diff --git a/.gitattributes b/.gitattributes
index 040de50870ffaa594319320098be4bbdb03f083e..42cb2cbbb829632be20c580b9e7565b926f04f39 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 open_clip_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
diff --git a/config.json b/config.json
index b783dddee0e4d54f0daf7f9e88fd58c2beab3e8b..14244325ca2eba11045b3170a7ec0276681ca20a 100644
--- a/config.json
+++ b/config.json
@@ -1,176 +1,180 @@
 {
-    "architectures": [
-      "CLIPModel"
-    ],
+  "_commit_hash": null,
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 1280,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "initializer_factor": 1.0,
-    "logit_scale_init_value": 2.6592,
-    "model_type": "clip",
-    "projection_dim": 1280,
-    "text_config": {
-      "_name_or_path": "",
-      "add_cross_attention": false,
-      "architectures": null,
-      "attention_dropout": 0.0,
-      "bad_words_ids": null,
-      "bos_token_id": 0,
-      "chunk_size_feed_forward": 0,
-      "cross_attention_hidden_size": null,
-      "decoder_start_token_id": null,
-      "diversity_penalty": 0.0,
-      "do_sample": false,
-      "dropout": 0.0,
-      "early_stopping": false,
-      "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": 2,
-      "exponential_decay_length_penalty": null,
-      "finetuning_task": null,
-      "forced_bos_token_id": null,
-      "forced_eos_token_id": null,
-      "hidden_act": "gelu",
-      "hidden_size": 1280,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "initializer_factor": 1.0,
-      "initializer_range": 0.02,
-      "intermediate_size": 5120,
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "layer_norm_eps": 1e-05,
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "max_position_embeddings": 77,
-      "min_length": 0,
-      "model_type": "clip_text_model",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 20,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_hidden_layers": 32,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": 1,
-      "prefix": null,
-      "problem_type": null,
-      "pruned_heads": {},
-      "remove_invalid_values": false,
-      "repetition_penalty": 1.0,
-      "return_dict": true,
-      "return_dict_in_generate": false,
-      "sep_token_id": null,
-      "task_specific_params": null,
-      "temperature": 1.0,
-      "tf_legacy_loss": false,
-      "tie_encoder_decoder": false,
-      "tie_word_embeddings": true,
-      "tokenizer_class": null,
-      "top_k": 50,
-      "top_p": 1.0,
-      "torch_dtype": null,
-      "torchscript": false,
-      "transformers_version": "4.21.3",
-      "typical_p": 1.0,
-      "use_bfloat16": false,
-      "vocab_size": 49408
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
     },
-    "text_config_dict": {
-      "hidden_act": "gelu",
-      "hidden_size": 1280,
-      "intermediate_size": 5120,
-      "num_attention_heads": 20,
-      "num_hidden_layers": 32
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 20,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "intermediate_size": 5120,
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1664,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
     },
-    "torch_dtype": "float32",
-    "transformers_version": null,
-    "vision_config": {
-      "_name_or_path": "",
-      "add_cross_attention": false,
-      "architectures": null,
-      "attention_dropout": 0.0,
-      "bad_words_ids": null,
-      "bos_token_id": null,
-      "chunk_size_feed_forward": 0,
-      "cross_attention_hidden_size": null,
-      "decoder_start_token_id": null,
-      "diversity_penalty": 0.0,
-      "do_sample": false,
-      "dropout": 0.0,
-      "early_stopping": false,
-      "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": null,
-      "exponential_decay_length_penalty": null,
-      "finetuning_task": null,
-      "forced_bos_token_id": null,
-      "forced_eos_token_id": null,
-      "hidden_act": "gelu",
-      "hidden_size": 1664,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "image_size": 224,
-      "initializer_factor": 1.0,
-      "initializer_range": 0.02,
-      "intermediate_size": 8192,
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "layer_norm_eps": 1e-05,
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "min_length": 0,
-      "model_type": "clip_vision_model",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 16,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_channels": 3,
-      "num_hidden_layers": 48,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": null,
-      "patch_size": 14,
-      "prefix": null,
-      "problem_type": null,
-      "pruned_heads": {},
-      "remove_invalid_values": false,
-      "repetition_penalty": 1.0,
-      "return_dict": true,
-      "return_dict_in_generate": false,
-      "sep_token_id": null,
-      "task_specific_params": null,
-      "temperature": 1.0,
-      "tf_legacy_loss": false,
-      "tie_encoder_decoder": false,
-      "tie_word_embeddings": true,
-      "tokenizer_class": null,
-      "top_k": 50,
-      "top_p": 1.0,
-      "torch_dtype": null,
-      "torchscript": false,
-      "transformers_version": "4.21.3",
-      "typical_p": 1.0,
-      "use_bfloat16": false
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
     },
-    "vision_config_dict": {
-      "hidden_act": "gelu",
-      "hidden_size": 1664,
-      "intermediate_size": 8192,
-      "num_attention_heads": 16,
-      "num_hidden_layers": 48,
-      "patch_size": 14
-    }
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 48,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_act": "gelu",
+    "hidden_size": 1664,
+    "intermediate_size": 8192,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "patch_size": 14
   }
-  
\ No newline at end of file
+}
diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2722fda4ab1382b31d4d6f6b9d0c63188f97c5be
--- /dev/null
+++ b/pytorch_model-00001-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cfbc5cb39085ce8eedff70562d3c54795abdccd132d6dcb8e1462fbd71a1a0
+size 9990161549
diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e2b6d873efccbc3740000d61a806a6c5c5c000f2
--- /dev/null
+++ b/pytorch_model-00002-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31847ed3e29dade79ab29eafc0f8230200ec46233ce1d8f6e71b987a9fbacf47
+size 168539369
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d18c617ba44d53ab80ad7a54456d1696383903b6
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,1303 @@
+{
+  "metadata": {
+    "total_size": 10158271092
+  },
+  "weight_map": {
+    "logit_scale": "pytorch_model-00001-of-00002.bin",
+    "text_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.embeddings.position_ids": "pytorch_model-00001-of-00002.bin",
+    "text_model.embeddings.token_embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "text_model.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "text_model.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_projection.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin",
+    "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.embeddings.position_ids": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.40.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.41.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.42.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.43.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.44.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.45.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.46.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.47.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.47.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00002.bin",
+    "visual_projection.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}