
+3. Provide proper attribution to the original model creators
+
+## Attribution
+
+**Original Model**: Google Gemma 3 1B IT
+**Quantization & Optimization**: Antonio (chill123)
+**License**: Gemma License (see link above)
+
+For any licensing questions regarding the base model, please refer to Google's official Gemma documentation.