Add pipeline tag, library name, and sample usage

Hi! I'm Niels, part of the community science team at Hugging Face.

This PR improves the model card by adding relevant metadata:
- `library_name: transformers`: Since the model architecture is compatible with the Transformers library.
- `pipeline_tag: text-generation`: Ensuring the model is correctly categorized and discoverable.

I've also added a usage section with a code snippet from the GitHub README to help users get started with the RecursiveMAS framework and this specific agent role.

README.md

@@ -2,6 +2,8 @@
 base_model:
 - Qwen/Qwen2.5-Math-1.5B
 license: mit
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 # Sequential-Light-Solver-Qwen2.5-Math-1.5B
@@ -23,6 +25,24 @@ RecursiveMAS treats a multi-agent system as a unified recursive computation, whe
 ⚠️ **Note:** This checkpoint is a **role-specific agent** in [**RecursiveMAS**](https://arxiv.org/abs/2604.25917), rather than a standalone model intended for plain-text generation.  
 For detailed usage instructions, please refer to our [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS).
 
+## Usage
+
+To use this agent as part of the RecursiveMAS framework, you can load the entire system using the following code from the official repository:
+
+```python
+from system_loader import load_mas_system
+
+mas = load_mas_system(
+    style="sequential_light",
+    device="cuda",
+    trust_remote_code=True,
+)
+
+planner = mas.agents["planner"].model
+critic = mas.agents["critic"].model
+solver = mas.agents["solver"].model
+```
+
 ## Model Collections for RecursiveMAS
 
 | Style | Model Collection |