omarelsayeed commited on
Commit
f2bf7fd
·
1 Parent(s): 728109e

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "word_embedding_dimension": 256,
3
  "pooling_mode_cls_token": false,
4
  "pooling_mode_mean_tokens": true,
5
  "pooling_mode_max_tokens": false,
 
1
  {
2
+ "word_embedding_dimension": 768,
3
  "pooling_mode_cls_token": false,
4
  "pooling_mode_mean_tokens": true,
5
  "pooling_mode_max_tokens": false,
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
 
11
  # {MODEL_NAME}
12
 
13
- This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 256 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
 
15
  <!--- Describe your model here -->
16
 
@@ -85,9 +85,9 @@ The model was trained with the parameters:
85
 
86
  **DataLoader**:
87
 
88
- `torch.utils.data.dataloader.DataLoader` of length 719 with parameters:
89
  ```
90
- {'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
91
  ```
92
 
93
  **Loss**:
@@ -106,7 +106,7 @@ Parameters of the fit()-Method:
106
  "max_grad_norm": 1,
107
  "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
108
  "optimizer_params": {
109
- "lr": 5e-05
110
  },
111
  "scheduler": "WarmupLinear",
112
  "steps_per_epoch": null,
@@ -119,8 +119,8 @@ Parameters of the fit()-Method:
119
  ## Full Model Architecture
120
  ```
121
  SentenceTransformer(
122
- (0): Transformer({'max_seq_length': 60, 'do_lower_case': False}) with Transformer model: BertModel
123
- (1): Pooling({'word_embedding_dimension': 256, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
124
  )
125
  ```
126
 
 
10
 
11
  # {MODEL_NAME}
12
 
13
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
 
15
  <!--- Describe your model here -->
16
 
 
85
 
86
  **DataLoader**:
87
 
88
+ `torch.utils.data.dataloader.DataLoader` of length 3543 with parameters:
89
  ```
90
+ {'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
91
  ```
92
 
93
  **Loss**:
 
106
  "max_grad_norm": 1,
107
  "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
108
  "optimizer_params": {
109
+ "lr": 0.0005
110
  },
111
  "scheduler": "WarmupLinear",
112
  "steps_per_epoch": null,
 
119
  ## Full Model Architecture
120
  ```
121
  SentenceTransformer(
122
+ (0): Transformer({'max_seq_length': 50, 'do_lower_case': False}) with Transformer model: BertModel
123
+ (1): Pooling({'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})
124
  )
125
  ```
126
 
config.json CHANGED
@@ -1,149 +1,32 @@
1
  {
2
  "_name_or_path": "/root/.cache/torch/sentence_transformers/omarelsayeed_DISASTER_MODEL_PRECHATS/",
3
- "_num_labels": 2,
4
  "architectures": [
5
  "BertModel"
6
  ],
7
  "attention_probs_dropout_prob": 0.1,
8
  "classifier_dropout": null,
9
- "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
- "hidden_size": 256,
13
- "id2label": {
14
- "0": "\u0627\u0645\u0627\u0643\u0646 \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a",
15
- "1": "\u0645\u0648\u0627\u0639\u064a\u062f \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a",
16
- "2": "\u0648\u0638\u064a\u0641\u0629",
17
- "3": "\u0645\u062e\u0627\u0644\u0641\u0627\u062a \u0627\u0644\u0645\u0631\u0648\u0631",
18
- "4": "\u0627\u0633\u062a\u0644\u0627\u0645 \u0627\u0644\u0631\u062e\u0635\u0629",
19
- "5": "\u062a\u062c\u062f\u064a\u062f \u0627\u0644\u0631\u062e\u0635\u0629",
20
- "6": "\u0627\u0636\u0627\u0641\u0647 \u0643\u0627\u0631\u062a",
21
- "7": "\u062d\u0630\u0641 \u0643\u0627\u0631\u062a",
22
- "8": "\u062a\u062e\u0637\u0649 \u062d\u062f \u0645\u0633\u0645\u0648\u062d",
23
- "9": "\u0628\u0637\u0627\u0642\u0647 \u0645\u0639\u0644\u0642\u0629/\u0627\u0644\u0628\u0637\u0627\u0642\u0629 \u0645\u062d\u0638\u0648\u0631\u0629",
24
- "10": "\u062d\u0633\u0627\u0628 \u062c\u062f\u064a\u062f",
25
- "11": "\u062a\u0633\u062c\u064a\u0644 \u062f\u062e\u0648\u0644 \u062d\u0633\u0627\u0628",
26
- "12": "\u062d\u0630\u0641 \u062d\u0633\u0627\u0628",
27
- "13": "\u062d\u0633\u0627\u0628 \u0645\u062d\u0638\u0648\u0631",
28
- "14": "\u062a\u062d\u062f\u064a\u062b \u062d\u0633\u0627\u0628",
29
- "15": "\u0637\u0628\u0627\u0639\u0647 \u0641\u0627\u062a\u0648\u0631\u0629",
30
- "16": "\u0627\u0633\u062a\u0641\u0633\u0627\u0631 \u0639\u0646 \u062d\u0627\u0644\u0629 \u0627\u0644\u0639\u0645\u0644\u064a\u0629/\u0627\u0644\u0639\u0645\u0644\u064a\u0629 \u0627\u062a\u062e\u0635\u0645\u062a",
31
- "17": "\u0634\u0631\u0627\u0621 \u0645\u0627\u0643\u064a\u0646\u0647",
32
- "18": "\u062a\u062d\u0648\u064a\u0644 \u0645\u0628\u0644\u063a \u0645\u0627\u0644\u064a",
33
- "19": "\u062e\u062f\u0645\u0627\u062a \u0627\u0644\u0642\u0648\u0627\u062a \u0627\u0644\u0645\u0633\u0644\u062d\u0629",
34
- "20": "\u0634\u062d\u0646 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644",
35
- "21": "\u0641\u0627\u062a\u0648\u0631\u0629 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644",
36
- "22": "\u0645\u064a\u0627\u0647",
37
- "23": "\u063a\u0627\u0632",
38
- "24": "\u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621",
39
- "25": "\u0641\u0648\u0631\u064a \u0628\u0627\u064a",
40
- "26": "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621",
41
- "27": "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0645\u064a\u0627\u0647",
42
- "28": "\u0645\u0634\u0643\u0644\u0629 \u0641\u064a \u0627\u0644\u062a\u0637\u0628\u064a\u0642",
43
- "29": "\u0627\u0633\u062a\u0631\u0627\u062c\u0639 \u0642\u064a\u0645\u0629 \u0645\u0627\u0644\u064a\u0629",
44
- "30": "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u062f\u0648\u0644\u064a\u0629",
45
- "31": "\u062a\u0630\u0627\u0643\u0631",
46
- "32": "\u0627\u0644\u062a\u0623\u0645\u064a\u0646",
47
- "33": "\u0627\u0644\u0646\u0642\u0627\u0628\u0627\u062a",
48
- "34": "\u062a\u0639\u0644\u064a\u0645",
49
- "35": "\u062e\u062f\u0645\u0629 \u0627\u0644\u0639\u0645\u0644\u0627\u0621",
50
- "36": "\u0627\u0644\u0639\u0627\u0628 \u0627\u0648\u0646\u0644\u0627\u064a\u0646",
51
- "37": "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u0645\u0627\u0644\u064a\u0629 \u0648 \u0628\u0646\u0648\u0643",
52
- "38": "\u062a\u0645\u0648\u064a\u0644 \u0645\u062a\u0646\u0627\u0647\u064a \u0627\u0644\u0635\u063a\u0631",
53
- "39": "\u0645\u062f\u0641\u0648\u0639\u0627\u062a \u0627\u0648\u0646\u0644\u0627\u064a\u0646",
54
- "40": "\u062a\u0628\u0631\u0639\u0627\u062a",
55
- "41": "\u0627\u0634\u062a\u0631\u0627\u0643 \u0646\u0648\u0627\u062f\u064a",
56
- "42": "Yellow Card",
57
- "43": "\u062c\u0648\u0627\u0626\u0632",
58
- "44": "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u063a\u0627\u0632",
59
- "45": "\u0627\u0644\u0627\u0646\u062a\u0631\u0646\u062a \u0627\u0644\u0645\u0646\u0632\u0644\u064a",
60
- "46": "\u0627\u0644\u062a\u0644\u064a\u0641\u0648\u0646 \u0627\u0644\u0623\u0631\u0636\u064a",
61
- "47": "\u0641\u0648\u0631\u064a \u062a\u0642\u0633\u064a\u0637",
62
- "48": "\u0641\u0648\u0631\u064a \u064a\u0648\u0645\u064a",
63
- "49": "\u062a\u0642\u062f\u064a\u0645 \u0634\u0643\u0648\u064a",
64
- "50": "\u0633\u0643\u0646 \u0648\u0639\u0642\u0627\u0631\u0627\u062a",
65
- "51": "\u0641\u0648\u0631\u064a \u0644\u0644\u0648\u0633\u0627\u0637\u0629 \u0627\u0644\u062a\u0623\u0645\u064a\u0646\u064a\u0629",
66
- "52": "\u062a\u0623\u0645\u064a\u0646 \u0627\u062c\u062a\u0645\u0627\u0639\u064a",
67
- "53": "\u0627\u064a\u062f\u0627\u0639",
68
- "54": "Consumer Finance",
69
- "55": "\u062a\u0633\u062c\u064a\u0644 \u0627\u0644\u0648\u062d\u062f\u0627\u062a \u0627\u0644\u0639\u0642\u0627\u0631\u064a\u0629",
70
- "56": "\u0633\u062d\u0628",
71
- "57": "\u0634\u0631\u0627\u0621 \u0645\u0646 \u0645\u062d\u0644"
72
- },
73
  "initializer_range": 0.02,
74
- "intermediate_size": 1024,
75
- "label2id": {
76
- "Consumer Finance": 54,
77
- "Yellow Card": 42,
78
- "\u0627\u0633\u062a\u0631\u0627\u062c\u0639 \u0642\u064a\u0645\u0629 \u0645\u0627\u0644\u064a\u0629": 29,
79
- "\u0627\u0633\u062a\u0641\u0633\u0627\u0631 \u0639\u0646 \u062d\u0627\u0644\u0629 \u0627\u0644\u0639\u0645\u0644\u064a\u0629/\u0627\u0644\u0639\u0645\u0644\u064a\u0629 \u0627\u062a\u062e\u0635\u0645\u062a": 16,
80
- "\u0627\u0633\u062a\u0644\u0627\u0645 \u0627\u0644\u0631\u062e\u0635\u0629": 4,
81
- "\u0627\u0634\u062a\u0631\u0627\u0643 \u0646\u0648\u0627\u062f\u064a": 41,
82
- "\u0627\u0636\u0627\u0641\u0647 \u0643\u0627\u0631\u062a": 6,
83
- "\u0627\u0644\u0627\u0646\u062a\u0631\u0646\u062a \u0627\u0644\u0645\u0646\u0632\u0644\u064a": 45,
84
- "\u0627\u0644\u062a\u0623\u0645\u064a\u0646": 32,
85
- "\u0627\u0644\u062a\u0644\u064a\u0641\u0648\u0646 \u0627\u0644\u0623\u0631\u0636\u064a": 46,
86
- "\u0627\u0644\u0639\u0627\u0628 \u0627\u0648\u0646\u0644\u0627\u064a\u0646": 36,
87
- "\u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621": 24,
88
- "\u0627\u0644\u0646\u0642\u0627\u0628\u0627\u062a": 33,
89
- "\u0627\u0645\u0627\u0643\u0646 \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a": 0,
90
- "\u0627\u064a\u062f\u0627\u0639": 53,
91
- "\u0628\u0637\u0627\u0642\u0647 \u0645\u0639\u0644\u0642\u0629/\u0627\u0644\u0628\u0637\u0627\u0642\u0629 \u0645\u062d\u0638\u0648\u0631\u0629": 9,
92
- "\u062a\u0623\u0645\u064a\u0646 \u0627\u062c\u062a\u0645\u0627\u0639\u064a": 52,
93
- "\u062a\u0628\u0631\u0639\u0627\u062a": 40,
94
- "\u062a\u062c\u062f\u064a\u062f \u0627\u0644\u0631\u062e\u0635\u0629": 5,
95
- "\u062a\u062d\u062f\u064a\u062b \u062d\u0633\u0627\u0628": 14,
96
- "\u062a\u062d\u0648\u064a\u0644 \u0645\u0628\u0644\u063a \u0645\u0627\u0644\u064a": 18,
97
- "\u062a\u062e\u0637\u0649 \u062d\u062f \u0645\u0633\u0645\u0648\u062d": 8,
98
- "\u062a\u0630\u0627\u0643\u0631": 31,
99
- "\u062a\u0633\u062c\u064a\u0644 \u0627\u0644\u0648\u062d\u062f\u0627\u062a \u0627\u0644\u0639\u0642\u0627\u0631\u064a\u0629": 55,
100
- "\u062a\u0633\u062c\u064a\u0644 \u062f\u062e\u0648\u0644 \u062d\u0633\u0627\u0628": 11,
101
- "\u062a\u0639\u0644\u064a\u0645": 34,
102
- "\u062a\u0642\u062f\u064a\u0645 \u0634\u0643\u0648\u064a": 49,
103
- "\u062a\u0645\u0648\u064a\u0644 \u0645\u062a\u0646\u0627\u0647\u064a \u0627\u0644\u0635\u063a\u0631": 38,
104
- "\u062c\u0648\u0627\u0626\u0632": 43,
105
- "\u062d\u0630\u0641 \u062d\u0633\u0627\u0628": 12,
106
- "\u062d\u0630\u0641 \u0643\u0627\u0631\u062a": 7,
107
- "\u062d\u0633\u0627\u0628 \u062c\u062f\u064a\u062f": 10,
108
- "\u062d\u0633\u0627\u0628 \u0645\u062d\u0638\u0648\u0631": 13,
109
- "\u062e\u062f\u0645\u0627\u062a \u0627\u0644\u0642\u0648\u0627\u062a \u0627\u0644\u0645\u0633\u0644\u062d\u0629": 19,
110
- "\u062e\u062f\u0645\u0629 \u0627\u0644\u0639\u0645\u0644\u0627\u0621": 35,
111
- "\u0633\u062d\u0628": 56,
112
- "\u0633\u0643\u0646 \u0648\u0639\u0642\u0627\u0631\u0627\u062a": 50,
113
- "\u0634\u062d\u0646 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644": 20,
114
- "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u063a\u0627\u0632": 44,
115
- "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0643\u0647\u0631\u0628\u0627\u0621": 26,
116
- "\u0634\u062d\u0646 \u0643\u0627\u0631\u062a \u0627\u0644\u0645\u064a\u0627\u0647": 27,
117
- "\u0634\u0631\u0627\u0621 \u0645\u0627\u0643\u064a\u0646\u0647": 17,
118
- "\u0634\u0631\u0627\u0621 \u0645\u0646 \u0645\u062d\u0644": 57,
119
- "\u0637\u0628\u0627\u0639\u0647 \u0641\u0627\u062a\u0648\u0631\u0629": 15,
120
- "\u063a\u0627\u0632": 23,
121
- "\u0641\u0627\u062a\u0648\u0631\u0629 \u0627\u0644\u0645\u0648\u0628\u0627\u064a\u0644": 21,
122
- "\u0641\u0648\u0631\u064a \u0628\u0627\u064a": 25,
123
- "\u0641\u0648\u0631\u064a \u062a\u0642\u0633\u064a\u0637": 47,
124
- "\u0641\u0648\u0631\u064a \u0644\u0644\u0648\u0633\u0627\u0637\u0629 \u0627\u0644\u062a\u0623\u0645\u064a\u0646\u064a\u0629": 51,
125
- "\u0641\u0648\u0631\u064a \u064a\u0648\u0645\u064a": 48,
126
- "\u0645\u062e\u0627\u0644\u0641\u0627\u062a \u0627\u0644\u0645\u0631\u0648\u0631": 3,
127
- "\u0645\u062f\u0641\u0648\u0639\u0627\u062a \u0627\u0648\u0646\u0644\u0627\u064a\u0646": 39,
128
- "\u0645\u0634\u0643\u0644\u0629 \u0641\u064a \u0627\u0644\u062a\u0637\u0628\u064a\u0642": 28,
129
- "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u062f\u0648\u0644\u064a\u0629": 30,
130
- "\u0645\u0639\u0627\u0645\u0644\u0627\u062a \u0645\u0627\u0644\u064a\u0629 \u0648 \u0628\u0646\u0648\u0643": 37,
131
- "\u0645\u0648\u0627\u0639\u064a\u062f \u0641\u0631\u0648\u0639 \u0641\u0648\u0631\u064a": 1,
132
- "\u0645\u064a\u0627\u0647": 22,
133
- "\u0648\u0638\u064a\u0641\u0629": 2
134
- },
135
  "layer_norm_eps": 1e-12,
136
  "max_position_embeddings": 512,
137
  "model_type": "bert",
138
- "num_attention_heads": 4,
139
- "num_hidden_layers": 4,
140
- "output_past": true,
141
  "pad_token_id": 0,
 
 
 
 
 
 
142
  "position_embedding_type": "absolute",
143
- "problem_type": "single_label_classification",
144
  "torch_dtype": "float32",
145
  "transformers_version": "4.30.2",
146
  "type_vocab_size": 2,
147
  "use_cache": true,
148
- "vocab_size": 32000
149
  }
 
1
  {
2
  "_name_or_path": "/root/.cache/torch/sentence_transformers/omarelsayeed_DISASTER_MODEL_PRECHATS/",
 
3
  "architectures": [
4
  "BertModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
+ "directionality": "bidi",
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
  "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
 
19
  "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "pooling": "average",
26
  "position_embedding_type": "absolute",
 
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.30.2",
29
  "type_vocab_size": 2,
30
  "use_cache": true,
31
+ "vocab_size": 119547
32
  }
config_sentence_transformers.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "__version__": {
3
  "sentence_transformers": "2.2.2",
4
- "transformers": "4.33.0",
5
  "pytorch": "2.0.0"
6
  }
7
  }
 
1
  {
2
  "__version__": {
3
  "sentence_transformers": "2.2.2",
4
+ "transformers": "4.30.2",
5
  "pytorch": "2.0.0"
6
  }
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8e68dd0bf7d28487247d76aedce9b88c2bbfda70bb5cc8bba812cdb14f332eb
3
- size 46223689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4120f56e79e6e9dd467c6c22ed034791779f35a9084749ec4f7d0860225f9bde
3
+ size 711484973
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "max_seq_length": 60,
3
  "do_lower_case": false
4
  }
 
1
  {
2
+ "max_seq_length": 50,
3
  "do_lower_case": false
4
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,65 +1,13 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
- "full_tokenizer_file": null,
49
  "mask_token": "[MASK]",
50
- "max_length": 512,
51
- "model_max_length": 1000000000000000019884624838656,
52
- "never_split": null,
53
- "pad_to_multiple_of": null,
54
  "pad_token": "[PAD]",
55
- "pad_token_type_id": 0,
56
- "padding_side": "right",
57
  "sep_token": "[SEP]",
58
- "stride": 0,
59
  "strip_accents": null,
60
  "tokenize_chinese_chars": true,
61
  "tokenizer_class": "BertTokenizer",
62
- "truncation_side": "right",
63
- "truncation_strategy": "longest_first",
64
  "unk_token": "[UNK]"
65
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
+ "do_lower_case": false,
 
 
5
  "mask_token": "[MASK]",
6
+ "model_max_length": 512,
 
 
 
7
  "pad_token": "[PAD]",
 
 
8
  "sep_token": "[SEP]",
 
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
  "tokenizer_class": "BertTokenizer",
 
 
12
  "unk_token": "[UNK]"
13
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff