diff --git a/config.json b/config.json
index dfbe323..3c68ae2 100644
--- a/config.json
+++ b/config.json
@@ -1,294 +1,294 @@
 {
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 64,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "initializer_factor": 1.0,
-    "logit_scale_init_value": 2.6592,
-    "model_type": "clip",
-    "projection_dim": 64,
-    "text_config": {
-        "_name_or_path": "",
-        "add_cross_attention": false,
-        "architectures": null,
-        "attention_dropout": 0.1,
-        "bad_words_ids": null,
-        "bos_token_id": 0,
-        "chunk_size_feed_forward": 0,
-        "decoder_start_token_id": null,
-        "diversity_penalty": 0.0,
-        "do_sample": false,
-        "dropout": 0.1,
-        "early_stopping": false,
-        "encoder_no_repeat_ngram_size": 0,
-        "eos_token_id": 2,
-        "finetuning_task": null,
-        "forced_bos_token_id": null,
-        "forced_eos_token_id": null,
-        "gradient_checkpointing": false,
-        "hidden_act": "quick_gelu",
-        "hidden_size": 32,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "initializer_factor": 1.0,
-        "initializer_range": 0.02,
-        "intermediate_size": 37,
-        "is_decoder": false,
-        "is_encoder_decoder": false,
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "layer_norm_eps": 1e-5,
-        "length_penalty": 1.0,
-        "max_length": 20,
-        "max_position_embeddings": 512,
-        "min_length": 0,
-        "model_type": "clip_text_model",
-        "no_repeat_ngram_size": 0,
-        "num_attention_heads": 4,
-        "num_beam_groups": 1,
-        "num_beams": 1,
-        "num_hidden_layers": 5,
-        "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,
-        "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": "4.11.0.dev0",
-        "use_bfloat16": false,
-        "vocab_size": 1000
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
     },
-    "text_config_dict": {
-        "_name_or_path": "",
-        "add_cross_attention": false,
-        "architectures": null,
-        "attention_dropout": 0.1,
-        "bad_words_ids": null,
-        "bos_token_id": 0,
-        "chunk_size_feed_forward": 0,
-        "decoder_start_token_id": null,
-        "diversity_penalty": 0.0,
-        "do_sample": false,
-        "dropout": 0.1,
-        "early_stopping": false,
-        "encoder_no_repeat_ngram_size": 0,
-        "eos_token_id": 2,
-        "finetuning_task": null,
-        "forced_bos_token_id": null,
-        "forced_eos_token_id": null,
-        "gradient_checkpointing": false,
-        "hidden_act": "quick_gelu",
-        "hidden_size": 32,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "initializer_factor": 1.0,
-        "initializer_range": 0.02,
-        "intermediate_size": 37,
-        "is_decoder": false,
-        "is_encoder_decoder": false,
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "layer_norm_eps": 1e-5,
-        "length_penalty": 1.0,
-        "max_length": 20,
-        "max_position_embeddings": 512,
-        "min_length": 0,
-        "model_type": "clip_text_model",
-        "no_repeat_ngram_size": 0,
-        "num_attention_heads": 4,
-        "num_beam_groups": 1,
-        "num_beams": 1,
-        "num_hidden_layers": 5,
-        "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,
-        "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": "4.11.0.dev0",
-        "use_bfloat16": false,
-        "vocab_size": 1000
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 5,
+    "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,
+    "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": "4.11.0.dev0",
+    "use_bfloat16": false,
+    "vocab_size": 99
+  },
+  "text_config_dict": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
     },
-    "transformers_version": null,
-    "vision_config": {
-        "_name_or_path": "",
-        "add_cross_attention": false,
-        "architectures": null,
-        "attention_dropout": 0.1,
-        "bad_words_ids": null,
-        "bos_token_id": null,
-        "chunk_size_feed_forward": 0,
-        "decoder_start_token_id": null,
-        "diversity_penalty": 0.0,
-        "do_sample": false,
-        "dropout": 0.1,
-        "early_stopping": false,
-        "encoder_no_repeat_ngram_size": 0,
-        "eos_token_id": null,
-        "finetuning_task": null,
-        "forced_bos_token_id": null,
-        "forced_eos_token_id": null,
-        "gradient_checkpointing": false,
-        "hidden_act": "quick_gelu",
-        "hidden_size": 32,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "image_size": 30,
-        "initializer_factor": 1.0,
-        "initializer_range": 0.02,
-        "intermediate_size": 37,
-        "is_decoder": false,
-        "is_encoder_decoder": false,
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "layer_norm_eps": 1e-5,
-        "length_penalty": 1.0,
-        "max_length": 20,
-        "min_length": 0,
-        "model_type": "clip_vision_model",
-        "no_repeat_ngram_size": 0,
-        "num_attention_heads": 4,
-        "num_beam_groups": 1,
-        "num_beams": 1,
-        "num_channels": 3,
-        "num_hidden_layers": 5,
-        "num_return_sequences": 1,
-        "output_attentions": false,
-        "output_hidden_states": false,
-        "output_scores": false,
-        "pad_token_id": null,
-        "patch_size": 2,
-        "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,
-        "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": "4.11.0.dev0",
-        "use_bfloat16": false
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
     },
-    "vision_config_dict": {
-        "_name_or_path": "",
-        "add_cross_attention": false,
-        "architectures": null,
-        "attention_dropout": 0.1,
-        "bad_words_ids": null,
-        "bos_token_id": null,
-        "chunk_size_feed_forward": 0,
-        "decoder_start_token_id": null,
-        "diversity_penalty": 0.0,
-        "do_sample": false,
-        "dropout": 0.1,
-        "early_stopping": false,
-        "encoder_no_repeat_ngram_size": 0,
-        "eos_token_id": null,
-        "finetuning_task": null,
-        "forced_bos_token_id": null,
-        "forced_eos_token_id": null,
-        "gradient_checkpointing": false,
-        "hidden_act": "quick_gelu",
-        "hidden_size": 32,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "image_size": 30,
-        "initializer_factor": 1.0,
-        "initializer_range": 0.02,
-        "intermediate_size": 37,
-        "is_decoder": false,
-        "is_encoder_decoder": false,
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "layer_norm_eps": 1e-5,
-        "length_penalty": 1.0,
-        "max_length": 20,
-        "min_length": 0,
-        "model_type": "clip_vision_model",
-        "no_repeat_ngram_size": 0,
-        "num_attention_heads": 4,
-        "num_beam_groups": 1,
-        "num_beams": 1,
-        "num_channels": 3,
-        "num_hidden_layers": 5,
-        "num_return_sequences": 1,
-        "output_attentions": false,
-        "output_hidden_states": false,
-        "output_scores": false,
-        "pad_token_id": null,
-        "patch_size": 2,
-        "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,
-        "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": "4.11.0.dev0",
-        "use_bfloat16": false
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 5,
+    "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,
+    "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": "4.11.0.dev0",
+    "use_bfloat16": false,
+    "vocab_size": 99
+  },
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
     },
-    "vocab_size": 1000
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "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": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 2,
+    "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,
+    "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": "4.11.0.dev0",
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "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": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 2,
+    "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,
+    "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": "4.11.0.dev0",
+    "use_bfloat16": false
+  },
+  "vocab_size": 1000
 }