initial upload

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<ACT_0>": 32001,
+  "<ACT_10>": 32011,
+  "<ACT_11>": 32012,
+  "<ACT_12>": 32013,
+  "<ACT_13>": 32014,
+  "<ACT_14>": 32015,
+  "<ACT_15>": 32016,
+  "<ACT_16>": 32017,
+  "<ACT_17>": 32018,
+  "<ACT_18>": 32019,
+  "<ACT_19>": 32020,
+  "<ACT_1>": 32002,
+  "<ACT_20>": 32021,
+  "<ACT_21>": 32022,
+  "<ACT_22>": 32023,
+  "<ACT_23>": 32024,
+  "<ACT_24>": 32025,
+  "<ACT_25>": 32026,
+  "<ACT_26>": 32027,
+  "<ACT_27>": 32028,
+  "<ACT_28>": 32029,
+  "<ACT_29>": 32030,
+  "<ACT_2>": 32003,
+  "<ACT_30>": 32031,
+  "<ACT_31>": 32032,
+  "<ACT_3>": 32004,
+  "<ACT_4>": 32005,
+  "<ACT_5>": 32006,
+  "<ACT_6>": 32007,
+  "<ACT_7>": 32008,
+  "<ACT_8>": 32009,
+  "<ACT_9>": 32010,
+  "<PAD>": 32000
+}

config.json

@@ -0,0 +1,503 @@
+{
+  "arch_specifier": "no-align+fused-gelu-mlp",
+  "architectures": [
+    "OpenVLAForActionPrediction"
+  ],
+  "hf_llm_id": "meta-llama/Llama-2-7b-hf",
+  "image_resize_strategy": "resize-naive",
+  "image_sizes": [
+    224,
+    224
+  ],
+  "llm_backbone_id": "llama2-7b-pure",
+  "llm_max_length": 2048,
+  "model_type": "openvla",
+  "n_action_bins": 256,
+  "norm_stats": {
+    "ego4d_split_1": {
+      "action": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      },
+      "num_trajectories": 16567,
+      "num_transitions": 89259,
+      "proprio": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      }
+    },
+    "ego4d_split_2": {
+      "action": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      },
+      "num_trajectories": 19147,
+      "num_transitions": 106175,
+      "proprio": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      }
+    },
+    "ego4d_split_3": {
+      "action": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      },
+      "num_trajectories": 18167,
+      "num_transitions": 99426,
+      "proprio": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      }
+    },
+    "ego4d_split_4": {
+      "action": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      },
+      "num_trajectories": 20014,
+      "num_transitions": 119935,
+      "proprio": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      }
+    }
+  },
+  "output_projector_states": false,
+  "pad_to_multiple_of": 64,
+  "pad_token_id": 32000,
+  "text_config": {
+    "model_type": "llama",
+    "pad_token_id": 32000,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "timm_model_ids": [
+    "vit_large_patch14_reg4_dinov2.lvd142m",
+    "vit_so400m_patch14_siglip_224"
+  ],
+  "timm_override_act_layers": [
+    null,
+    null
+  ],
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_fused_vision_backbone": true,
+  "vision_backbone_id": "dinosiglip-vit-so-224px"
+}

dataset_statistics.json

@@ -0,0 +1,466 @@
+{
+  "ego4d_split_1": {
+    "action": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "proprio": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 89259,
+    "num_trajectories": 16567
+  },
+  "ego4d_split_2": {
+    "action": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "proprio": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 106175,
+    "num_trajectories": 19147
+  },
+  "ego4d_split_3": {
+    "action": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "proprio": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 99426,
+    "num_trajectories": 18167
+  },
+  "ego4d_split_4": {
+    "action": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "proprio": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 119935,
+    "num_trajectories": 20014
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32000,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87aa610201a743d6808b10a429c3e33510d180b861c73709533e873b3b9a5ac9
+size 6948961960

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ee47d6e2badb3306e54551f14a7c8388a0a605b0e3b2ecc3635c5ed91fdfc9
+size 6971232040

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25117b6ac82b3c3462e7b64096ea6ff97447ba9f503f136306d58d1f7c08145
+size 1162406824

model.safetensors.index.json

@@ -0,0 +1,989 @@
+{
+  "metadata": {
+    "total_size": 15082474368
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
+    "projector.fc1.bias": "model-00001-of-00003.safetensors",
+    "projector.fc1.weight": "model-00001-of-00003.safetensors",
+    "projector.fc2.bias": "model-00001-of-00003.safetensors",
+    "projector.fc2.weight": "model-00001-of-00003.safetensors",
+    "projector.fc3.bias": "model-00001-of-00003.safetensors",
+    "projector.fc3.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.ls1.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.ls2.scale_factor": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.cls_token": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.norm.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.norm.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.pos_embed": "model-00001-of-00003.safetensors",
+    "vision_backbone.featurizer.reg_token": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.kv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.kv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.latent": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.norm.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.norm.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.q.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.attn_pool.q.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.norm.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.norm.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
+    "vision_backbone.fused_featurizer.pos_embed": "model-00001-of-00003.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,110 @@
+{
+  "image_processor_type": "PrismaticImageProcessor",
+  "image_resize_strategy": "resize-naive",
+  "input_sizes": [
+    [
+      3,
+      224,
+      224
+    ],
+    [
+      3,
+      224,
+      224
+    ]
+  ],
+  "interpolations": [
+    "bicubic",
+    "bicubic"
+  ],
+  "means": [
+    [
+      0.485,
+      0.456,
+      0.406
+    ],
+    [
+      0.485,
+      0.456,
+      0.406
+    ]
+  ],
+  "processor_class": "PrismaticProcessor",
+  "stds": [
+    [
+      0.229,
+      0.224,
+      0.225
+    ],
+    [
+      0.229,
+      0.224,
+      0.225
+    ]
+  ],
+  "tvf_crop_params": [
+    {
+      "output_size": [
+        224,
+        224
+      ]
+    },
+    {
+      "output_size": [
+        224,
+        224
+      ]
+    }
+  ],
+  "tvf_do_letterbox": false,
+  "tvf_letterbox_fill": null,
+  "tvf_normalize_params": [
+    {
+      "inplace": false,
+      "mean": [
+        0.484375,
+        0.455078125,
+        0.40625
+      ],
+      "std": [
+        0.228515625,
+        0.2236328125,
+        0.224609375
+      ]
+    },
+    {
+      "inplace": false,
+      "mean": [
+        0.484375,
+        0.455078125,
+        0.40625
+      ],
+      "std": [
+        0.228515625,
+        0.2236328125,
+        0.224609375
+      ]
+    }
+  ],
+  "tvf_resize_params": [
+    {
+      "antialias": true,
+      "interpolation": 3,
+      "max_size": null,
+      "size": [
+        224,
+        224
+      ]
+    },
+    {
+      "antialias": true,
+      "interpolation": 3,
+      "max_size": null,
+      "size": [
+        224,
+        224
+      ]
+    }
+  ],
+  "use_fused_vision_backbone": true
+}

special_tokens_map.json

@@ -0,0 +1,256 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<ACT_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ACT_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,340 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<ACT_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<ACT_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<ACT_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<ACT_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<ACT_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<ACT_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<ACT_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<ACT_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<ACT_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<ACT_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<ACT_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<ACT_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<ACT_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<ACT_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<ACT_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<ACT_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<ACT_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<ACT_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<ACT_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<ACT_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<ACT_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<ACT_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<ACT_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<ACT_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<ACT_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<ACT_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<ACT_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<ACT_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<ACT_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<ACT_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<ACT_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<ACT_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<ACT_0>",
+    "<ACT_1>",
+    "<ACT_2>",
+    "<ACT_3>",
+    "<ACT_4>",
+    "<ACT_5>",
+    "<ACT_6>",
+    "<ACT_7>",
+    "<ACT_8>",
+    "<ACT_9>",
+    "<ACT_10>",
+    "<ACT_11>",
+    "<ACT_12>",
+    "<ACT_13>",
+    "<ACT_14>",
+    "<ACT_15>",
+    "<ACT_16>",
+    "<ACT_17>",
+    "<ACT_18>",
+    "<ACT_19>",
+    "<ACT_20>",
+    "<ACT_21>",
+    "<ACT_22>",
+    "<ACT_23>",
+    "<ACT_24>",
+    "<ACT_25>",
+    "<ACT_26>",
+    "<ACT_27>",
+    "<ACT_28>",
+    "<ACT_29>",
+    "<ACT_30>",
+    "<ACT_31>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "processor_class": "PrismaticProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}