Upload folder using huggingface_hub

config.json

@@ -57,17 +57,19 @@
         "STATE": "MIN_MAX",
         "ACTION": "MIN_MAX"
     },
-    "vision_backbone": "resnet18",
-    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+    "vision_backbone": "vit_b_16",
+    "pretrained_backbone_weights": null,
     "input_image_size": [
-        320,
-        320
+        224,
+        224
     ],
+    "num_cameras": 4,
+    "vision_freeze_layers": 0,
     "state_dim": 7,
     "action_dim": 7,
     "d_model": 512,
     "nhead": 8,
-    "num_encoder_layers": 4,
+    "num_encoder_layers": 3,
     "num_decoder_layers": 6,
     "dim_feedforward": 512,
     "diffusion_step_embed_dim": 256,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a0adb5d9dc5f7b912ed93243e9e40dcb1701de733d90ccf6ce948a0d8be37c
-size 267791780
+oid sha256:6e2017337e911d4fb3d27c9af88a55c8798d935d5777e0a358674a8802fdc4f4
+size 1132117780