Add files using upload-large-folder tool

.gitattributes

@@ -1,3 +1,5 @@
 checkpoint-* filter=lfs diff=lfs merge=lfs -text
 experiment_cfg/* filter=lfs diff=lfs merge=lfs -text
 runs/* filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

checkpoint-500/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6d791fd2480c671a761135eb9cf425012709799653d335dc6e16fc795f1b9c
+size 1829

checkpoint-500/experiment_cfg/metadata.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2883598ebc9f9d3ecef8ca0e6a9031299fe24f148e30a79ca28044e08cb5e72c
+size 5919

checkpoint-500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71f119fd9609bde723745722cd070999ca0886c1b0cee714aebc0c9b721ec32
+size 4938446392

checkpoint-500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acf13549713af43baa8caa02a9613f0b8ddccdad1426034420f4eeff44865d8
+size 3821736024

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90cee11a978518c61891fa13863c771b18224beb5143346356eda94ec916299
+size 90287

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bf5cbc4596b44e7b1406e7333cedbf28c9cef7d89a071c740a57c12f20760a
+size 10272357262

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4b739e7d0f948be23d89ba3cfa95ecc6f9539d89bbd8d8cc39afa42ead9e39
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2523ecdb7c00f012b6edc4618dc718bc76648144c4b2022b6abe048cfe5c2f52
+size 9403

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
   "action_dim": 32,
   "action_head_cfg": {
     "action_dim": 32,

experiment_cfg/metadata.json

@@ -1,259 +1,3 @@
-{
-    "new_embodiment": {
-        "statistics": {
-            "state": {
-                "single_arm": {
-                    "max": [
-                        73.125,
-                        192.744140625,
-                        173.056640625,
-                        96.50390625,
-                        16.875,
-                        39.46629333496094
-                    ],
-                    "min": [
-                        -11.77734375,
-                        107.05078125,
-                        38.232421875,
-                        -87.099609375,
-                        -60.380859375,
-                        -2.528089761734009
-                    ],
-                    "mean": [
-                        17.49227523803711,
-                        169.3153076171875,
-                        131.19882202148438,
-                        37.52477264404297,
-                        -4.550821304321289,
-                        8.92446231842041
-                    ],
-                    "std": [
-                        16.42386245727539,
-                        21.5903263092041,
-                        30.546218872070312,
-                        32.77304458618164,
-                        9.99141788482666,
-                        11.073107719421387
-                    ],
-                    "q01": [
-                        0.4166015625000008,
-                        109.60927734375,
-                        44.18261718750001,
-                        -87.01171875,
-                        -46.68310546875,
-                        -2.528089761734009
-                    ],
-                    "q99": [
-                        67.8515625,
-                        192.744140625,
-                        172.880859375,
-                        80.771484375,
-                        11.25,
-                        33.7780876159668
-                    ]
-                },
-                "gripper": {
-                    "max": [
-                        37.6171875,
-                        193.359375,
-                        178.857421875,
-                        106.083984375,
-                        55.37109375,
-                        43.535987854003906
-                    ],
-                    "min": [
-                        -75.5859375,
-                        120.05859375,
-                        57.392578125,
-                        -105.029296875,
-                        -83.408203125,
-                        -1.6072676181793213
-                    ],
-                    "mean": [
-                        -8.77374267578125,
-                        172.61582946777344,
-                        145.73057556152344,
-                        33.48724365234375,
-                        4.162647724151611,
-                        17.054317474365234
-                    ],
-                    "std": [
-                        18.441892623901367,
-                        18.212947845458984,
-                        32.55632019042969,
-                        30.88580894470215,
-                        11.133428573608398,
-                        12.858570098876953
-                    ],
-                    "q01": [
-                        -71.4779296875,
-                        131.923828125,
-                        67.79619140625,
-                        -36.44208984375,
-                        -8.876953125,
-                        -1.6072676181793213
-                    ],
-                    "q99": [
-                        14.765625,
-                        193.359375,
-                        178.76953125,
-                        90.55019531249985,
-                        34.47597656249986,
-                        43.39622497558594
-                    ]
-                }
-            },
-            "action": {
-                "single_arm": {
-                    "max": [
-                        74.70703125,
-                        197.2265625,
-                        183.1640625,
-                        96.85546875,
-                        18.193359375,
-                        42.25352096557617
-                    ],
-                    "min": [
-                        -13.447265625,
-                        107.40234375,
-                        34.541015625,
-                        -88.154296875,
-                        -60.64453125,
-                        -7.2908034324646
-                    ],
-                    "mean": [
-                        17.84712791442871,
-                        173.34576416015625,
-                        130.4300994873047,
-                        37.48929214477539,
-                        -4.6664605140686035,
-                        8.580680847167969
-                    ],
-                    "std": [
-                        16.606603622436523,
-                        22.975238800048828,
-                        32.07327651977539,
-                        32.946292877197266,
-                        10.011028289794922,
-                        11.577706336975098
-                    ],
-                    "q01": [
-                        0.52734375,
-                        110.830078125,
-                        41.9431640625,
-                        -87.099609375,
-                        -47.09970703125,
-                        -3.976802110671997
-                    ],
-                    "q99": [
-                        68.37890625,
-                        196.171875,
-                        182.900390625,
-                        80.33203125,
-                        11.30537109374993,
-                        33.38856506347656
-                    ]
-                },
-                "gripper": {
-                    "max": [
-                        40.95703125,
-                        197.666015625,
-                        183.427734375,
-                        106.962890625,
-                        56.6015625,
-                        43.637916564941406
-                    ],
-                    "min": [
-                        -75.76171875,
-                        121.11328125,
-                        54.052734375,
-                        -108.369140625,
-                        -84.814453125,
-                        -6.660973072052002
-                    ],
-                    "mean": [
-                        -8.914937019348145,
-                        174.48568725585938,
-                        146.09896850585938,
-                        33.1975212097168,
-                        4.200614929199219,
-                        16.537626266479492
-                    ],
-                    "std": [
-                        19.090517044067383,
-                        18.074752807617188,
-                        34.33214569091797,
-                        31.37607765197754,
-                        11.111959457397461,
-                        13.707727432250977
-                    ],
-                    "q01": [
-                        -72.34716796875,
-                        132.71484375,
-                        65.42314453125,
-                        -39.73974609375,
-                        -9.140625,
-                        -4.355251789093018
-                    ],
-                    "q99": [
-                        15.61201171874993,
-                        196.787109375,
-                        183.076171875,
-                        89.99033203124979,
-                        34.56386718749986,
-                        43.637916564941406
-                    ]
-                }
-            }
-        },
-        "modalities": {
-            "video": {
-                "webcam": {
-                    "resolution": [
-                        640,
-                        480
-                    ],
-                    "channels": 3,
-                    "fps": 30.0
-                }
-            },
-            "state": {
-                "single_arm": {
-                    "absolute": true,
-                    "rotation_type": null,
-                    "shape": [
-                        6
-                    ],
-                    "continuous": true
-                },
-                "gripper": {
-                    "absolute": true,
-                    "rotation_type": null,
-                    "shape": [
-                        6
-                    ],
-                    "continuous": true
-                }
-            },
-            "action": {
-                "single_arm": {
-                    "absolute": true,
-                    "rotation_type": null,
-                    "shape": [
-                        6
-                    ],
-                    "continuous": true
-                },
-                "gripper": {
-                    "absolute": true,
-                    "rotation_type": null,
-                    "shape": [
-                        6
-                    ],
-                    "continuous": true
-                }
-            }
-        },
-        "embodiment_tag": "new_embodiment"
-    }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:2883598ebc9f9d3ecef8ca0e6a9031299fe24f148e30a79ca28044e08cb5e72c
+size 5919

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71f119fd9609bde723745722cd070999ca0886c1b0cee714aebc0c9b721ec32
+size 4938446392

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acf13549713af43baa8caa02a9613f0b8ddccdad1426034420f4eeff44865d8
+size 3821736024

model.safetensors.index.json

@@ -0,0 +1,809 @@
+{
+  "metadata": {
+    "total_size": 8760067008
+  },
+  "weight_map": {
+    "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
+    "backbone.linear.bias": "model-00002-of-00002.safetensors",
+    "backbone.linear.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}