Upload folder using huggingface_hub
Browse files- category_mapping.json +1 -0
- config.json +78 -0
- evaluation_results.json +654 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- training_args.bin +3 -0
category_mapping.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"category_to_idx": {"biology": 0, "business": 1, "chemistry": 2, "computer science": 3, "economics": 4, "engineering": 5, "health": 6, "history": 7, "law": 8, "math": 9, "other": 10, "philosophy": 11, "physics": 12, "psychology": 13}, "idx_to_category": {"0": "biology", "1": "business", "2": "chemistry", "3": "computer science", "4": "economics", "5": "engineering", "6": "health", "7": "history", "8": "law", "9": "math", "10": "other", "11": "philosophy", "12": "physics", "13": "psychology"}}
|
config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"ModernBertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 50281,
|
8 |
+
"classifier_activation": "gelu",
|
9 |
+
"classifier_bias": false,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"classifier_pooling": "mean",
|
12 |
+
"cls_token_id": 50281,
|
13 |
+
"decoder_bias": true,
|
14 |
+
"deterministic_flash_attn": false,
|
15 |
+
"embedding_dropout": 0.0,
|
16 |
+
"eos_token_id": 50282,
|
17 |
+
"global_attn_every_n_layers": 3,
|
18 |
+
"global_rope_theta": 160000.0,
|
19 |
+
"gradient_checkpointing": false,
|
20 |
+
"hidden_activation": "gelu",
|
21 |
+
"hidden_size": 768,
|
22 |
+
"id2label": {
|
23 |
+
"0": "biology",
|
24 |
+
"1": "business",
|
25 |
+
"2": "chemistry",
|
26 |
+
"3": "computer science",
|
27 |
+
"4": "economics",
|
28 |
+
"5": "engineering",
|
29 |
+
"6": "health",
|
30 |
+
"7": "history",
|
31 |
+
"8": "law",
|
32 |
+
"9": "math",
|
33 |
+
"10": "other",
|
34 |
+
"11": "philosophy",
|
35 |
+
"12": "physics",
|
36 |
+
"13": "psychology"
|
37 |
+
},
|
38 |
+
"initializer_cutoff_factor": 2.0,
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 1152,
|
41 |
+
"label2id": {
|
42 |
+
"biology": 0,
|
43 |
+
"business": 1,
|
44 |
+
"chemistry": 2,
|
45 |
+
"computer science": 3,
|
46 |
+
"economics": 4,
|
47 |
+
"engineering": 5,
|
48 |
+
"health": 6,
|
49 |
+
"history": 7,
|
50 |
+
"law": 8,
|
51 |
+
"math": 9,
|
52 |
+
"other": 10,
|
53 |
+
"philosophy": 11,
|
54 |
+
"physics": 12,
|
55 |
+
"psychology": 13
|
56 |
+
},
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"local_attention": 128,
|
59 |
+
"local_rope_theta": 10000.0,
|
60 |
+
"max_position_embeddings": 8192,
|
61 |
+
"mlp_bias": false,
|
62 |
+
"mlp_dropout": 0.0,
|
63 |
+
"model_type": "modernbert",
|
64 |
+
"norm_bias": false,
|
65 |
+
"norm_eps": 1e-05,
|
66 |
+
"num_attention_heads": 12,
|
67 |
+
"num_hidden_layers": 22,
|
68 |
+
"pad_token_id": 50283,
|
69 |
+
"position_embedding_type": "absolute",
|
70 |
+
"problem_type": "single_label_classification",
|
71 |
+
"repad_logits_with_grad": false,
|
72 |
+
"sep_token_id": 50282,
|
73 |
+
"sparse_pred_ignore_index": -100,
|
74 |
+
"sparse_prediction": false,
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.54.1",
|
77 |
+
"vocab_size": 50368
|
78 |
+
}
|
evaluation_results.json
ADDED
@@ -0,0 +1,654 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"validation_accuracy": 0.8526315789473684,
|
3 |
+
"test_accuracy": 0.8343490304709141,
|
4 |
+
"validation_report": {
|
5 |
+
"biology": {
|
6 |
+
"precision": 0.8425925925925926,
|
7 |
+
"recall": 0.8425925925925926,
|
8 |
+
"f1-score": 0.8425925925925926,
|
9 |
+
"support": 108.0
|
10 |
+
},
|
11 |
+
"business": {
|
12 |
+
"precision": 0.8695652173913043,
|
13 |
+
"recall": 0.8403361344537815,
|
14 |
+
"f1-score": 0.8547008547008547,
|
15 |
+
"support": 119.0
|
16 |
+
},
|
17 |
+
"chemistry": {
|
18 |
+
"precision": 0.861271676300578,
|
19 |
+
"recall": 0.8764705882352941,
|
20 |
+
"f1-score": 0.8688046647230321,
|
21 |
+
"support": 170.0
|
22 |
+
},
|
23 |
+
"computer science": {
|
24 |
+
"precision": 0.8507462686567164,
|
25 |
+
"recall": 0.9193548387096774,
|
26 |
+
"f1-score": 0.8837209302325582,
|
27 |
+
"support": 62.0
|
28 |
+
},
|
29 |
+
"economics": {
|
30 |
+
"precision": 0.7986111111111112,
|
31 |
+
"recall": 0.905511811023622,
|
32 |
+
"f1-score": 0.8487084870848709,
|
33 |
+
"support": 127.0
|
34 |
+
},
|
35 |
+
"engineering": {
|
36 |
+
"precision": 0.8776978417266187,
|
37 |
+
"recall": 0.8413793103448276,
|
38 |
+
"f1-score": 0.8591549295774648,
|
39 |
+
"support": 145.0
|
40 |
+
},
|
41 |
+
"health": {
|
42 |
+
"precision": 0.8095238095238095,
|
43 |
+
"recall": 0.8292682926829268,
|
44 |
+
"f1-score": 0.8192771084337349,
|
45 |
+
"support": 123.0
|
46 |
+
},
|
47 |
+
"history": {
|
48 |
+
"precision": 0.896551724137931,
|
49 |
+
"recall": 0.9122807017543859,
|
50 |
+
"f1-score": 0.9043478260869565,
|
51 |
+
"support": 57.0
|
52 |
+
},
|
53 |
+
"law": {
|
54 |
+
"precision": 0.9585798816568047,
|
55 |
+
"recall": 0.9818181818181818,
|
56 |
+
"f1-score": 0.9700598802395209,
|
57 |
+
"support": 165.0
|
58 |
+
},
|
59 |
+
"math": {
|
60 |
+
"precision": 0.8888888888888888,
|
61 |
+
"recall": 0.9108910891089109,
|
62 |
+
"f1-score": 0.8997555012224939,
|
63 |
+
"support": 202.0
|
64 |
+
},
|
65 |
+
"other": {
|
66 |
+
"precision": 0.7916666666666666,
|
67 |
+
"recall": 0.6884057971014492,
|
68 |
+
"f1-score": 0.7364341085271318,
|
69 |
+
"support": 138.0
|
70 |
+
},
|
71 |
+
"philosophy": {
|
72 |
+
"precision": 0.8375,
|
73 |
+
"recall": 0.8933333333333333,
|
74 |
+
"f1-score": 0.864516129032258,
|
75 |
+
"support": 75.0
|
76 |
+
},
|
77 |
+
"physics": {
|
78 |
+
"precision": 0.8157894736842105,
|
79 |
+
"recall": 0.7948717948717948,
|
80 |
+
"f1-score": 0.8051948051948052,
|
81 |
+
"support": 195.0
|
82 |
+
},
|
83 |
+
"psychology": {
|
84 |
+
"precision": 0.8073394495412844,
|
85 |
+
"recall": 0.7394957983193278,
|
86 |
+
"f1-score": 0.7719298245614035,
|
87 |
+
"support": 119.0
|
88 |
+
},
|
89 |
+
"accuracy": 0.8526315789473684,
|
90 |
+
"macro avg": {
|
91 |
+
"precision": 0.8504517572770369,
|
92 |
+
"recall": 0.8554293045964361,
|
93 |
+
"f1-score": 0.8520855458721199,
|
94 |
+
"support": 1805.0
|
95 |
+
},
|
96 |
+
"weighted avg": {
|
97 |
+
"precision": 0.8520451342930214,
|
98 |
+
"recall": 0.8526315789473684,
|
99 |
+
"f1-score": 0.8515396065019253,
|
100 |
+
"support": 1805.0
|
101 |
+
}
|
102 |
+
},
|
103 |
+
"test_report": {
|
104 |
+
"biology": {
|
105 |
+
"precision": 0.8461538461538461,
|
106 |
+
"recall": 0.822429906542056,
|
107 |
+
"f1-score": 0.8341232227488151,
|
108 |
+
"support": 107.0
|
109 |
+
},
|
110 |
+
"business": {
|
111 |
+
"precision": 0.8648648648648649,
|
112 |
+
"recall": 0.8135593220338984,
|
113 |
+
"f1-score": 0.8384279475982532,
|
114 |
+
"support": 118.0
|
115 |
+
},
|
116 |
+
"chemistry": {
|
117 |
+
"precision": 0.8170731707317073,
|
118 |
+
"recall": 0.788235294117647,
|
119 |
+
"f1-score": 0.8023952095808383,
|
120 |
+
"support": 170.0
|
121 |
+
},
|
122 |
+
"computer science": {
|
123 |
+
"precision": 0.8301886792452831,
|
124 |
+
"recall": 0.7213114754098361,
|
125 |
+
"f1-score": 0.7719298245614035,
|
126 |
+
"support": 61.0
|
127 |
+
},
|
128 |
+
"economics": {
|
129 |
+
"precision": 0.8688524590163934,
|
130 |
+
"recall": 0.8412698412698413,
|
131 |
+
"f1-score": 0.8548387096774194,
|
132 |
+
"support": 126.0
|
133 |
+
},
|
134 |
+
"engineering": {
|
135 |
+
"precision": 0.8394160583941606,
|
136 |
+
"recall": 0.7876712328767124,
|
137 |
+
"f1-score": 0.8127208480565371,
|
138 |
+
"support": 146.0
|
139 |
+
},
|
140 |
+
"health": {
|
141 |
+
"precision": 0.8790322580645161,
|
142 |
+
"recall": 0.8861788617886179,
|
143 |
+
"f1-score": 0.8825910931174089,
|
144 |
+
"support": 123.0
|
145 |
+
},
|
146 |
+
"history": {
|
147 |
+
"precision": 0.9433962264150944,
|
148 |
+
"recall": 0.8771929824561403,
|
149 |
+
"f1-score": 0.9090909090909091,
|
150 |
+
"support": 57.0
|
151 |
+
},
|
152 |
+
"law": {
|
153 |
+
"precision": 0.9457831325301205,
|
154 |
+
"recall": 0.9515151515151515,
|
155 |
+
"f1-score": 0.9486404833836858,
|
156 |
+
"support": 165.0
|
157 |
+
},
|
158 |
+
"math": {
|
159 |
+
"precision": 0.8440366972477065,
|
160 |
+
"recall": 0.9064039408866995,
|
161 |
+
"f1-score": 0.8741092636579573,
|
162 |
+
"support": 203.0
|
163 |
+
},
|
164 |
+
"other": {
|
165 |
+
"precision": 0.6923076923076923,
|
166 |
+
"recall": 0.7122302158273381,
|
167 |
+
"f1-score": 0.7021276595744681,
|
168 |
+
"support": 139.0
|
169 |
+
},
|
170 |
+
"philosophy": {
|
171 |
+
"precision": 0.8333333333333334,
|
172 |
+
"recall": 0.9333333333333333,
|
173 |
+
"f1-score": 0.8805031446540881,
|
174 |
+
"support": 75.0
|
175 |
+
},
|
176 |
+
"physics": {
|
177 |
+
"precision": 0.7853658536585366,
|
178 |
+
"recall": 0.8256410256410256,
|
179 |
+
"f1-score": 0.805,
|
180 |
+
"support": 195.0
|
181 |
+
},
|
182 |
+
"psychology": {
|
183 |
+
"precision": 0.768595041322314,
|
184 |
+
"recall": 0.775,
|
185 |
+
"f1-score": 0.7717842323651453,
|
186 |
+
"support": 120.0
|
187 |
+
},
|
188 |
+
"accuracy": 0.8343490304709141,
|
189 |
+
"macro avg": {
|
190 |
+
"precision": 0.8398856652346834,
|
191 |
+
"recall": 0.8315694702641643,
|
192 |
+
"f1-score": 0.8348773248619237,
|
193 |
+
"support": 1805.0
|
194 |
+
},
|
195 |
+
"weighted avg": {
|
196 |
+
"precision": 0.8352151540840406,
|
197 |
+
"recall": 0.8343490304709141,
|
198 |
+
"f1-score": 0.8341367555565297,
|
199 |
+
"support": 1805.0
|
200 |
+
}
|
201 |
+
},
|
202 |
+
"validation_confusion_matrix": [
|
203 |
+
[
|
204 |
+
91,
|
205 |
+
0,
|
206 |
+
2,
|
207 |
+
0,
|
208 |
+
1,
|
209 |
+
0,
|
210 |
+
9,
|
211 |
+
0,
|
212 |
+
0,
|
213 |
+
0,
|
214 |
+
2,
|
215 |
+
0,
|
216 |
+
0,
|
217 |
+
3
|
218 |
+
],
|
219 |
+
[
|
220 |
+
0,
|
221 |
+
100,
|
222 |
+
1,
|
223 |
+
0,
|
224 |
+
10,
|
225 |
+
0,
|
226 |
+
0,
|
227 |
+
0,
|
228 |
+
0,
|
229 |
+
3,
|
230 |
+
2,
|
231 |
+
2,
|
232 |
+
0,
|
233 |
+
1
|
234 |
+
],
|
235 |
+
[
|
236 |
+
1,
|
237 |
+
0,
|
238 |
+
149,
|
239 |
+
0,
|
240 |
+
0,
|
241 |
+
5,
|
242 |
+
1,
|
243 |
+
0,
|
244 |
+
0,
|
245 |
+
1,
|
246 |
+
0,
|
247 |
+
0,
|
248 |
+
13,
|
249 |
+
0
|
250 |
+
],
|
251 |
+
[
|
252 |
+
0,
|
253 |
+
0,
|
254 |
+
0,
|
255 |
+
57,
|
256 |
+
0,
|
257 |
+
0,
|
258 |
+
0,
|
259 |
+
0,
|
260 |
+
0,
|
261 |
+
3,
|
262 |
+
2,
|
263 |
+
0,
|
264 |
+
0,
|
265 |
+
0
|
266 |
+
],
|
267 |
+
[
|
268 |
+
1,
|
269 |
+
5,
|
270 |
+
0,
|
271 |
+
0,
|
272 |
+
115,
|
273 |
+
0,
|
274 |
+
0,
|
275 |
+
0,
|
276 |
+
1,
|
277 |
+
2,
|
278 |
+
1,
|
279 |
+
2,
|
280 |
+
0,
|
281 |
+
0
|
282 |
+
],
|
283 |
+
[
|
284 |
+
0,
|
285 |
+
0,
|
286 |
+
3,
|
287 |
+
5,
|
288 |
+
0,
|
289 |
+
122,
|
290 |
+
0,
|
291 |
+
0,
|
292 |
+
0,
|
293 |
+
2,
|
294 |
+
0,
|
295 |
+
0,
|
296 |
+
13,
|
297 |
+
0
|
298 |
+
],
|
299 |
+
[
|
300 |
+
5,
|
301 |
+
0,
|
302 |
+
1,
|
303 |
+
0,
|
304 |
+
1,
|
305 |
+
0,
|
306 |
+
102,
|
307 |
+
0,
|
308 |
+
1,
|
309 |
+
0,
|
310 |
+
5,
|
311 |
+
3,
|
312 |
+
1,
|
313 |
+
4
|
314 |
+
],
|
315 |
+
[
|
316 |
+
1,
|
317 |
+
0,
|
318 |
+
0,
|
319 |
+
0,
|
320 |
+
0,
|
321 |
+
0,
|
322 |
+
1,
|
323 |
+
52,
|
324 |
+
0,
|
325 |
+
0,
|
326 |
+
2,
|
327 |
+
1,
|
328 |
+
0,
|
329 |
+
0
|
330 |
+
],
|
331 |
+
[
|
332 |
+
0,
|
333 |
+
0,
|
334 |
+
0,
|
335 |
+
0,
|
336 |
+
1,
|
337 |
+
0,
|
338 |
+
1,
|
339 |
+
0,
|
340 |
+
162,
|
341 |
+
0,
|
342 |
+
1,
|
343 |
+
0,
|
344 |
+
0,
|
345 |
+
0
|
346 |
+
],
|
347 |
+
[
|
348 |
+
0,
|
349 |
+
3,
|
350 |
+
0,
|
351 |
+
2,
|
352 |
+
2,
|
353 |
+
1,
|
354 |
+
1,
|
355 |
+
0,
|
356 |
+
1,
|
357 |
+
184,
|
358 |
+
1,
|
359 |
+
0,
|
360 |
+
3,
|
361 |
+
4
|
362 |
+
],
|
363 |
+
[
|
364 |
+
2,
|
365 |
+
5,
|
366 |
+
2,
|
367 |
+
1,
|
368 |
+
10,
|
369 |
+
0,
|
370 |
+
3,
|
371 |
+
3,
|
372 |
+
2,
|
373 |
+
2,
|
374 |
+
95,
|
375 |
+
2,
|
376 |
+
4,
|
377 |
+
7
|
378 |
+
],
|
379 |
+
[
|
380 |
+
1,
|
381 |
+
0,
|
382 |
+
0,
|
383 |
+
0,
|
384 |
+
1,
|
385 |
+
0,
|
386 |
+
1,
|
387 |
+
2,
|
388 |
+
1,
|
389 |
+
0,
|
390 |
+
1,
|
391 |
+
67,
|
392 |
+
0,
|
393 |
+
1
|
394 |
+
],
|
395 |
+
[
|
396 |
+
1,
|
397 |
+
0,
|
398 |
+
15,
|
399 |
+
0,
|
400 |
+
0,
|
401 |
+
11,
|
402 |
+
0,
|
403 |
+
0,
|
404 |
+
0,
|
405 |
+
9,
|
406 |
+
3,
|
407 |
+
0,
|
408 |
+
155,
|
409 |
+
1
|
410 |
+
],
|
411 |
+
[
|
412 |
+
5,
|
413 |
+
2,
|
414 |
+
0,
|
415 |
+
2,
|
416 |
+
3,
|
417 |
+
0,
|
418 |
+
7,
|
419 |
+
1,
|
420 |
+
1,
|
421 |
+
1,
|
422 |
+
5,
|
423 |
+
3,
|
424 |
+
1,
|
425 |
+
88
|
426 |
+
]
|
427 |
+
],
|
428 |
+
"test_confusion_matrix": [
|
429 |
+
[
|
430 |
+
88,
|
431 |
+
0,
|
432 |
+
0,
|
433 |
+
0,
|
434 |
+
1,
|
435 |
+
0,
|
436 |
+
6,
|
437 |
+
1,
|
438 |
+
2,
|
439 |
+
1,
|
440 |
+
1,
|
441 |
+
0,
|
442 |
+
1,
|
443 |
+
6
|
444 |
+
],
|
445 |
+
[
|
446 |
+
0,
|
447 |
+
96,
|
448 |
+
0,
|
449 |
+
0,
|
450 |
+
5,
|
451 |
+
0,
|
452 |
+
0,
|
453 |
+
0,
|
454 |
+
1,
|
455 |
+
6,
|
456 |
+
3,
|
457 |
+
2,
|
458 |
+
1,
|
459 |
+
4
|
460 |
+
],
|
461 |
+
[
|
462 |
+
2,
|
463 |
+
0,
|
464 |
+
134,
|
465 |
+
1,
|
466 |
+
0,
|
467 |
+
8,
|
468 |
+
0,
|
469 |
+
0,
|
470 |
+
0,
|
471 |
+
2,
|
472 |
+
2,
|
473 |
+
0,
|
474 |
+
21,
|
475 |
+
0
|
476 |
+
],
|
477 |
+
[
|
478 |
+
0,
|
479 |
+
0,
|
480 |
+
1,
|
481 |
+
44,
|
482 |
+
0,
|
483 |
+
3,
|
484 |
+
1,
|
485 |
+
0,
|
486 |
+
0,
|
487 |
+
9,
|
488 |
+
3,
|
489 |
+
0,
|
490 |
+
0,
|
491 |
+
0
|
492 |
+
],
|
493 |
+
[
|
494 |
+
1,
|
495 |
+
4,
|
496 |
+
0,
|
497 |
+
0,
|
498 |
+
106,
|
499 |
+
0,
|
500 |
+
0,
|
501 |
+
0,
|
502 |
+
1,
|
503 |
+
3,
|
504 |
+
6,
|
505 |
+
1,
|
506 |
+
0,
|
507 |
+
4
|
508 |
+
],
|
509 |
+
[
|
510 |
+
1,
|
511 |
+
0,
|
512 |
+
13,
|
513 |
+
1,
|
514 |
+
0,
|
515 |
+
115,
|
516 |
+
0,
|
517 |
+
0,
|
518 |
+
0,
|
519 |
+
6,
|
520 |
+
1,
|
521 |
+
0,
|
522 |
+
9,
|
523 |
+
0
|
524 |
+
],
|
525 |
+
[
|
526 |
+
6,
|
527 |
+
0,
|
528 |
+
1,
|
529 |
+
0,
|
530 |
+
1,
|
531 |
+
1,
|
532 |
+
109,
|
533 |
+
0,
|
534 |
+
0,
|
535 |
+
1,
|
536 |
+
2,
|
537 |
+
0,
|
538 |
+
0,
|
539 |
+
2
|
540 |
+
],
|
541 |
+
[
|
542 |
+
1,
|
543 |
+
0,
|
544 |
+
0,
|
545 |
+
0,
|
546 |
+
0,
|
547 |
+
0,
|
548 |
+
0,
|
549 |
+
50,
|
550 |
+
0,
|
551 |
+
0,
|
552 |
+
5,
|
553 |
+
0,
|
554 |
+
0,
|
555 |
+
1
|
556 |
+
],
|
557 |
+
[
|
558 |
+
0,
|
559 |
+
0,
|
560 |
+
0,
|
561 |
+
0,
|
562 |
+
0,
|
563 |
+
0,
|
564 |
+
0,
|
565 |
+
0,
|
566 |
+
157,
|
567 |
+
0,
|
568 |
+
4,
|
569 |
+
4,
|
570 |
+
0,
|
571 |
+
0
|
572 |
+
],
|
573 |
+
[
|
574 |
+
1,
|
575 |
+
2,
|
576 |
+
0,
|
577 |
+
5,
|
578 |
+
1,
|
579 |
+
0,
|
580 |
+
0,
|
581 |
+
0,
|
582 |
+
0,
|
583 |
+
184,
|
584 |
+
0,
|
585 |
+
0,
|
586 |
+
9,
|
587 |
+
1
|
588 |
+
],
|
589 |
+
[
|
590 |
+
0,
|
591 |
+
9,
|
592 |
+
1,
|
593 |
+
2,
|
594 |
+
7,
|
595 |
+
0,
|
596 |
+
2,
|
597 |
+
1,
|
598 |
+
4,
|
599 |
+
1,
|
600 |
+
99,
|
601 |
+
4,
|
602 |
+
2,
|
603 |
+
7
|
604 |
+
],
|
605 |
+
[
|
606 |
+
0,
|
607 |
+
0,
|
608 |
+
0,
|
609 |
+
0,
|
610 |
+
0,
|
611 |
+
0,
|
612 |
+
0,
|
613 |
+
0,
|
614 |
+
0,
|
615 |
+
0,
|
616 |
+
3,
|
617 |
+
70,
|
618 |
+
0,
|
619 |
+
2
|
620 |
+
],
|
621 |
+
[
|
622 |
+
1,
|
623 |
+
0,
|
624 |
+
14,
|
625 |
+
0,
|
626 |
+
0,
|
627 |
+
10,
|
628 |
+
0,
|
629 |
+
0,
|
630 |
+
0,
|
631 |
+
4,
|
632 |
+
4,
|
633 |
+
0,
|
634 |
+
161,
|
635 |
+
1
|
636 |
+
],
|
637 |
+
[
|
638 |
+
3,
|
639 |
+
0,
|
640 |
+
0,
|
641 |
+
0,
|
642 |
+
1,
|
643 |
+
0,
|
644 |
+
6,
|
645 |
+
1,
|
646 |
+
1,
|
647 |
+
1,
|
648 |
+
10,
|
649 |
+
3,
|
650 |
+
1,
|
651 |
+
93
|
652 |
+
]
|
653 |
+
]
|
654 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ac997d635f7abf77e40553d15af381cf775aad0f20362c3e8f2e0e9d0353abe
|
3 |
+
size 598476704
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "|||IP_ADDRESS|||",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<|padding|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"50254": {
|
20 |
+
"content": " ",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": false
|
26 |
+
},
|
27 |
+
"50255": {
|
28 |
+
"content": " ",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"50256": {
|
36 |
+
"content": " ",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"50257": {
|
44 |
+
"content": " ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"50258": {
|
52 |
+
"content": " ",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"50259": {
|
60 |
+
"content": " ",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"50260": {
|
68 |
+
"content": " ",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"50261": {
|
76 |
+
"content": " ",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"50262": {
|
84 |
+
"content": " ",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"50263": {
|
92 |
+
"content": " ",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"50264": {
|
100 |
+
"content": " ",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"50265": {
|
108 |
+
"content": " ",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"50266": {
|
116 |
+
"content": " ",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"50267": {
|
124 |
+
"content": " ",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"50268": {
|
132 |
+
"content": " ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"50269": {
|
140 |
+
"content": " ",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"50270": {
|
148 |
+
"content": " ",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"50271": {
|
156 |
+
"content": " ",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"50272": {
|
164 |
+
"content": " ",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"50273": {
|
172 |
+
"content": " ",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"50274": {
|
180 |
+
"content": " ",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"50275": {
|
188 |
+
"content": " ",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"50276": {
|
196 |
+
"content": " ",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"50277": {
|
204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"50278": {
|
212 |
+
"content": "|||PHONE_NUMBER|||",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"50279": {
|
220 |
+
"content": "<|endoftext|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"50280": {
|
228 |
+
"content": "[UNK]",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"50281": {
|
236 |
+
"content": "[CLS]",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"50282": {
|
244 |
+
"content": "[SEP]",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"50283": {
|
252 |
+
"content": "[PAD]",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"50284": {
|
260 |
+
"content": "[MASK]",
|
261 |
+
"lstrip": true,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"50285": {
|
268 |
+
"content": "[unused0]",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"50286": {
|
276 |
+
"content": "[unused1]",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"50287": {
|
284 |
+
"content": "[unused2]",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"50288": {
|
292 |
+
"content": "[unused3]",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"50289": {
|
300 |
+
"content": "[unused4]",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"50290": {
|
308 |
+
"content": "[unused5]",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"50291": {
|
316 |
+
"content": "[unused6]",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"50292": {
|
324 |
+
"content": "[unused7]",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"50293": {
|
332 |
+
"content": "[unused8]",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"50294": {
|
340 |
+
"content": "[unused9]",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"50295": {
|
348 |
+
"content": "[unused10]",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"50296": {
|
356 |
+
"content": "[unused11]",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"50297": {
|
364 |
+
"content": "[unused12]",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"50298": {
|
372 |
+
"content": "[unused13]",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"50299": {
|
380 |
+
"content": "[unused14]",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"50300": {
|
388 |
+
"content": "[unused15]",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"50301": {
|
396 |
+
"content": "[unused16]",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"50302": {
|
404 |
+
"content": "[unused17]",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"50303": {
|
412 |
+
"content": "[unused18]",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"50304": {
|
420 |
+
"content": "[unused19]",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"50305": {
|
428 |
+
"content": "[unused20]",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"50306": {
|
436 |
+
"content": "[unused21]",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"50307": {
|
444 |
+
"content": "[unused22]",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"50308": {
|
452 |
+
"content": "[unused23]",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"50309": {
|
460 |
+
"content": "[unused24]",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"50310": {
|
468 |
+
"content": "[unused25]",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"50311": {
|
476 |
+
"content": "[unused26]",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"50312": {
|
484 |
+
"content": "[unused27]",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"50313": {
|
492 |
+
"content": "[unused28]",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"50314": {
|
500 |
+
"content": "[unused29]",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"50315": {
|
508 |
+
"content": "[unused30]",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"50316": {
|
516 |
+
"content": "[unused31]",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"50317": {
|
524 |
+
"content": "[unused32]",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"50318": {
|
532 |
+
"content": "[unused33]",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"50319": {
|
540 |
+
"content": "[unused34]",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"50320": {
|
548 |
+
"content": "[unused35]",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"50321": {
|
556 |
+
"content": "[unused36]",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"50322": {
|
564 |
+
"content": "[unused37]",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"50323": {
|
572 |
+
"content": "[unused38]",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"50324": {
|
580 |
+
"content": "[unused39]",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"50325": {
|
588 |
+
"content": "[unused40]",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"50326": {
|
596 |
+
"content": "[unused41]",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"50327": {
|
604 |
+
"content": "[unused42]",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"50328": {
|
612 |
+
"content": "[unused43]",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"50329": {
|
620 |
+
"content": "[unused44]",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"50330": {
|
628 |
+
"content": "[unused45]",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"50331": {
|
636 |
+
"content": "[unused46]",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"50332": {
|
644 |
+
"content": "[unused47]",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"50333": {
|
652 |
+
"content": "[unused48]",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"50334": {
|
660 |
+
"content": "[unused49]",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"50335": {
|
668 |
+
"content": "[unused50]",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": true,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"50336": {
|
676 |
+
"content": "[unused51]",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"50337": {
|
684 |
+
"content": "[unused52]",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": true,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"50338": {
|
692 |
+
"content": "[unused53]",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": true,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"50339": {
|
700 |
+
"content": "[unused54]",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": true,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"50340": {
|
708 |
+
"content": "[unused55]",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"50341": {
|
716 |
+
"content": "[unused56]",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": true,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"50342": {
|
724 |
+
"content": "[unused57]",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": true,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"50343": {
|
732 |
+
"content": "[unused58]",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": true,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"50344": {
|
740 |
+
"content": "[unused59]",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"50345": {
|
748 |
+
"content": "[unused60]",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": true,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"50346": {
|
756 |
+
"content": "[unused61]",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": true,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"50347": {
|
764 |
+
"content": "[unused62]",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": true,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"50348": {
|
772 |
+
"content": "[unused63]",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": true,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"50349": {
|
780 |
+
"content": "[unused64]",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"50350": {
|
788 |
+
"content": "[unused65]",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": true,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"50351": {
|
796 |
+
"content": "[unused66]",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": true,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"50352": {
|
804 |
+
"content": "[unused67]",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"50353": {
|
812 |
+
"content": "[unused68]",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": true,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"50354": {
|
820 |
+
"content": "[unused69]",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": true,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"50355": {
|
828 |
+
"content": "[unused70]",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": true,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"50356": {
|
836 |
+
"content": "[unused71]",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": true,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": false
|
842 |
+
},
|
843 |
+
"50357": {
|
844 |
+
"content": "[unused72]",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"50358": {
|
852 |
+
"content": "[unused73]",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"50359": {
|
860 |
+
"content": "[unused74]",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"50360": {
|
868 |
+
"content": "[unused75]",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"50361": {
|
876 |
+
"content": "[unused76]",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"50362": {
|
884 |
+
"content": "[unused77]",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"50363": {
|
892 |
+
"content": "[unused78]",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"50364": {
|
900 |
+
"content": "[unused79]",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"50365": {
|
908 |
+
"content": "[unused80]",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"50366": {
|
916 |
+
"content": "[unused81]",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"50367": {
|
924 |
+
"content": "[unused82]",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
}
|
931 |
+
},
|
932 |
+
"clean_up_tokenization_spaces": true,
|
933 |
+
"cls_token": "[CLS]",
|
934 |
+
"extra_special_tokens": {},
|
935 |
+
"mask_token": "[MASK]",
|
936 |
+
"model_input_names": [
|
937 |
+
"input_ids",
|
938 |
+
"attention_mask"
|
939 |
+
],
|
940 |
+
"model_max_length": 8192,
|
941 |
+
"pad_token": "[PAD]",
|
942 |
+
"sep_token": "[SEP]",
|
943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
944 |
+
"unk_token": "[UNK]"
|
945 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c469ad6d75724ea5e403a6a9e14cd2b3afbb0aebef6b5e8e129064bdaf81e4ab
|
3 |
+
size 5777
|