Add pipeline tag and sample usage
Browse filesThis PR improves the model card for the Distillation-Outerlinks component of RecursiveMAS. Specifically, it:
- Adds the `pipeline_tag: text-generation` to the YAML metadata for better discoverability.
- Includes a "Sample Usage" section with a code snippet from the official repository to help users integrate the model.
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
# Distillation-Outerlinks
|
| 7 |
|
| 8 |
[🌐 Project Page](https://recursivemas.github.io) | [💻 Code](https://github.com/RecursiveMAS/RecursiveMAS) | [📄 Paper](https://arxiv.org/abs/2604.25917)
|
|
@@ -23,6 +23,23 @@ RecursiveMAS treats a multi-agent system as a unified recursive computation, whe
|
|
| 23 |
⚠️ **Note:** This checkpoint contains **Outer RecursiveLink modules** in [**RecursiveMAS**](https://arxiv.org/abs/2604.25917), rather than a standalone model intended for plain-text generation.
|
| 24 |
For detailed usage instructions, please refer to our [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS).
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
## Model Collections for RecursiveMAS
|
| 27 |
|
| 28 |
| Style | Model Collection |
|
|
@@ -50,3 +67,4 @@ For detailed usage instructions, please refer to our [GitHub repository](https:/
|
|
| 50 |
primaryClass={cs.AI},
|
| 51 |
url={https://arxiv.org/abs/2604.25917},
|
| 52 |
}
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
---
|
| 5 |
|
|
|
|
| 6 |
# Distillation-Outerlinks
|
| 7 |
|
| 8 |
[🌐 Project Page](https://recursivemas.github.io) | [💻 Code](https://github.com/RecursiveMAS/RecursiveMAS) | [📄 Paper](https://arxiv.org/abs/2604.25917)
|
|
|
|
| 23 |
⚠️ **Note:** This checkpoint contains **Outer RecursiveLink modules** in [**RecursiveMAS**](https://arxiv.org/abs/2604.25917), rather than a standalone model intended for plain-text generation.
|
| 24 |
For detailed usage instructions, please refer to our [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS).
|
| 25 |
|
| 26 |
+
## Sample Usage
|
| 27 |
+
|
| 28 |
+
You can load the entire multi-agent system using the following code:
|
| 29 |
+
|
| 30 |
+
```python
|
| 31 |
+
from system_loader import load_mas_system
|
| 32 |
+
|
| 33 |
+
mas = load_mas_system(
|
| 34 |
+
style="distillation",
|
| 35 |
+
device="cuda",
|
| 36 |
+
trust_remote_code=True,
|
| 37 |
+
)
|
| 38 |
+
|
| 39 |
+
expert = mas.agents["expert"].model
|
| 40 |
+
learner = mas.agents["learner"].model
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
## Model Collections for RecursiveMAS
|
| 44 |
|
| 45 |
| Style | Model Collection |
|
|
|
|
| 67 |
primaryClass={cs.AI},
|
| 68 |
url={https://arxiv.org/abs/2604.25917},
|
| 69 |
}
|
| 70 |
+
```
|