TCMLLM commited on Nov 27, 2024

Commit

3bf9a0d

verified ·

1 Parent(s): 0c470db

Initial release.

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

fold0/1_Pooling/config.json +10 -0
fold0/config.json +26 -0
fold0/config_sentence_transformers.json +10 -0
fold0/model.safetensors +3 -0
fold0/modules.json +14 -0
fold0/sentence_bert_config.json +4 -0
fold0/special_tokens_map.json +7 -0
fold0/tokenizer.json +0 -0
fold0/tokenizer_config.json +58 -0
fold0/vocab.txt +0 -0
fold1/1_Pooling/config.json +10 -0
fold1/config.json +26 -0
fold1/config_sentence_transformers.json +10 -0
fold1/model.safetensors +3 -0
fold1/modules.json +14 -0
fold1/sentence_bert_config.json +4 -0
fold1/special_tokens_map.json +7 -0
fold1/tokenizer.json +0 -0
fold1/tokenizer_config.json +58 -0
fold1/vocab.txt +0 -0
fold2/1_Pooling/config.json +10 -0
fold2/config.json +26 -0
fold2/config_sentence_transformers.json +10 -0
fold2/model.safetensors +3 -0
fold2/modules.json +14 -0
fold2/sentence_bert_config.json +4 -0
fold2/special_tokens_map.json +7 -0
fold2/tokenizer.json +0 -0
fold2/tokenizer_config.json +58 -0
fold2/vocab.txt +0 -0
fold3/1_Pooling/config.json +10 -0
fold3/config.json +26 -0
fold3/config_sentence_transformers.json +10 -0
fold3/model.safetensors +3 -0
fold3/modules.json +14 -0
fold3/sentence_bert_config.json +4 -0
fold3/special_tokens_map.json +7 -0
fold3/tokenizer.json +0 -0
fold3/tokenizer_config.json +58 -0
fold3/vocab.txt +0 -0
fold4/1_Pooling/config.json +10 -0
fold4/config.json +26 -0
fold4/config_sentence_transformers.json +10 -0
fold4/model.safetensors +3 -0
fold4/modules.json +14 -0
fold4/sentence_bert_config.json +4 -0
fold4/special_tokens_map.json +7 -0
fold4/tokenizer.json +0 -0
fold4/tokenizer_config.json +58 -0
fold4/vocab.txt +0 -0

fold0/1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

fold0/config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "_name_or_path": "/var/lib/docker/huarui/TreeSimilarity/pretrain_model/SapBERT-from-PubMedBERT-fulltext",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

fold0/config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

fold0/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:899cfe21f66e82d69fb14e50304d98958c4da956fc85bb6423878a7c2d2eafe5
+size 437951328

fold0/modules.json ADDED Viewed

	@@ -0,0 +1,14 @@

+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

fold0/sentence_bert_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 30,
+  "do_lower_case": false
+}

fold0/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

fold0/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

fold0/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

fold0/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

fold1/1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

fold1/config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "_name_or_path": "/var/lib/docker/huarui/TreeSimilarity/pretrain_model/SapBERT-from-PubMedBERT-fulltext",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

fold1/config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

fold1/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a25382ddbf925b41f4ae38ea3f4df9f231807eb6bccc2cd4eeb5a372a919b6c
+size 437951328

fold1/modules.json ADDED Viewed

	@@ -0,0 +1,14 @@

+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

fold1/sentence_bert_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 30,
+  "do_lower_case": false
+}

fold1/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

fold1/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

fold1/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

fold1/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

fold2/1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

fold2/config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "_name_or_path": "/var/lib/docker/huarui/TreeSimilarity/pretrain_model/SapBERT-from-PubMedBERT-fulltext",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

fold2/config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

fold2/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:36620354921a12ba8452f9ee1ecf7b31ec8ddea9169bc7c8b7703e636802feef
+size 437951328

fold2/modules.json ADDED Viewed

	@@ -0,0 +1,14 @@

+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

fold2/sentence_bert_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 30,
+  "do_lower_case": false
+}

fold2/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

fold2/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

fold2/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

fold2/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

fold3/1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

fold3/config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "_name_or_path": "/var/lib/docker/huarui/TreeSimilarity/pretrain_model/SapBERT-from-PubMedBERT-fulltext",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

fold3/config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

fold3/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cbaf019a25d7aacb58ea0f60b3e118a1db6ddf3e5af0589ce17ca0805b168d41
+size 437951328

fold3/modules.json ADDED Viewed

	@@ -0,0 +1,14 @@

+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

fold3/sentence_bert_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 30,
+  "do_lower_case": false
+}

fold3/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

fold3/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

fold3/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

fold3/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

fold4/1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

fold4/config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "_name_or_path": "/var/lib/docker/huarui/TreeSimilarity/pretrain_model/SapBERT-from-PubMedBERT-fulltext",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

fold4/config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

fold4/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:14a083ed620abcfac0d924bc90d2a99043268e546e85d632826f0f6c5bc52428
+size 437951328

fold4/modules.json ADDED Viewed

	@@ -0,0 +1,14 @@

+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

fold4/sentence_bert_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 30,
+  "do_lower_case": false
+}

fold4/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

fold4/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

fold4/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

fold4/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff