root
commited on
Commit
·
a252ac1
1
Parent(s):
8bba306
Fix empty input
Browse files- config.json +36 -2
- flax_model.msgpack +2 -2
- pytorch_model.bin +2 -2
- special_tokens_map.json +103 -0
- tf_model.h5 +2 -2
- tokenizer.json +97 -1029
- tokenizer_config.json +106 -0
config.json
CHANGED
@@ -6,20 +6,54 @@
|
|
6 |
"d_kv": 64,
|
7 |
"d_model": 768,
|
8 |
"decoder_start_token_id": 0,
|
|
|
9 |
"dropout_rate": 0.1,
|
10 |
"eos_token_id": 1,
|
11 |
"feed_forward_proj": "relu",
|
12 |
"initializer_factor": 1.0,
|
13 |
"is_encoder_decoder": true,
|
|
|
14 |
"layer_norm_epsilon": 1e-06,
|
15 |
"model_type": "t5",
|
|
|
16 |
"num_decoder_layers": 12,
|
17 |
"num_heads": 12,
|
18 |
"num_layers": 12,
|
19 |
"output_past": true,
|
20 |
"pad_token_id": 0,
|
|
|
21 |
"relative_attention_num_buckets": 32,
|
22 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
6 |
"d_kv": 64,
|
7 |
"d_model": 768,
|
8 |
"decoder_start_token_id": 0,
|
9 |
+
"dense_act_fn": "relu",
|
10 |
"dropout_rate": 0.1,
|
11 |
"eos_token_id": 1,
|
12 |
"feed_forward_proj": "relu",
|
13 |
"initializer_factor": 1.0,
|
14 |
"is_encoder_decoder": true,
|
15 |
+
"is_gated_act": false,
|
16 |
"layer_norm_epsilon": 1e-06,
|
17 |
"model_type": "t5",
|
18 |
+
"n_positions": 512,
|
19 |
"num_decoder_layers": 12,
|
20 |
"num_heads": 12,
|
21 |
"num_layers": 12,
|
22 |
"output_past": true,
|
23 |
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
+
"task_specific_params": {
|
27 |
+
"summarization": {
|
28 |
+
"early_stopping": true,
|
29 |
+
"length_penalty": 2.0,
|
30 |
+
"max_length": 200,
|
31 |
+
"min_length": 30,
|
32 |
+
"no_repeat_ngram_size": 3,
|
33 |
+
"num_beams": 4,
|
34 |
+
"prefix": "summarize: "
|
35 |
+
},
|
36 |
+
"translation_en_to_de": {
|
37 |
+
"early_stopping": true,
|
38 |
+
"max_length": 300,
|
39 |
+
"num_beams": 4,
|
40 |
+
"prefix": "translate English to German: "
|
41 |
+
},
|
42 |
+
"translation_en_to_fr": {
|
43 |
+
"early_stopping": true,
|
44 |
+
"max_length": 300,
|
45 |
+
"num_beams": 4,
|
46 |
+
"prefix": "translate English to French: "
|
47 |
+
},
|
48 |
+
"translation_en_to_ro": {
|
49 |
+
"early_stopping": true,
|
50 |
+
"max_length": 300,
|
51 |
+
"num_beams": 4,
|
52 |
+
"prefix": "translate English to Romanian: "
|
53 |
+
}
|
54 |
+
},
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.21.3",
|
57 |
"use_cache": true,
|
58 |
+
"vocab_size": 36096
|
59 |
}
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cce6e8cccabe0a60e8334538f83332f824c17768cbdd9789b232839944bf7a7
|
3 |
+
size 903815044
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e666460219d3495e6437ac09061425ccf896532c92ec00cd3e6130cc94f3f44
|
3 |
+
size 903886847
|
special_tokens_map.json
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>"
|
99 |
+
],
|
100 |
+
"eos_token": "</s>",
|
101 |
+
"pad_token": "<pad>",
|
102 |
+
"unk_token": "<unk>"
|
103 |
+
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:751a7fba06a6b5a482334c5845dee17d1da967b169decccc8047aac74e6af581
|
3 |
+
size 904334744
|
tokenizer.json
CHANGED
@@ -2,935 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
-
"added_tokens": [
|
6 |
-
{
|
7 |
-
"id": 0,
|
8 |
-
"content": "<pad>",
|
9 |
-
"single_word": false,
|
10 |
-
"lstrip": false,
|
11 |
-
"rstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"special": true
|
14 |
-
},
|
15 |
-
{
|
16 |
-
"id": 1,
|
17 |
-
"content": "</s>",
|
18 |
-
"single_word": false,
|
19 |
-
"lstrip": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"normalized": false,
|
22 |
-
"special": true
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"id": 2,
|
26 |
-
"content": "<unk>",
|
27 |
-
"single_word": false,
|
28 |
-
"lstrip": false,
|
29 |
-
"rstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 36000,
|
35 |
-
"content": "<extra_id_99>",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"special": true
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 36001,
|
44 |
-
"content": "<extra_id_98>",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"id": 36002,
|
53 |
-
"content": "<extra_id_97>",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"id": 36003,
|
62 |
-
"content": "<extra_id_96>",
|
63 |
-
"single_word": false,
|
64 |
-
"lstrip": false,
|
65 |
-
"rstrip": false,
|
66 |
-
"normalized": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
{
|
70 |
-
"id": 36004,
|
71 |
-
"content": "<extra_id_95>",
|
72 |
-
"single_word": false,
|
73 |
-
"lstrip": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"normalized": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
{
|
79 |
-
"id": 36005,
|
80 |
-
"content": "<extra_id_94>",
|
81 |
-
"single_word": false,
|
82 |
-
"lstrip": false,
|
83 |
-
"rstrip": false,
|
84 |
-
"normalized": false,
|
85 |
-
"special": true
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"id": 36006,
|
89 |
-
"content": "<extra_id_93>",
|
90 |
-
"single_word": false,
|
91 |
-
"lstrip": false,
|
92 |
-
"rstrip": false,
|
93 |
-
"normalized": false,
|
94 |
-
"special": true
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"id": 36007,
|
98 |
-
"content": "<extra_id_92>",
|
99 |
-
"single_word": false,
|
100 |
-
"lstrip": false,
|
101 |
-
"rstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"special": true
|
104 |
-
},
|
105 |
-
{
|
106 |
-
"id": 36008,
|
107 |
-
"content": "<extra_id_91>",
|
108 |
-
"single_word": false,
|
109 |
-
"lstrip": false,
|
110 |
-
"rstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"special": true
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"id": 36009,
|
116 |
-
"content": "<extra_id_90>",
|
117 |
-
"single_word": false,
|
118 |
-
"lstrip": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"normalized": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"id": 36010,
|
125 |
-
"content": "<extra_id_89>",
|
126 |
-
"single_word": false,
|
127 |
-
"lstrip": false,
|
128 |
-
"rstrip": false,
|
129 |
-
"normalized": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"id": 36011,
|
134 |
-
"content": "<extra_id_88>",
|
135 |
-
"single_word": false,
|
136 |
-
"lstrip": false,
|
137 |
-
"rstrip": false,
|
138 |
-
"normalized": false,
|
139 |
-
"special": true
|
140 |
-
},
|
141 |
-
{
|
142 |
-
"id": 36012,
|
143 |
-
"content": "<extra_id_87>",
|
144 |
-
"single_word": false,
|
145 |
-
"lstrip": false,
|
146 |
-
"rstrip": false,
|
147 |
-
"normalized": false,
|
148 |
-
"special": true
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"id": 36013,
|
152 |
-
"content": "<extra_id_86>",
|
153 |
-
"single_word": false,
|
154 |
-
"lstrip": false,
|
155 |
-
"rstrip": false,
|
156 |
-
"normalized": false,
|
157 |
-
"special": true
|
158 |
-
},
|
159 |
-
{
|
160 |
-
"id": 36014,
|
161 |
-
"content": "<extra_id_85>",
|
162 |
-
"single_word": false,
|
163 |
-
"lstrip": false,
|
164 |
-
"rstrip": false,
|
165 |
-
"normalized": false,
|
166 |
-
"special": true
|
167 |
-
},
|
168 |
-
{
|
169 |
-
"id": 36015,
|
170 |
-
"content": "<extra_id_84>",
|
171 |
-
"single_word": false,
|
172 |
-
"lstrip": false,
|
173 |
-
"rstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"special": true
|
176 |
-
},
|
177 |
-
{
|
178 |
-
"id": 36016,
|
179 |
-
"content": "<extra_id_83>",
|
180 |
-
"single_word": false,
|
181 |
-
"lstrip": false,
|
182 |
-
"rstrip": false,
|
183 |
-
"normalized": false,
|
184 |
-
"special": true
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"id": 36017,
|
188 |
-
"content": "<extra_id_82>",
|
189 |
-
"single_word": false,
|
190 |
-
"lstrip": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"normalized": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
{
|
196 |
-
"id": 36018,
|
197 |
-
"content": "<extra_id_81>",
|
198 |
-
"single_word": false,
|
199 |
-
"lstrip": false,
|
200 |
-
"rstrip": false,
|
201 |
-
"normalized": false,
|
202 |
-
"special": true
|
203 |
-
},
|
204 |
-
{
|
205 |
-
"id": 36019,
|
206 |
-
"content": "<extra_id_80>",
|
207 |
-
"single_word": false,
|
208 |
-
"lstrip": false,
|
209 |
-
"rstrip": false,
|
210 |
-
"normalized": false,
|
211 |
-
"special": true
|
212 |
-
},
|
213 |
-
{
|
214 |
-
"id": 36020,
|
215 |
-
"content": "<extra_id_79>",
|
216 |
-
"single_word": false,
|
217 |
-
"lstrip": false,
|
218 |
-
"rstrip": false,
|
219 |
-
"normalized": false,
|
220 |
-
"special": true
|
221 |
-
},
|
222 |
-
{
|
223 |
-
"id": 36021,
|
224 |
-
"content": "<extra_id_78>",
|
225 |
-
"single_word": false,
|
226 |
-
"lstrip": false,
|
227 |
-
"rstrip": false,
|
228 |
-
"normalized": false,
|
229 |
-
"special": true
|
230 |
-
},
|
231 |
-
{
|
232 |
-
"id": 36022,
|
233 |
-
"content": "<extra_id_77>",
|
234 |
-
"single_word": false,
|
235 |
-
"lstrip": false,
|
236 |
-
"rstrip": false,
|
237 |
-
"normalized": false,
|
238 |
-
"special": true
|
239 |
-
},
|
240 |
-
{
|
241 |
-
"id": 36023,
|
242 |
-
"content": "<extra_id_76>",
|
243 |
-
"single_word": false,
|
244 |
-
"lstrip": false,
|
245 |
-
"rstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"special": true
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"id": 36024,
|
251 |
-
"content": "<extra_id_75>",
|
252 |
-
"single_word": false,
|
253 |
-
"lstrip": false,
|
254 |
-
"rstrip": false,
|
255 |
-
"normalized": false,
|
256 |
-
"special": true
|
257 |
-
},
|
258 |
-
{
|
259 |
-
"id": 36025,
|
260 |
-
"content": "<extra_id_74>",
|
261 |
-
"single_word": false,
|
262 |
-
"lstrip": false,
|
263 |
-
"rstrip": false,
|
264 |
-
"normalized": false,
|
265 |
-
"special": true
|
266 |
-
},
|
267 |
-
{
|
268 |
-
"id": 36026,
|
269 |
-
"content": "<extra_id_73>",
|
270 |
-
"single_word": false,
|
271 |
-
"lstrip": false,
|
272 |
-
"rstrip": false,
|
273 |
-
"normalized": false,
|
274 |
-
"special": true
|
275 |
-
},
|
276 |
-
{
|
277 |
-
"id": 36027,
|
278 |
-
"content": "<extra_id_72>",
|
279 |
-
"single_word": false,
|
280 |
-
"lstrip": false,
|
281 |
-
"rstrip": false,
|
282 |
-
"normalized": false,
|
283 |
-
"special": true
|
284 |
-
},
|
285 |
-
{
|
286 |
-
"id": 36028,
|
287 |
-
"content": "<extra_id_71>",
|
288 |
-
"single_word": false,
|
289 |
-
"lstrip": false,
|
290 |
-
"rstrip": false,
|
291 |
-
"normalized": false,
|
292 |
-
"special": true
|
293 |
-
},
|
294 |
-
{
|
295 |
-
"id": 36029,
|
296 |
-
"content": "<extra_id_70>",
|
297 |
-
"single_word": false,
|
298 |
-
"lstrip": false,
|
299 |
-
"rstrip": false,
|
300 |
-
"normalized": false,
|
301 |
-
"special": true
|
302 |
-
},
|
303 |
-
{
|
304 |
-
"id": 36030,
|
305 |
-
"content": "<extra_id_69>",
|
306 |
-
"single_word": false,
|
307 |
-
"lstrip": false,
|
308 |
-
"rstrip": false,
|
309 |
-
"normalized": false,
|
310 |
-
"special": true
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"id": 36031,
|
314 |
-
"content": "<extra_id_68>",
|
315 |
-
"single_word": false,
|
316 |
-
"lstrip": false,
|
317 |
-
"rstrip": false,
|
318 |
-
"normalized": false,
|
319 |
-
"special": true
|
320 |
-
},
|
321 |
-
{
|
322 |
-
"id": 36032,
|
323 |
-
"content": "<extra_id_67>",
|
324 |
-
"single_word": false,
|
325 |
-
"lstrip": false,
|
326 |
-
"rstrip": false,
|
327 |
-
"normalized": false,
|
328 |
-
"special": true
|
329 |
-
},
|
330 |
-
{
|
331 |
-
"id": 36033,
|
332 |
-
"content": "<extra_id_66>",
|
333 |
-
"single_word": false,
|
334 |
-
"lstrip": false,
|
335 |
-
"rstrip": false,
|
336 |
-
"normalized": false,
|
337 |
-
"special": true
|
338 |
-
},
|
339 |
-
{
|
340 |
-
"id": 36034,
|
341 |
-
"content": "<extra_id_65>",
|
342 |
-
"single_word": false,
|
343 |
-
"lstrip": false,
|
344 |
-
"rstrip": false,
|
345 |
-
"normalized": false,
|
346 |
-
"special": true
|
347 |
-
},
|
348 |
-
{
|
349 |
-
"id": 36035,
|
350 |
-
"content": "<extra_id_64>",
|
351 |
-
"single_word": false,
|
352 |
-
"lstrip": false,
|
353 |
-
"rstrip": false,
|
354 |
-
"normalized": false,
|
355 |
-
"special": true
|
356 |
-
},
|
357 |
-
{
|
358 |
-
"id": 36036,
|
359 |
-
"content": "<extra_id_63>",
|
360 |
-
"single_word": false,
|
361 |
-
"lstrip": false,
|
362 |
-
"rstrip": false,
|
363 |
-
"normalized": false,
|
364 |
-
"special": true
|
365 |
-
},
|
366 |
-
{
|
367 |
-
"id": 36037,
|
368 |
-
"content": "<extra_id_62>",
|
369 |
-
"single_word": false,
|
370 |
-
"lstrip": false,
|
371 |
-
"rstrip": false,
|
372 |
-
"normalized": false,
|
373 |
-
"special": true
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"id": 36038,
|
377 |
-
"content": "<extra_id_61>",
|
378 |
-
"single_word": false,
|
379 |
-
"lstrip": false,
|
380 |
-
"rstrip": false,
|
381 |
-
"normalized": false,
|
382 |
-
"special": true
|
383 |
-
},
|
384 |
-
{
|
385 |
-
"id": 36039,
|
386 |
-
"content": "<extra_id_60>",
|
387 |
-
"single_word": false,
|
388 |
-
"lstrip": false,
|
389 |
-
"rstrip": false,
|
390 |
-
"normalized": false,
|
391 |
-
"special": true
|
392 |
-
},
|
393 |
-
{
|
394 |
-
"id": 36040,
|
395 |
-
"content": "<extra_id_59>",
|
396 |
-
"single_word": false,
|
397 |
-
"lstrip": false,
|
398 |
-
"rstrip": false,
|
399 |
-
"normalized": false,
|
400 |
-
"special": true
|
401 |
-
},
|
402 |
-
{
|
403 |
-
"id": 36041,
|
404 |
-
"content": "<extra_id_58>",
|
405 |
-
"single_word": false,
|
406 |
-
"lstrip": false,
|
407 |
-
"rstrip": false,
|
408 |
-
"normalized": false,
|
409 |
-
"special": true
|
410 |
-
},
|
411 |
-
{
|
412 |
-
"id": 36042,
|
413 |
-
"content": "<extra_id_57>",
|
414 |
-
"single_word": false,
|
415 |
-
"lstrip": false,
|
416 |
-
"rstrip": false,
|
417 |
-
"normalized": false,
|
418 |
-
"special": true
|
419 |
-
},
|
420 |
-
{
|
421 |
-
"id": 36043,
|
422 |
-
"content": "<extra_id_56>",
|
423 |
-
"single_word": false,
|
424 |
-
"lstrip": false,
|
425 |
-
"rstrip": false,
|
426 |
-
"normalized": false,
|
427 |
-
"special": true
|
428 |
-
},
|
429 |
-
{
|
430 |
-
"id": 36044,
|
431 |
-
"content": "<extra_id_55>",
|
432 |
-
"single_word": false,
|
433 |
-
"lstrip": false,
|
434 |
-
"rstrip": false,
|
435 |
-
"normalized": false,
|
436 |
-
"special": true
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"id": 36045,
|
440 |
-
"content": "<extra_id_54>",
|
441 |
-
"single_word": false,
|
442 |
-
"lstrip": false,
|
443 |
-
"rstrip": false,
|
444 |
-
"normalized": false,
|
445 |
-
"special": true
|
446 |
-
},
|
447 |
-
{
|
448 |
-
"id": 36046,
|
449 |
-
"content": "<extra_id_53>",
|
450 |
-
"single_word": false,
|
451 |
-
"lstrip": false,
|
452 |
-
"rstrip": false,
|
453 |
-
"normalized": false,
|
454 |
-
"special": true
|
455 |
-
},
|
456 |
-
{
|
457 |
-
"id": 36047,
|
458 |
-
"content": "<extra_id_52>",
|
459 |
-
"single_word": false,
|
460 |
-
"lstrip": false,
|
461 |
-
"rstrip": false,
|
462 |
-
"normalized": false,
|
463 |
-
"special": true
|
464 |
-
},
|
465 |
-
{
|
466 |
-
"id": 36048,
|
467 |
-
"content": "<extra_id_51>",
|
468 |
-
"single_word": false,
|
469 |
-
"lstrip": false,
|
470 |
-
"rstrip": false,
|
471 |
-
"normalized": false,
|
472 |
-
"special": true
|
473 |
-
},
|
474 |
-
{
|
475 |
-
"id": 36049,
|
476 |
-
"content": "<extra_id_50>",
|
477 |
-
"single_word": false,
|
478 |
-
"lstrip": false,
|
479 |
-
"rstrip": false,
|
480 |
-
"normalized": false,
|
481 |
-
"special": true
|
482 |
-
},
|
483 |
-
{
|
484 |
-
"id": 36050,
|
485 |
-
"content": "<extra_id_49>",
|
486 |
-
"single_word": false,
|
487 |
-
"lstrip": false,
|
488 |
-
"rstrip": false,
|
489 |
-
"normalized": false,
|
490 |
-
"special": true
|
491 |
-
},
|
492 |
-
{
|
493 |
-
"id": 36051,
|
494 |
-
"content": "<extra_id_48>",
|
495 |
-
"single_word": false,
|
496 |
-
"lstrip": false,
|
497 |
-
"rstrip": false,
|
498 |
-
"normalized": false,
|
499 |
-
"special": true
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"id": 36052,
|
503 |
-
"content": "<extra_id_47>",
|
504 |
-
"single_word": false,
|
505 |
-
"lstrip": false,
|
506 |
-
"rstrip": false,
|
507 |
-
"normalized": false,
|
508 |
-
"special": true
|
509 |
-
},
|
510 |
-
{
|
511 |
-
"id": 36053,
|
512 |
-
"content": "<extra_id_46>",
|
513 |
-
"single_word": false,
|
514 |
-
"lstrip": false,
|
515 |
-
"rstrip": false,
|
516 |
-
"normalized": false,
|
517 |
-
"special": true
|
518 |
-
},
|
519 |
-
{
|
520 |
-
"id": 36054,
|
521 |
-
"content": "<extra_id_45>",
|
522 |
-
"single_word": false,
|
523 |
-
"lstrip": false,
|
524 |
-
"rstrip": false,
|
525 |
-
"normalized": false,
|
526 |
-
"special": true
|
527 |
-
},
|
528 |
-
{
|
529 |
-
"id": 36055,
|
530 |
-
"content": "<extra_id_44>",
|
531 |
-
"single_word": false,
|
532 |
-
"lstrip": false,
|
533 |
-
"rstrip": false,
|
534 |
-
"normalized": false,
|
535 |
-
"special": true
|
536 |
-
},
|
537 |
-
{
|
538 |
-
"id": 36056,
|
539 |
-
"content": "<extra_id_43>",
|
540 |
-
"single_word": false,
|
541 |
-
"lstrip": false,
|
542 |
-
"rstrip": false,
|
543 |
-
"normalized": false,
|
544 |
-
"special": true
|
545 |
-
},
|
546 |
-
{
|
547 |
-
"id": 36057,
|
548 |
-
"content": "<extra_id_42>",
|
549 |
-
"single_word": false,
|
550 |
-
"lstrip": false,
|
551 |
-
"rstrip": false,
|
552 |
-
"normalized": false,
|
553 |
-
"special": true
|
554 |
-
},
|
555 |
-
{
|
556 |
-
"id": 36058,
|
557 |
-
"content": "<extra_id_41>",
|
558 |
-
"single_word": false,
|
559 |
-
"lstrip": false,
|
560 |
-
"rstrip": false,
|
561 |
-
"normalized": false,
|
562 |
-
"special": true
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"id": 36059,
|
566 |
-
"content": "<extra_id_40>",
|
567 |
-
"single_word": false,
|
568 |
-
"lstrip": false,
|
569 |
-
"rstrip": false,
|
570 |
-
"normalized": false,
|
571 |
-
"special": true
|
572 |
-
},
|
573 |
-
{
|
574 |
-
"id": 36060,
|
575 |
-
"content": "<extra_id_39>",
|
576 |
-
"single_word": false,
|
577 |
-
"lstrip": false,
|
578 |
-
"rstrip": false,
|
579 |
-
"normalized": false,
|
580 |
-
"special": true
|
581 |
-
},
|
582 |
-
{
|
583 |
-
"id": 36061,
|
584 |
-
"content": "<extra_id_38>",
|
585 |
-
"single_word": false,
|
586 |
-
"lstrip": false,
|
587 |
-
"rstrip": false,
|
588 |
-
"normalized": false,
|
589 |
-
"special": true
|
590 |
-
},
|
591 |
-
{
|
592 |
-
"id": 36062,
|
593 |
-
"content": "<extra_id_37>",
|
594 |
-
"single_word": false,
|
595 |
-
"lstrip": false,
|
596 |
-
"rstrip": false,
|
597 |
-
"normalized": false,
|
598 |
-
"special": true
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"id": 36063,
|
602 |
-
"content": "<extra_id_36>",
|
603 |
-
"single_word": false,
|
604 |
-
"lstrip": false,
|
605 |
-
"rstrip": false,
|
606 |
-
"normalized": false,
|
607 |
-
"special": true
|
608 |
-
},
|
609 |
-
{
|
610 |
-
"id": 36064,
|
611 |
-
"content": "<extra_id_35>",
|
612 |
-
"single_word": false,
|
613 |
-
"lstrip": false,
|
614 |
-
"rstrip": false,
|
615 |
-
"normalized": false,
|
616 |
-
"special": true
|
617 |
-
},
|
618 |
-
{
|
619 |
-
"id": 36065,
|
620 |
-
"content": "<extra_id_34>",
|
621 |
-
"single_word": false,
|
622 |
-
"lstrip": false,
|
623 |
-
"rstrip": false,
|
624 |
-
"normalized": false,
|
625 |
-
"special": true
|
626 |
-
},
|
627 |
-
{
|
628 |
-
"id": 36066,
|
629 |
-
"content": "<extra_id_33>",
|
630 |
-
"single_word": false,
|
631 |
-
"lstrip": false,
|
632 |
-
"rstrip": false,
|
633 |
-
"normalized": false,
|
634 |
-
"special": true
|
635 |
-
},
|
636 |
-
{
|
637 |
-
"id": 36067,
|
638 |
-
"content": "<extra_id_32>",
|
639 |
-
"single_word": false,
|
640 |
-
"lstrip": false,
|
641 |
-
"rstrip": false,
|
642 |
-
"normalized": false,
|
643 |
-
"special": true
|
644 |
-
},
|
645 |
-
{
|
646 |
-
"id": 36068,
|
647 |
-
"content": "<extra_id_31>",
|
648 |
-
"single_word": false,
|
649 |
-
"lstrip": false,
|
650 |
-
"rstrip": false,
|
651 |
-
"normalized": false,
|
652 |
-
"special": true
|
653 |
-
},
|
654 |
-
{
|
655 |
-
"id": 36069,
|
656 |
-
"content": "<extra_id_30>",
|
657 |
-
"single_word": false,
|
658 |
-
"lstrip": false,
|
659 |
-
"rstrip": false,
|
660 |
-
"normalized": false,
|
661 |
-
"special": true
|
662 |
-
},
|
663 |
-
{
|
664 |
-
"id": 36070,
|
665 |
-
"content": "<extra_id_29>",
|
666 |
-
"single_word": false,
|
667 |
-
"lstrip": false,
|
668 |
-
"rstrip": false,
|
669 |
-
"normalized": false,
|
670 |
-
"special": true
|
671 |
-
},
|
672 |
-
{
|
673 |
-
"id": 36071,
|
674 |
-
"content": "<extra_id_28>",
|
675 |
-
"single_word": false,
|
676 |
-
"lstrip": false,
|
677 |
-
"rstrip": false,
|
678 |
-
"normalized": false,
|
679 |
-
"special": true
|
680 |
-
},
|
681 |
-
{
|
682 |
-
"id": 36072,
|
683 |
-
"content": "<extra_id_27>",
|
684 |
-
"single_word": false,
|
685 |
-
"lstrip": false,
|
686 |
-
"rstrip": false,
|
687 |
-
"normalized": false,
|
688 |
-
"special": true
|
689 |
-
},
|
690 |
-
{
|
691 |
-
"id": 36073,
|
692 |
-
"content": "<extra_id_26>",
|
693 |
-
"single_word": false,
|
694 |
-
"lstrip": false,
|
695 |
-
"rstrip": false,
|
696 |
-
"normalized": false,
|
697 |
-
"special": true
|
698 |
-
},
|
699 |
-
{
|
700 |
-
"id": 36074,
|
701 |
-
"content": "<extra_id_25>",
|
702 |
-
"single_word": false,
|
703 |
-
"lstrip": false,
|
704 |
-
"rstrip": false,
|
705 |
-
"normalized": false,
|
706 |
-
"special": true
|
707 |
-
},
|
708 |
-
{
|
709 |
-
"id": 36075,
|
710 |
-
"content": "<extra_id_24>",
|
711 |
-
"single_word": false,
|
712 |
-
"lstrip": false,
|
713 |
-
"rstrip": false,
|
714 |
-
"normalized": false,
|
715 |
-
"special": true
|
716 |
-
},
|
717 |
-
{
|
718 |
-
"id": 36076,
|
719 |
-
"content": "<extra_id_23>",
|
720 |
-
"single_word": false,
|
721 |
-
"lstrip": false,
|
722 |
-
"rstrip": false,
|
723 |
-
"normalized": false,
|
724 |
-
"special": true
|
725 |
-
},
|
726 |
-
{
|
727 |
-
"id": 36077,
|
728 |
-
"content": "<extra_id_22>",
|
729 |
-
"single_word": false,
|
730 |
-
"lstrip": false,
|
731 |
-
"rstrip": false,
|
732 |
-
"normalized": false,
|
733 |
-
"special": true
|
734 |
-
},
|
735 |
-
{
|
736 |
-
"id": 36078,
|
737 |
-
"content": "<extra_id_21>",
|
738 |
-
"single_word": false,
|
739 |
-
"lstrip": false,
|
740 |
-
"rstrip": false,
|
741 |
-
"normalized": false,
|
742 |
-
"special": true
|
743 |
-
},
|
744 |
-
{
|
745 |
-
"id": 36079,
|
746 |
-
"content": "<extra_id_20>",
|
747 |
-
"single_word": false,
|
748 |
-
"lstrip": false,
|
749 |
-
"rstrip": false,
|
750 |
-
"normalized": false,
|
751 |
-
"special": true
|
752 |
-
},
|
753 |
-
{
|
754 |
-
"id": 36080,
|
755 |
-
"content": "<extra_id_19>",
|
756 |
-
"single_word": false,
|
757 |
-
"lstrip": false,
|
758 |
-
"rstrip": false,
|
759 |
-
"normalized": false,
|
760 |
-
"special": true
|
761 |
-
},
|
762 |
-
{
|
763 |
-
"id": 36081,
|
764 |
-
"content": "<extra_id_18>",
|
765 |
-
"single_word": false,
|
766 |
-
"lstrip": false,
|
767 |
-
"rstrip": false,
|
768 |
-
"normalized": false,
|
769 |
-
"special": true
|
770 |
-
},
|
771 |
-
{
|
772 |
-
"id": 36082,
|
773 |
-
"content": "<extra_id_17>",
|
774 |
-
"single_word": false,
|
775 |
-
"lstrip": false,
|
776 |
-
"rstrip": false,
|
777 |
-
"normalized": false,
|
778 |
-
"special": true
|
779 |
-
},
|
780 |
-
{
|
781 |
-
"id": 36083,
|
782 |
-
"content": "<extra_id_16>",
|
783 |
-
"single_word": false,
|
784 |
-
"lstrip": false,
|
785 |
-
"rstrip": false,
|
786 |
-
"normalized": false,
|
787 |
-
"special": true
|
788 |
-
},
|
789 |
-
{
|
790 |
-
"id": 36084,
|
791 |
-
"content": "<extra_id_15>",
|
792 |
-
"single_word": false,
|
793 |
-
"lstrip": false,
|
794 |
-
"rstrip": false,
|
795 |
-
"normalized": false,
|
796 |
-
"special": true
|
797 |
-
},
|
798 |
-
{
|
799 |
-
"id": 36085,
|
800 |
-
"content": "<extra_id_14>",
|
801 |
-
"single_word": false,
|
802 |
-
"lstrip": false,
|
803 |
-
"rstrip": false,
|
804 |
-
"normalized": false,
|
805 |
-
"special": true
|
806 |
-
},
|
807 |
-
{
|
808 |
-
"id": 36086,
|
809 |
-
"content": "<extra_id_13>",
|
810 |
-
"single_word": false,
|
811 |
-
"lstrip": false,
|
812 |
-
"rstrip": false,
|
813 |
-
"normalized": false,
|
814 |
-
"special": true
|
815 |
-
},
|
816 |
-
{
|
817 |
-
"id": 36087,
|
818 |
-
"content": "<extra_id_12>",
|
819 |
-
"single_word": false,
|
820 |
-
"lstrip": false,
|
821 |
-
"rstrip": false,
|
822 |
-
"normalized": false,
|
823 |
-
"special": true
|
824 |
-
},
|
825 |
-
{
|
826 |
-
"id": 36088,
|
827 |
-
"content": "<extra_id_11>",
|
828 |
-
"single_word": false,
|
829 |
-
"lstrip": false,
|
830 |
-
"rstrip": false,
|
831 |
-
"normalized": false,
|
832 |
-
"special": true
|
833 |
-
},
|
834 |
-
{
|
835 |
-
"id": 36089,
|
836 |
-
"content": "<extra_id_10>",
|
837 |
-
"single_word": false,
|
838 |
-
"lstrip": false,
|
839 |
-
"rstrip": false,
|
840 |
-
"normalized": false,
|
841 |
-
"special": true
|
842 |
-
},
|
843 |
-
{
|
844 |
-
"id": 36090,
|
845 |
-
"content": "<extra_id_9>",
|
846 |
-
"single_word": false,
|
847 |
-
"lstrip": false,
|
848 |
-
"rstrip": false,
|
849 |
-
"normalized": false,
|
850 |
-
"special": true
|
851 |
-
},
|
852 |
-
{
|
853 |
-
"id": 36091,
|
854 |
-
"content": "<extra_id_8>",
|
855 |
-
"single_word": false,
|
856 |
-
"lstrip": false,
|
857 |
-
"rstrip": false,
|
858 |
-
"normalized": false,
|
859 |
-
"special": true
|
860 |
-
},
|
861 |
-
{
|
862 |
-
"id": 36092,
|
863 |
-
"content": "<extra_id_7>",
|
864 |
-
"single_word": false,
|
865 |
-
"lstrip": false,
|
866 |
-
"rstrip": false,
|
867 |
-
"normalized": false,
|
868 |
-
"special": true
|
869 |
-
},
|
870 |
-
{
|
871 |
-
"id": 36093,
|
872 |
-
"content": "<extra_id_6>",
|
873 |
-
"single_word": false,
|
874 |
-
"lstrip": false,
|
875 |
-
"rstrip": false,
|
876 |
-
"normalized": false,
|
877 |
-
"special": true
|
878 |
-
},
|
879 |
-
{
|
880 |
-
"id": 36094,
|
881 |
-
"content": "<extra_id_5>",
|
882 |
-
"single_word": false,
|
883 |
-
"lstrip": false,
|
884 |
-
"rstrip": false,
|
885 |
-
"normalized": false,
|
886 |
-
"special": true
|
887 |
-
},
|
888 |
-
{
|
889 |
-
"id": 36095,
|
890 |
-
"content": "<extra_id_4>",
|
891 |
-
"single_word": false,
|
892 |
-
"lstrip": false,
|
893 |
-
"rstrip": false,
|
894 |
-
"normalized": false,
|
895 |
-
"special": true
|
896 |
-
},
|
897 |
-
{
|
898 |
-
"id": 36096,
|
899 |
-
"content": "<extra_id_3>",
|
900 |
-
"single_word": false,
|
901 |
-
"lstrip": false,
|
902 |
-
"rstrip": false,
|
903 |
-
"normalized": false,
|
904 |
-
"special": true
|
905 |
-
},
|
906 |
-
{
|
907 |
-
"id": 36097,
|
908 |
-
"content": "<extra_id_2>",
|
909 |
-
"single_word": false,
|
910 |
-
"lstrip": false,
|
911 |
-
"rstrip": false,
|
912 |
-
"normalized": false,
|
913 |
-
"special": true
|
914 |
-
},
|
915 |
-
{
|
916 |
-
"id": 36098,
|
917 |
-
"content": "<extra_id_1>",
|
918 |
-
"single_word": false,
|
919 |
-
"lstrip": false,
|
920 |
-
"rstrip": false,
|
921 |
-
"normalized": false,
|
922 |
-
"special": true
|
923 |
-
},
|
924 |
-
{
|
925 |
-
"id": 36099,
|
926 |
-
"content": "<extra_id_0>",
|
927 |
-
"single_word": false,
|
928 |
-
"lstrip": false,
|
929 |
-
"rstrip": false,
|
930 |
-
"normalized": false,
|
931 |
-
"special": true
|
932 |
-
}
|
933 |
-
],
|
934 |
"normalizer": {
|
935 |
"type": "Sequence",
|
936 |
"normalizers": [
|
@@ -37019,106 +36091,102 @@
|
|
37019 |
"_": 35997,
|
37020 |
"+": 35998,
|
37021 |
"*": 35999,
|
37022 |
-
"<
|
37023 |
-
"<
|
37024 |
-
"<
|
37025 |
-
"<
|
37026 |
-
"<
|
37027 |
-
"<
|
37028 |
-
"<
|
37029 |
-
"<
|
37030 |
-
"<
|
37031 |
-
"<
|
37032 |
-
"<
|
37033 |
-
"<
|
37034 |
-
"<
|
37035 |
-
"<
|
37036 |
-
"<
|
37037 |
-
"<
|
37038 |
-
"<
|
37039 |
-
"<
|
37040 |
-
"<
|
37041 |
-
"<
|
37042 |
-
"<
|
37043 |
-
"<
|
37044 |
-
"<
|
37045 |
-
"<
|
37046 |
-
"<
|
37047 |
-
"<
|
37048 |
-
"<
|
37049 |
-
"<
|
37050 |
-
"<
|
37051 |
-
"<
|
37052 |
-
"<
|
37053 |
-
"<
|
37054 |
-
"<
|
37055 |
-
"<
|
37056 |
-
"<
|
37057 |
-
"<
|
37058 |
-
"<
|
37059 |
-
"<
|
37060 |
-
"<
|
37061 |
-
"<
|
37062 |
-
"<
|
37063 |
-
"<
|
37064 |
-
"<
|
37065 |
-
"<
|
37066 |
-
"<
|
37067 |
-
"<
|
37068 |
-
"<
|
37069 |
-
"<
|
37070 |
-
"<
|
37071 |
-
"<
|
37072 |
-
"<
|
37073 |
-
"<
|
37074 |
-
"<
|
37075 |
-
"<
|
37076 |
-
"<
|
37077 |
-
"<
|
37078 |
-
"<
|
37079 |
-
"<
|
37080 |
-
"<
|
37081 |
-
"<
|
37082 |
-
"<
|
37083 |
-
"<
|
37084 |
-
"<
|
37085 |
-
"<
|
37086 |
-
"<
|
37087 |
-
"<
|
37088 |
-
"<
|
37089 |
-
"<
|
37090 |
-
"<
|
37091 |
-
"<
|
37092 |
-
"<
|
37093 |
-
"<
|
37094 |
-
"<
|
37095 |
-
"<
|
37096 |
-
"<
|
37097 |
-
"<
|
37098 |
-
"<
|
37099 |
-
"<
|
37100 |
-
"<
|
37101 |
-
"<
|
37102 |
-
"<
|
37103 |
-
"<
|
37104 |
-
"<
|
37105 |
-
"<
|
37106 |
-
"<
|
37107 |
-
"<
|
37108 |
-
"<
|
37109 |
-
"<
|
37110 |
-
"<
|
37111 |
-
"<
|
37112 |
-
"<
|
37113 |
-
"<
|
37114 |
-
"<
|
37115 |
-
"<
|
37116 |
-
"<
|
37117 |
-
"<
|
37118 |
-
"<extra_id_3>": 36096,
|
37119 |
-
"<extra_id_2>": 36097,
|
37120 |
-
"<extra_id_1>": 36098,
|
37121 |
-
"<extra_id_0>": 36099
|
37122 |
},
|
37123 |
"merges": [
|
37124 |
"n g",
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
+
"added_tokens": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"normalizer": {
|
7 |
"type": "Sequence",
|
8 |
"normalizers": [
|
|
|
36091 |
"_": 35997,
|
36092 |
"+": 35998,
|
36093 |
"*": 35999,
|
36094 |
+
"<extra_id_95>": 36000,
|
36095 |
+
"<extra_id_94>": 36001,
|
36096 |
+
"<extra_id_93>": 36002,
|
36097 |
+
"<extra_id_92>": 36003,
|
36098 |
+
"<extra_id_91>": 36004,
|
36099 |
+
"<extra_id_90>": 36005,
|
36100 |
+
"<extra_id_89>": 36006,
|
36101 |
+
"<extra_id_88>": 36007,
|
36102 |
+
"<extra_id_87>": 36008,
|
36103 |
+
"<extra_id_86>": 36009,
|
36104 |
+
"<extra_id_85>": 36010,
|
36105 |
+
"<extra_id_84>": 36011,
|
36106 |
+
"<extra_id_83>": 36012,
|
36107 |
+
"<extra_id_82>": 36013,
|
36108 |
+
"<extra_id_81>": 36014,
|
36109 |
+
"<extra_id_80>": 36015,
|
36110 |
+
"<extra_id_79>": 36016,
|
36111 |
+
"<extra_id_78>": 36017,
|
36112 |
+
"<extra_id_77>": 36018,
|
36113 |
+
"<extra_id_76>": 36019,
|
36114 |
+
"<extra_id_75>": 36020,
|
36115 |
+
"<extra_id_74>": 36021,
|
36116 |
+
"<extra_id_73>": 36022,
|
36117 |
+
"<extra_id_72>": 36023,
|
36118 |
+
"<extra_id_71>": 36024,
|
36119 |
+
"<extra_id_70>": 36025,
|
36120 |
+
"<extra_id_69>": 36026,
|
36121 |
+
"<extra_id_68>": 36027,
|
36122 |
+
"<extra_id_67>": 36028,
|
36123 |
+
"<extra_id_66>": 36029,
|
36124 |
+
"<extra_id_65>": 36030,
|
36125 |
+
"<extra_id_64>": 36031,
|
36126 |
+
"<extra_id_63>": 36032,
|
36127 |
+
"<extra_id_62>": 36033,
|
36128 |
+
"<extra_id_61>": 36034,
|
36129 |
+
"<extra_id_60>": 36035,
|
36130 |
+
"<extra_id_59>": 36036,
|
36131 |
+
"<extra_id_58>": 36037,
|
36132 |
+
"<extra_id_57>": 36038,
|
36133 |
+
"<extra_id_56>": 36039,
|
36134 |
+
"<extra_id_55>": 36040,
|
36135 |
+
"<extra_id_54>": 36041,
|
36136 |
+
"<extra_id_53>": 36042,
|
36137 |
+
"<extra_id_52>": 36043,
|
36138 |
+
"<extra_id_51>": 36044,
|
36139 |
+
"<extra_id_50>": 36045,
|
36140 |
+
"<extra_id_49>": 36046,
|
36141 |
+
"<extra_id_48>": 36047,
|
36142 |
+
"<extra_id_47>": 36048,
|
36143 |
+
"<extra_id_46>": 36049,
|
36144 |
+
"<extra_id_45>": 36050,
|
36145 |
+
"<extra_id_44>": 36051,
|
36146 |
+
"<extra_id_43>": 36052,
|
36147 |
+
"<extra_id_42>": 36053,
|
36148 |
+
"<extra_id_41>": 36054,
|
36149 |
+
"<extra_id_40>": 36055,
|
36150 |
+
"<extra_id_39>": 36056,
|
36151 |
+
"<extra_id_38>": 36057,
|
36152 |
+
"<extra_id_37>": 36058,
|
36153 |
+
"<extra_id_36>": 36059,
|
36154 |
+
"<extra_id_35>": 36060,
|
36155 |
+
"<extra_id_34>": 36061,
|
36156 |
+
"<extra_id_33>": 36062,
|
36157 |
+
"<extra_id_32>": 36063,
|
36158 |
+
"<extra_id_31>": 36064,
|
36159 |
+
"<extra_id_30>": 36065,
|
36160 |
+
"<extra_id_29>": 36066,
|
36161 |
+
"<extra_id_28>": 36067,
|
36162 |
+
"<extra_id_27>": 36068,
|
36163 |
+
"<extra_id_26>": 36069,
|
36164 |
+
"<extra_id_25>": 36070,
|
36165 |
+
"<extra_id_24>": 36071,
|
36166 |
+
"<extra_id_23>": 36072,
|
36167 |
+
"<extra_id_22>": 36073,
|
36168 |
+
"<extra_id_21>": 36074,
|
36169 |
+
"<extra_id_20>": 36075,
|
36170 |
+
"<extra_id_19>": 36076,
|
36171 |
+
"<extra_id_18>": 36077,
|
36172 |
+
"<extra_id_17>": 36078,
|
36173 |
+
"<extra_id_16>": 36079,
|
36174 |
+
"<extra_id_15>": 36080,
|
36175 |
+
"<extra_id_14>": 36081,
|
36176 |
+
"<extra_id_13>": 36082,
|
36177 |
+
"<extra_id_12>": 36083,
|
36178 |
+
"<extra_id_11>": 36084,
|
36179 |
+
"<extra_id_10>": 36085,
|
36180 |
+
"<extra_id_9>": 36086,
|
36181 |
+
"<extra_id_8>": 36087,
|
36182 |
+
"<extra_id_7>": 36088,
|
36183 |
+
"<extra_id_6>": 36089,
|
36184 |
+
"<extra_id_5>": 36090,
|
36185 |
+
"<extra_id_4>": 36091,
|
36186 |
+
"<extra_id_3>": 36092,
|
36187 |
+
"<extra_id_2>": 36093,
|
36188 |
+
"<extra_id_1>": 36094,
|
36189 |
+
"<extra_id_0>": 36095
|
|
|
|
|
|
|
|
|
36190 |
},
|
36191 |
"merges": [
|
36192 |
"n g",
|
tokenizer_config.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>"
|
99 |
+
],
|
100 |
+
"eos_token": "</s>",
|
101 |
+
"extra_ids": 96,
|
102 |
+
"pad_token": "<pad>",
|
103 |
+
"sp_model_kwargs": {},
|
104 |
+
"tokenizer_class": "T5Tokenizer",
|
105 |
+
"unk_token": "<unk>"
|
106 |
+
}
|