nielsr HF Staff commited on
Commit
ff78401
·
verified ·
1 Parent(s): b944f11

Add pipeline tag and sample usage

Browse files

This PR improves the model card by adding the `text-generation` pipeline tag to the metadata and including a "Sample Usage" section with a code snippet from the official GitHub repository to demonstrate how to load the multi-agent system.

Files changed (1) hide show
  1. README.md +21 -1
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  license: mit
 
3
  ---
4
 
5
  # Sequential-Scaled-Outerlinks
@@ -21,7 +22,26 @@ RecursiveMAS treats a multi-agent system as a unified recursive computation, whe
21
  | Solver-Planner-Outerlink.pt | Solver Agent → Planner Agent |
22
 
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
 
 
1
  ---
2
  license: mit
3
+ pipeline_tag: text-generation
4
  ---
5
 
6
  # Sequential-Scaled-Outerlinks
 
22
  | Solver-Planner-Outerlink.pt | Solver Agent → Planner Agent |
23
 
24
  ⚠️ **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.
25
+
26
+ ## Sample Usage
27
+
28
+ You can load the full multi-agent system (MAS) including these modules using the following code snippet from the [official repository](https://github.com/RecursiveMAS/RecursiveMAS):
29
+
30
+ ```python
31
+ from system_loader import load_mas_system
32
+
33
+ mas = load_mas_system(
34
+ style="sequential_scaled",
35
+ device="cuda",
36
+ trust_remote_code=True,
37
+ )
38
+
39
+ planner = mas.agents["planner"].model
40
+ critic = mas.agents["critic"].model
41
+ solver = mas.agents["solver"].model
42
+ ```
43
+
44
+ For detailed usage instructions, please refer to the GitHub repository.
45
 
46
  ## Model Collections for RecursiveMAS
47