Initial commit

config.json

@@ -0,0 +1,62 @@
+{
+    "type": "omy_baseline",
+    "n_obs_steps": 1,
+    "normalization_mapping": {
+        "STATE": "MEAN_STD",
+        "ENVIRONMENT_STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                7
+            ]
+        },
+        "observation.image": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.wrist_image": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                7
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "chunk_size": 10,
+    "n_action_steps": 10,
+    "backbone": "mlp",
+    "vision_backbone": "facebook/dinov3-vitb16-pretrain-lvd1689m",
+    "projection_dim": 0,
+    "freeze_backbone": true,
+    "n_hidden_layers": 10,
+    "hidden_dim": 512,
+    "n_heads": 4,
+    "dim_feedforward": 2048,
+    "feedforward_activation": "gelu",
+    "dropout": 0.1,
+    "pre_norm": true,
+    "n_encoder_layers": 6,
+    "optimizer_lr": 0.0005,
+    "optimizer_weight_decay": 1e-06,
+    "lr_warmup_steps": 1000,
+    "total_training_steps": 500000,
+    "use_policy_training_preset": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf52fdffd7848f665b2f74659222845391edc85b1b5e90504bb57f67abf9cd8
+size 353859112