hyungseoksongh commited on
Commit
0445eb7
·
verified ·
1 Parent(s): 74191f8

Model card: policy architecture

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -12,8 +12,8 @@ tags:
12
 
13
  # PCBWorld checkpoints
14
 
15
- Trained routing policies from the PCBWorld paper. Weights only; all are small transformer policies trained
16
- from scratch, seeds 42–45.
17
 
18
  - Paper: [PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation](https://arxiv.org/abs/2607.05915)
19
  - Code: [github.com/LGAI-Research/PCBWorld](https://github.com/LGAI-Research/PCBWorld)
 
12
 
13
  # PCBWorld checkpoints
14
 
15
+ Trained routing policies from the PCBWorld paper. Weights only. All are decoder-only transformer policies
16
+ (4 layers, d_model 128, 8 heads, FFN 512; 1.6M parameters) trained from scratch, seeds 42–45.
17
 
18
  - Paper: [PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation](https://arxiv.org/abs/2607.05915)
19
  - Code: [github.com/LGAI-Research/PCBWorld](https://github.com/LGAI-Research/PCBWorld)