crossroderick commited on
Commit
02b7cd5
·
1 Parent(s): 40cabaf

Gradio remake

Browse files
README.md CHANGED
@@ -1,14 +1,12 @@
1
  ---
2
- title: Dalat5
3
- emoji: 💻
4
- colorFrom: blue
5
- colorTo: indigo
6
- sdk: gradio
7
- sdk_version: 5.27.0
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
  short_description: A transformer-based transliterator for the Kazakh language.
12
- ---
13
-
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: DalaT5
3
+ emoji: 🌐
4
+ colorFrom: pink
5
+ colorTo: green
6
+ sdk: streamlit
7
+ sdk_version: 1.44.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
  short_description: A transformer-based transliterator for the Kazakh language.
12
+ ---
 
 
app.py ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ from transformers import pipeline
3
+
4
+
5
+ # Load model once
6
+ model = pipeline("text2text-generation", model = "crossroderick/dalat5")
7
+
8
+
9
+ def transliterate(text: str) -> str:
10
+ """
11
+ Prediction function.
12
+ """
13
+ if text.strip() == "":
14
+ return "Енгізуді күтуде... жоғарыдағы кириллицаның көмегімен қазақ тілінде сөйлем теріңіз / Awaiting input... type a sentence in Kazakh using Cyrillic script above."
15
+
16
+ input_text = f"Cyrillic2Latin: {text.strip()}"
17
+ output = model(input_text, max_length = 128)[0]["generated_text"]
18
+
19
+ return output.strip()
20
+
21
+
22
+ # App description (Markdown style)
23
+ description = """
24
+ # 🇰🇿 DalaT5
25
+
26
+ Қазақша кириллица → латын графикасының генераторы / Kazakh Cyrillic → Latin Script Generator
27
+
28
+ ---
29
+
30
+ **[EN]**
31
+
32
+ DalaT5 is a T5-based model trained to convert natural Kazakh written in **Cyrillic** into fluent **Latin script**, based on the official 2021 alphabet reform of Kazakhstan.
33
+
34
+ This model is offered as a cultural gesture of respect and curiosity. It accepts modern Kazakh as people write it today - and answers in the language of its future.
35
+
36
+ **[KZ]**
37
+
38
+ DalaT5 - **кириллицада** жазылған табиғи қазақ тілін еркін **латын графикасына** ауыстыру үшін дайындалған T5 негізіндегі модель, Қазақстанның 2021 жылғы ресми әліпби реформасына негізделген.
39
+
40
+ Бұл модель құрмет пен қызығушылықтың мәдени қимылы ретінде ұсынылады. Ол қазіргі қазақ тілін бүгінгі адамдар қалай жазады, солай қабылдайды - және оның болашағының тілінде жауап береді.
41
+
42
+ 🧠 [Model link](https://huggingface.co/crossroderick/dalat5)
43
+ 🔤 [Kazakhstan 2021 alphabet reform](https://astanatimes.com/2021/02/kazakhstan-presents-new-latin-alphabet-plans-gradual-transition-through-2031/)
44
+ """
45
+
46
+ # Interface
47
+ demo = gr.Interface(
48
+ fn = transliterate,
49
+ inputs = gr.Textbox(
50
+ label = "Қазақ тілінде теріңіз (кириллица) / Type in Kazakh (Cyrillic script)",
51
+ placeholder = "Мен қазақ тілінде сөйлеймін.",
52
+ lines = 6
53
+ ),
54
+
55
+ outputs = gr.Textbox(
56
+ label = "Латын графикасының шығуы / Latin script output"
57
+ ),
58
+
59
+ title = "🇰🇿 DalaT5 - Kazakh Script Transformer",
60
+ description = description,
61
+ theme = "default",
62
+ allow_flagging = "never"
63
+ )
64
+
65
+ demo.launch()
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "num_decoder_layers": 6,
20
+ "num_heads": 8,
21
+ "num_layers": 6,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.51.2",
27
+ "use_cache": true,
28
+ "vocab_size": 40100
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.51.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301a885d1d6deadcc8cd3f69d48c233773d17dfd7a9248c17b8ac07c0d7ad7bc
3
+ size 258368552
requirements.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ gradio
2
+ transformers
3
+ sentencepiece
4
+ torch
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb4456f78071a8ab6ca5a1698b8a196823b52dea960f8bb0cbcbe082828ead4
3
+ size 1040899
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,949 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "3": {
29
+ "content": "</s>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "40000": {
37
+ "content": "<extra_id_99>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "40001": {
45
+ "content": "<extra_id_98>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "40002": {
53
+ "content": "<extra_id_97>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "40003": {
61
+ "content": "<extra_id_96>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "40004": {
69
+ "content": "<extra_id_95>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "40005": {
77
+ "content": "<extra_id_94>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "40006": {
85
+ "content": "<extra_id_93>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "40007": {
93
+ "content": "<extra_id_92>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "40008": {
101
+ "content": "<extra_id_91>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "40009": {
109
+ "content": "<extra_id_90>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "40010": {
117
+ "content": "<extra_id_89>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "40011": {
125
+ "content": "<extra_id_88>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "40012": {
133
+ "content": "<extra_id_87>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "40013": {
141
+ "content": "<extra_id_86>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "40014": {
149
+ "content": "<extra_id_85>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "40015": {
157
+ "content": "<extra_id_84>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "40016": {
165
+ "content": "<extra_id_83>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "40017": {
173
+ "content": "<extra_id_82>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "40018": {
181
+ "content": "<extra_id_81>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "40019": {
189
+ "content": "<extra_id_80>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "40020": {
197
+ "content": "<extra_id_79>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "40021": {
205
+ "content": "<extra_id_78>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "40022": {
213
+ "content": "<extra_id_77>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "40023": {
221
+ "content": "<extra_id_76>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "40024": {
229
+ "content": "<extra_id_75>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "40025": {
237
+ "content": "<extra_id_74>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "40026": {
245
+ "content": "<extra_id_73>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "40027": {
253
+ "content": "<extra_id_72>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "40028": {
261
+ "content": "<extra_id_71>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "40029": {
269
+ "content": "<extra_id_70>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "40030": {
277
+ "content": "<extra_id_69>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "40031": {
285
+ "content": "<extra_id_68>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "40032": {
293
+ "content": "<extra_id_67>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "40033": {
301
+ "content": "<extra_id_66>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "40034": {
309
+ "content": "<extra_id_65>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "40035": {
317
+ "content": "<extra_id_64>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "40036": {
325
+ "content": "<extra_id_63>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "40037": {
333
+ "content": "<extra_id_62>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "40038": {
341
+ "content": "<extra_id_61>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "40039": {
349
+ "content": "<extra_id_60>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "40040": {
357
+ "content": "<extra_id_59>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "40041": {
365
+ "content": "<extra_id_58>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "40042": {
373
+ "content": "<extra_id_57>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "40043": {
381
+ "content": "<extra_id_56>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "40044": {
389
+ "content": "<extra_id_55>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "40045": {
397
+ "content": "<extra_id_54>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "40046": {
405
+ "content": "<extra_id_53>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "40047": {
413
+ "content": "<extra_id_52>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "40048": {
421
+ "content": "<extra_id_51>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "40049": {
429
+ "content": "<extra_id_50>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "40050": {
437
+ "content": "<extra_id_49>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "40051": {
445
+ "content": "<extra_id_48>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "40052": {
453
+ "content": "<extra_id_47>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "40053": {
461
+ "content": "<extra_id_46>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "40054": {
469
+ "content": "<extra_id_45>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "40055": {
477
+ "content": "<extra_id_44>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "40056": {
485
+ "content": "<extra_id_43>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "40057": {
493
+ "content": "<extra_id_42>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "40058": {
501
+ "content": "<extra_id_41>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "40059": {
509
+ "content": "<extra_id_40>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "40060": {
517
+ "content": "<extra_id_39>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "40061": {
525
+ "content": "<extra_id_38>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "40062": {
533
+ "content": "<extra_id_37>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "40063": {
541
+ "content": "<extra_id_36>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "40064": {
549
+ "content": "<extra_id_35>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "40065": {
557
+ "content": "<extra_id_34>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "40066": {
565
+ "content": "<extra_id_33>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "40067": {
573
+ "content": "<extra_id_32>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "40068": {
581
+ "content": "<extra_id_31>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "40069": {
589
+ "content": "<extra_id_30>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "40070": {
597
+ "content": "<extra_id_29>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "40071": {
605
+ "content": "<extra_id_28>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "40072": {
613
+ "content": "<extra_id_27>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "40073": {
621
+ "content": "<extra_id_26>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "40074": {
629
+ "content": "<extra_id_25>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "40075": {
637
+ "content": "<extra_id_24>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "40076": {
645
+ "content": "<extra_id_23>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "40077": {
653
+ "content": "<extra_id_22>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "40078": {
661
+ "content": "<extra_id_21>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "40079": {
669
+ "content": "<extra_id_20>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "40080": {
677
+ "content": "<extra_id_19>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "40081": {
685
+ "content": "<extra_id_18>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "40082": {
693
+ "content": "<extra_id_17>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "40083": {
701
+ "content": "<extra_id_16>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "40084": {
709
+ "content": "<extra_id_15>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "40085": {
717
+ "content": "<extra_id_14>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "40086": {
725
+ "content": "<extra_id_13>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "40087": {
733
+ "content": "<extra_id_12>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "40088": {
741
+ "content": "<extra_id_11>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "40089": {
749
+ "content": "<extra_id_10>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "40090": {
757
+ "content": "<extra_id_9>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "40091": {
765
+ "content": "<extra_id_8>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "40092": {
773
+ "content": "<extra_id_7>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "40093": {
781
+ "content": "<extra_id_6>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "40094": {
789
+ "content": "<extra_id_5>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "40095": {
797
+ "content": "<extra_id_4>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "40096": {
805
+ "content": "<extra_id_3>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "40097": {
813
+ "content": "<extra_id_2>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "40098": {
821
+ "content": "<extra_id_1>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "40099": {
829
+ "content": "<extra_id_0>",
830
+ "lstrip": true,
831
+ "normalized": false,
832
+ "rstrip": true,
833
+ "single_word": false,
834
+ "special": true
835
+ }
836
+ },
837
+ "additional_special_tokens": [
838
+ "<extra_id_0>",
839
+ "<extra_id_1>",
840
+ "<extra_id_2>",
841
+ "<extra_id_3>",
842
+ "<extra_id_4>",
843
+ "<extra_id_5>",
844
+ "<extra_id_6>",
845
+ "<extra_id_7>",
846
+ "<extra_id_8>",
847
+ "<extra_id_9>",
848
+ "<extra_id_10>",
849
+ "<extra_id_11>",
850
+ "<extra_id_12>",
851
+ "<extra_id_13>",
852
+ "<extra_id_14>",
853
+ "<extra_id_15>",
854
+ "<extra_id_16>",
855
+ "<extra_id_17>",
856
+ "<extra_id_18>",
857
+ "<extra_id_19>",
858
+ "<extra_id_20>",
859
+ "<extra_id_21>",
860
+ "<extra_id_22>",
861
+ "<extra_id_23>",
862
+ "<extra_id_24>",
863
+ "<extra_id_25>",
864
+ "<extra_id_26>",
865
+ "<extra_id_27>",
866
+ "<extra_id_28>",
867
+ "<extra_id_29>",
868
+ "<extra_id_30>",
869
+ "<extra_id_31>",
870
+ "<extra_id_32>",
871
+ "<extra_id_33>",
872
+ "<extra_id_34>",
873
+ "<extra_id_35>",
874
+ "<extra_id_36>",
875
+ "<extra_id_37>",
876
+ "<extra_id_38>",
877
+ "<extra_id_39>",
878
+ "<extra_id_40>",
879
+ "<extra_id_41>",
880
+ "<extra_id_42>",
881
+ "<extra_id_43>",
882
+ "<extra_id_44>",
883
+ "<extra_id_45>",
884
+ "<extra_id_46>",
885
+ "<extra_id_47>",
886
+ "<extra_id_48>",
887
+ "<extra_id_49>",
888
+ "<extra_id_50>",
889
+ "<extra_id_51>",
890
+ "<extra_id_52>",
891
+ "<extra_id_53>",
892
+ "<extra_id_54>",
893
+ "<extra_id_55>",
894
+ "<extra_id_56>",
895
+ "<extra_id_57>",
896
+ "<extra_id_58>",
897
+ "<extra_id_59>",
898
+ "<extra_id_60>",
899
+ "<extra_id_61>",
900
+ "<extra_id_62>",
901
+ "<extra_id_63>",
902
+ "<extra_id_64>",
903
+ "<extra_id_65>",
904
+ "<extra_id_66>",
905
+ "<extra_id_67>",
906
+ "<extra_id_68>",
907
+ "<extra_id_69>",
908
+ "<extra_id_70>",
909
+ "<extra_id_71>",
910
+ "<extra_id_72>",
911
+ "<extra_id_73>",
912
+ "<extra_id_74>",
913
+ "<extra_id_75>",
914
+ "<extra_id_76>",
915
+ "<extra_id_77>",
916
+ "<extra_id_78>",
917
+ "<extra_id_79>",
918
+ "<extra_id_80>",
919
+ "<extra_id_81>",
920
+ "<extra_id_82>",
921
+ "<extra_id_83>",
922
+ "<extra_id_84>",
923
+ "<extra_id_85>",
924
+ "<extra_id_86>",
925
+ "<extra_id_87>",
926
+ "<extra_id_88>",
927
+ "<extra_id_89>",
928
+ "<extra_id_90>",
929
+ "<extra_id_91>",
930
+ "<extra_id_92>",
931
+ "<extra_id_93>",
932
+ "<extra_id_94>",
933
+ "<extra_id_95>",
934
+ "<extra_id_96>",
935
+ "<extra_id_97>",
936
+ "<extra_id_98>",
937
+ "<extra_id_99>"
938
+ ],
939
+ "clean_up_tokenization_spaces": false,
940
+ "eos_token": "</s>",
941
+ "extra_ids": 100,
942
+ "extra_special_tokens": {},
943
+ "legacy": true,
944
+ "model_max_length": 1000000000000000019884624838656,
945
+ "pad_token": "<pad>",
946
+ "sp_model_kwargs": {},
947
+ "tokenizer_class": "T5Tokenizer",
948
+ "unk_token": "<unk>"
949
+ }