Add metadata and usage example

This PR adds the correct metadata (license and pipeline tag) and includes a usage example from the official GitHub README. It also keeps the existing links to the paper and code.

README.md

@@ -1,3 +1,17 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+---
+
 This is the official MatGPTQ checkpoint of `Qwen/Qwen3-8B`, produced as described in the [**"MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization"**](https://arxiv.org/abs/2602.03537) paper.
 
-This model can be run via vLLM. Checkout our integration at [IST-DASLab/MatGPTQ](https://github.com/IST-DASLab/MatGPTQ)
+This model can be run via vLLM. Checkout our integration at [IST-DASLab/MatGPTQ](https://github.com/IST-DASLab/MatGPTQ)
+
+## Usage
+
+```python
+import vllm_matgptq
+from vllm import LLM
+
+llm = LLM(model="your-model", quantization="my_quant")
+```