Add pipeline tag and sample usage

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +19 -1
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) | [πŸ’» Code](https://github.com/RecursiveMAS/RecursiveMAS) | [πŸ“„ 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) | [πŸ’» Code](https://github.com/RecursiveMAS/RecursiveMAS) | [πŸ“„ 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
+ ```