Upload folder using huggingface_hub

config.json

@@ -0,0 +1,15 @@
+{
+    "hidden_size": 1024,
+    "num_hidden_layers": 24,
+    "layer_norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "hidden_act": "quick_gelu",
+    "attention_dropout": 0.0,
+    "intermediate_size": 4096,
+    "initializer_range": 0.02,
+    "image_size": 336,
+    "num_channels": 3,
+    "patch_size": 14,
+    "projection_dim": 512,
+    "model_type": "clip_vision_model"
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+    "crop_size": {
+        "height": 336,
+        "width": 336
+    },
+    "do_center_crop": true,
+    "do_normalize": true,
+    "do_resize": true,
+    "feature_extractor_type": "CLIPFeatureExtractor",
+    "image_mean": [
+        0.48145466,
+        0.4578275,
+        0.40821073
+    ],
+    "image_std": [
+        0.26862954,
+        0.26130258,
+        0.27577711
+    ],
+    "resample": 3,
+    "size": 336
+}

pytorch_model-00001-of-00001.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7039b502b452699e95f3dd57e94a828e02091a2741bf7842dfe9e00b03bcc8ce
+size 1214165707

pytorch_model.bin.index.json

@@ -0,0 +1,398 @@
+{
+    "metadata": {
+        "total_size": 1214029824
+    },
+    "weight_map": {
+        "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00001.bin",
+        "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00001.bin",
+        "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00001.bin"
+    }
+}