| { |
| "backbone": { |
| "hidden_dim": 1024, |
| "kwargs": { |
| "attention_bias": false, |
| "head_dim": 128, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 40960, |
| "num_heads": 16, |
| "num_key_value_heads": 8, |
| "num_layers": 28, |
| "rms_norm_eps": 1e-06, |
| "use_sliding_window": false |
| }, |
| "type": "qwen3" |
| }, |
| "encoder": { |
| "kwargs": { |
| "extra_fields": [], |
| "fourier_max": 10.0, |
| "fourier_min": 0.01, |
| "hidden_dim": 1024, |
| "modalities": [ |
| { |
| "field": "action", |
| "required": true, |
| "std": 0.02, |
| "tokens": 1, |
| "type": "discrete", |
| "vocab_size": 4 |
| }, |
| { |
| "field": "observation", |
| "required": true, |
| "std": 0.02, |
| "tokens": 1, |
| "type": "discrete", |
| "vocab_size": 64 |
| }, |
| { |
| "field": "reward", |
| "required": true, |
| "std": 0.02, |
| "tokens": 1, |
| "type": "fourier" |
| }, |
| { |
| "field": "done", |
| "required": true, |
| "std": 0.02, |
| "tokens": 1, |
| "type": "discrete", |
| "vocab_size": 5 |
| } |
| ], |
| "std": 0.02 |
| }, |
| "type": "numeric" |
| }, |
| "format": "mouse-core-model-v1", |
| "heads": { |
| "action_head": "action_value", |
| "heads": [ |
| { |
| "hidden_dim": 1024, |
| "in_features": 1024, |
| "name": "action_value", |
| "num_layers": 1, |
| "out_features": 4, |
| "scale": 0.1, |
| "type": "action_value", |
| "use_norm": true |
| } |
| ] |
| }, |
| "hidden_dim": 1024 |
| } |
|
|
