dn6 HF Staff commited on
Commit
da13281
·
verified ·
1 Parent(s): 89f8f8b

Upload folder using huggingface_hub

Browse files
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": 10,
3
+ "feature_extractor_type": "ClapFeatureExtractor",
4
+ "feature_size": 64,
5
+ "fft_window_size": 1024,
6
+ "frequency_max": 14000,
7
+ "frequency_min": 50,
8
+ "hop_length": 7900,
9
+ "max_length_s": 10,
10
+ "n_fft": 1024,
11
+ "nb_frequency_bins": 513,
12
+ "nb_max_frames": 1000,
13
+ "nb_max_samples": 480000,
14
+ "padding": "repeatpad",
15
+ "padding_side": "right",
16
+ "padding_value": 0.0,
17
+ "processor_class": "ClapProcessor",
18
+ "return_attention_mask": false,
19
+ "sampling_rate": 48000,
20
+ "top_db": null,
21
+ "truncation": "fusion"
22
+ }
language_model/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2Model"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "max_new_tokens": 8,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 99,
15
+ "n_embd": 16,
16
+ "n_head": 1,
17
+ "n_inner": null,
18
+ "n_layer": 1,
19
+ "n_positions": 99,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.50.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 1000
33
+ }
language_model/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70f1436cba809d275cd90a9d6ad2d7475d5c2504119a31c180c5a55e592ba36
3
+ size 88962
model_index.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AudioLDM2Pipeline",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "ClapFeatureExtractor"
7
+ ],
8
+ "language_model": [
9
+ "transformers",
10
+ "GPT2Model"
11
+ ],
12
+ "projection_model": [
13
+ "audioldm2",
14
+ "AudioLDM2ProjectionModel"
15
+ ],
16
+ "scheduler": [
17
+ "diffusers",
18
+ "DDIMScheduler"
19
+ ],
20
+ "text_encoder": [
21
+ "transformers",
22
+ "ClapModel"
23
+ ],
24
+ "text_encoder_2": [
25
+ "transformers",
26
+ "T5EncoderModel"
27
+ ],
28
+ "tokenizer": [
29
+ "transformers",
30
+ "RobertaTokenizer"
31
+ ],
32
+ "tokenizer_2": [
33
+ "transformers",
34
+ "T5Tokenizer"
35
+ ],
36
+ "unet": [
37
+ "audioldm2",
38
+ "AudioLDM2UNet2DConditionModel"
39
+ ],
40
+ "vae": [
41
+ "diffusers",
42
+ "AutoencoderKL"
43
+ ],
44
+ "vocoder": [
45
+ "transformers",
46
+ "SpeechT5HifiGan"
47
+ ]
48
+ }
projection_model/config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AudioLDM2ProjectionModel",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "langauge_model_dim": 16,
5
+ "max_seq_length": null,
6
+ "text_encoder_1_dim": 32,
7
+ "text_encoder_dim": 16,
8
+ "use_learned_position_embedding": null
9
+ }
projection_model/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42bd0f72fd49ad370f03d4762296a49302f74010f692a1a69e4d3bc0696f1a6
3
+ size 6780
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "steps_offset": 0,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
+ "trained_betas": null
19
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ClapModel"
4
+ ],
5
+ "audio_config": {
6
+ "_attn_implementation_autoset": true,
7
+ "depths": [
8
+ 1,
9
+ 1
10
+ ],
11
+ "hidden_size": 192,
12
+ "intermediate_size": 37,
13
+ "model_type": "clap_audio_model",
14
+ "num_attention_heads": [
15
+ 1,
16
+ 1
17
+ ],
18
+ "num_hidden_layers": 1,
19
+ "num_mel_bins": 8,
20
+ "patch_embed_input_channels": 4,
21
+ "patch_size": 2,
22
+ "patch_stride": 2,
23
+ "projection_dim": 16,
24
+ "spec_size": 8,
25
+ "window_size": 4
26
+ },
27
+ "hidden_size": 8,
28
+ "initializer_factor": 1.0,
29
+ "logit_scale_init_value": 14.285714285714285,
30
+ "model_type": "clap",
31
+ "num_hidden_layers": 3,
32
+ "projection_dim": 16,
33
+ "projection_hidden_act": "relu",
34
+ "text_config": {
35
+ "_attn_implementation_autoset": true,
36
+ "hidden_size": 8,
37
+ "intermediate_size": 37,
38
+ "layer_norm_eps": 1e-05,
39
+ "model_type": "clap_text_model",
40
+ "num_attention_heads": 1,
41
+ "num_hidden_layers": 1,
42
+ "projection_dim": 16,
43
+ "vocab_size": 1000
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.50.0.dev0"
47
+ }
text_encoder/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f165c882b1eb94a6b778e4e8c57cda20152e6886069e0aceddb11f665d621e7
3
+ size 2642474
text_encoder_2/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5EncoderModel"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 37,
7
+ "d_kv": 8,
8
+ "d_model": 32,
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
+ "num_decoder_layers": 1,
19
+ "num_heads": 1,
20
+ "num_layers": 1,
21
+ "pad_token_id": 0,
22
+ "relative_attention_max_distance": 128,
23
+ "relative_attention_num_buckets": 32,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.50.0.dev0",
26
+ "use_cache": true,
27
+ "vocab_size": 32100
28
+ }
text_encoder_2/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec71252f4ca242f8f161735c40964abd4b3822257505575ec00c1cbb98362d30
3
+ size 4127258
tokenizer/merges.txt ADDED
@@ -0,0 +1,803 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #version: 0.2
2
+ Ġ t
3
+ h e
4
+ Ġ a
5
+ i n
6
+ Ġt he
7
+ e r
8
+ o n
9
+ Ġ ,
10
+ r e
11
+ Ġ s
12
+ e d
13
+ Ġ o
14
+ Ġ w
15
+ n d
16
+ a t
17
+ Ġ .
18
+ o r
19
+ i t
20
+ Ġ c
21
+ e n
22
+ Ġ f
23
+ i s
24
+ e s
25
+ a r
26
+ Ġo f
27
+ Ġ b
28
+ a n
29
+ Ġ in
30
+ a l
31
+ in g
32
+ Ġ p
33
+ Ġa nd
34
+ a s
35
+ Ġt o
36
+ r o
37
+ i c
38
+ Ġ m
39
+ Ġ d
40
+ Ġ h
41
+ i on
42
+ l e
43
+ o u
44
+ Ġ T
45
+ Ġ re
46
+ Ġ =
47
+ Ġ "
48
+ Ġ A
49
+ Ġ S
50
+ en t
51
+ i l
52
+ Ġt h
53
+ Ġ 1
54
+ s t
55
+ Ġ C
56
+ e l
57
+ o m
58
+ Ġ l
59
+ a m
60
+ Ġ Ċ
61
+ Ġ e
62
+ Ġ n
63
+ Ġ @
64
+ a d
65
+ a c
66
+ Ġw as
67
+ Ġ M
68
+ u r
69
+ ĠT he
70
+ e c
71
+ Ġ on
72
+ l y
73
+ Ġ B
74
+ Ġ I
75
+ Ġ g
76
+ Ġ '
77
+ e t
78
+ o l
79
+ i d
80
+ i v
81
+ i m
82
+ Ġf or
83
+ i r
84
+ - @
85
+ Ġ@ -@
86
+ i g
87
+ o t
88
+ t er
89
+ Ġa s
90
+ Ġ H
91
+ u s
92
+ o w
93
+ Ġs t
94
+ u t
95
+ it h
96
+ a y
97
+ Ġ 2
98
+ Ġ P
99
+ at ion
100
+ v er
101
+ Ġb e
102
+ he r
103
+ Ġth at
104
+ Ġw ith
105
+ Ġ R
106
+ c e
107
+ t h
108
+ Ġ D
109
+ Ġ is
110
+ u n
111
+ e m
112
+ Ġ F
113
+ Ġw h
114
+ u l
115
+ Ġb y
116
+ Ġa l
117
+ c h
118
+ Ġ )
119
+ Ġ (
120
+ Ġ W
121
+ Ġc on
122
+ r a
123
+ Ġ G
124
+ o s
125
+ Ġ L
126
+ Ġ N
127
+ Ġa t
128
+ er s
129
+ c t
130
+ Ġ it
131
+ Ġ1 9
132
+ ro m
133
+ a nd
134
+ Ġa n
135
+ u m
136
+ es t
137
+ Ġ J
138
+ a g
139
+ Ġ he
140
+ 0 0
141
+ is t
142
+ a in
143
+ o d
144
+ a v
145
+ r i
146
+ Ġ E
147
+ Ġ O
148
+ Ġf rom
149
+ Ġc om
150
+ Ġh is
151
+ o p
152
+ Ġp ro
153
+ re s
154
+ i es
155
+ i f
156
+ Ġ v
157
+ or t
158
+ er e
159
+ il l
160
+ l d
161
+ Ġd e
162
+ p p
163
+ Ġs u
164
+ o re
165
+ ĠI n
166
+ Ġ r
167
+ Ġs e
168
+ Ġw ere
169
+ e w
170
+ on g
171
+ ig h
172
+ ar d
173
+ at e
174
+ al l
175
+ ar t
176
+ a k
177
+ ic h
178
+ Ġc h
179
+ Ġo r
180
+ a b
181
+ an t
182
+ u d
183
+ o c
184
+ b er
185
+ Ġe x
186
+ g h
187
+ it y
188
+ at ed
189
+ p t
190
+ es s
191
+ e ar
192
+ Ġ K
193
+ Ġp l
194
+ am e
195
+ q u
196
+ iv e
197
+ ro u
198
+ Ġa re
199
+ Ġ â
200
+ Ġs h
201
+ Ġ k
202
+ ac k
203
+ ec t
204
+ Ġâ Ģ
205
+ Ġ U
206
+ Ġh ad
207
+ s e
208
+ Ġwh ich
209
+ re d
210
+ o v
211
+ ĠS t
212
+ as t
213
+ Ġs p
214
+ i an
215
+ Ġ y
216
+ m ent
217
+ Ġ le
218
+ Ġn ot
219
+ g e
220
+ or d
221
+ r it
222
+ i p
223
+ in e
224
+ el l
225
+ al ly
226
+ ou r
227
+ o st
228
+ igh t
229
+ t her
230
+ a p
231
+ Ġ u
232
+ is h
233
+ ĠC h
234
+ ou n
235
+ i a
236
+ Ġ 3
237
+ av e
238
+ ar y
239
+ u st
240
+ o g
241
+ Ġ2 00
242
+ Ġ un
243
+ ou s
244
+ ir st
245
+ Ġ V
246
+ c c
247
+ Ġin c
248
+ Ġ ;
249
+ Ġcom p
250
+ r u
251
+ ion s
252
+ Ġthe ir
253
+ Ġb ut
254
+ id e
255
+ u re
256
+ s o
257
+ Ġcon t
258
+ Ġin t
259
+ f ter
260
+ ic al
261
+ i al
262
+ Ġa r
263
+ Ġf irst
264
+ ou ld
265
+ Ġit s
266
+ he d
267
+ ĠâĢ ĵ
268
+ Ġw he
269
+ w o
270
+ ou t
271
+ u b
272
+ Ġ2 0
273
+ f f
274
+ Ġ :
275
+ u e
276
+ Ġ her
277
+ ow n
278
+ o k
279
+ Ġal so
280
+ Ġc l
281
+ p er
282
+ ig n
283
+ at er
284
+ r an
285
+ or m
286
+ i e
287
+ om e
288
+ or k
289
+ as s
290
+ i re
291
+ e nd
292
+ Ġre s
293
+ Ġa b
294
+ Ġa d
295
+ Ġ us
296
+ r y
297
+ Ġre c
298
+ Ġh ave
299
+ ag e
300
+ ĠH e
301
+ Ġ 4
302
+ Ġ ro
303
+ m er
304
+ Ġon e
305
+ on d
306
+ l ow
307
+ Ġh as
308
+ ĠT h
309
+ d u
310
+ Ġ 5
311
+ Ġp er
312
+ Ġbe en
313
+ im e
314
+ Ġt wo
315
+ en ce
316
+ l and
317
+ Ġ1 8
318
+ . @
319
+ Ġ@ .@
320
+ ul t
321
+ re e
322
+ ou gh
323
+ i le
324
+ Ġwh o
325
+ ĠA l
326
+ Ġs c
327
+ ur ing
328
+ p l
329
+ or y
330
+ it ion
331
+ r ic
332
+ ation s
333
+ Ġd is
334
+ Ġth is
335
+ Ġb ec
336
+ Ġa pp
337
+ i z
338
+ ĠI t
339
+ a re
340
+ ac h
341
+ l ud
342
+ ad e
343
+ Ġpl ay
344
+ Ġ j
345
+ Ġm an
346
+ ac t
347
+ el y
348
+ Ġp art
349
+ Ġd es
350
+ Ġa g
351
+ Ġthe y
352
+ Ġy ear
353
+ oun t
354
+ Ġ20 1
355
+ Ġo ver
356
+ Ġo ther
357
+ ou nd
358
+ Ġa fter
359
+ i b
360
+ o ver
361
+ Ġs er
362
+ Ġ en
363
+ Ġof f
364
+ Ġ im
365
+ ct ion
366
+ Ġ Y
367
+ k e
368
+ it e
369
+ , @
370
+ Ġ@ ,@
371
+ t e
372
+ ur n
373
+ Ġinc lud
374
+ res s
375
+ an ce
376
+ an g
377
+ Ġat t
378
+ ic e
379
+ ac e
380
+ ar k
381
+ Ġo ut
382
+ w n
383
+ p h
384
+ em ber
385
+ Ġp re
386
+ Ġu p
387
+ en s
388
+ m an
389
+ Ġe v
390
+ Ġt ime
391
+ nd er
392
+ rou gh
393
+ c ed
394
+ Ġf in
395
+ Ġint o
396
+ on e
397
+ p ort
398
+ rou nd
399
+ w e
400
+ re n
401
+ l es
402
+ in t
403
+ ĠO n
404
+ v el
405
+ Ġcom m
406
+ Ġs he
407
+ as on
408
+ am p
409
+ Ġt e
410
+ Ġw ould
411
+ w ard
412
+ Ġm ore
413
+ Ġ 6
414
+ i ed
415
+ os e
416
+ ri b
417
+ ĠU n
418
+ Ġal l
419
+ ing s
420
+ ter n
421
+ c es
422
+ ab le
423
+ Ġw e
424
+ it ed
425
+ e ver
426
+ ent s
427
+ Ġh im
428
+ as ed
429
+ or s
430
+ o y
431
+ o od
432
+ Ġc ent
433
+ i x
434
+ as e
435
+ il d
436
+ ĠA n
437
+ Ġ 7
438
+ Ġw ork
439
+ at es
440
+ i ous
441
+ at h
442
+ Ġp o
443
+ ro p
444
+ ol d
445
+ al s
446
+ is s
447
+ e y
448
+ ic t
449
+ Ġf e
450
+ Ġthe m
451
+ g an
452
+ Ġs ec
453
+ Ġb et
454
+ Ġwhe n
455
+ Ġs ong
456
+ Ġre m
457
+ e p
458
+ f orm
459
+ a il
460
+ f er
461
+ Ġe ar
462
+ ub l
463
+ a w
464
+ Ġk n
465
+ ak e
466
+ a us
467
+ Ġm ost
468
+ Ġcon s
469
+ Ġd uring
470
+ ĠA s
471
+ or th
472
+ Ġn ew
473
+ er ed
474
+ il m
475
+ v ed
476
+ at t
477
+ Ġon ly
478
+ Ġ 9
479
+ Ġd ec
480
+ Ġ 8
481
+ ic k
482
+ Ġg ame
483
+ on s
484
+ u g
485
+ Ġt r
486
+ f t
487
+ ot h
488
+ o ok
489
+ ĠM ar
490
+ re at
491
+ w ay
492
+ Ġc an
493
+ ol low
494
+ ou th
495
+ we en
496
+ ĠE n
497
+ Ġ19 9
498
+ ter s
499
+ Ġre l
500
+ in d
501
+ Ġab out
502
+ Ġse ason
503
+ Ġag ain
504
+ r al
505
+ Ġth ree
506
+ ation al
507
+ Ġu nder
508
+ ul ar
509
+ Ġm e
510
+ Ġth an
511
+ ĠC om
512
+ ĠA r
513
+ h ip
514
+ o b
515
+ Ġn e
516
+ Ġbet ween
517
+ Ġf l
518
+ h n
519
+ v e
520
+ Ġch ar
521
+ Ġc ol
522
+ Ġrec ord
523
+ i ew
524
+ r on
525
+ f ore
526
+ Ġth rough
527
+ is ion
528
+ or n
529
+ Ġ 00
530
+ oc k
531
+ Ġ ver
532
+ Ġl ater
533
+ Ġn um
534
+ Ġe nd
535
+ ol og
536
+ am es
537
+ Ġp os
538
+ Ġw rit
539
+ Ġpro du
540
+ Ġwh ile
541
+ Ġa ct
542
+ Ġre le
543
+ Ġf ilm
544
+ is hed
545
+ Ġp r
546
+ an s
547
+ Ġre g
548
+ Ġfor m
549
+ Ġas s
550
+ ĠS e
551
+ ur y
552
+ t ed
553
+ t s
554
+ Ġm ade
555
+ Ġsu b
556
+ Ġp e
557
+ Ġs o
558
+ or ld
559
+ Ġre t
560
+ ĠN ew
561
+ Ġsp ec
562
+ Ġa cc
563
+ Ġ qu
564
+ Ġwhe re
565
+ en er
566
+ Ġm ov
567
+ he s
568
+ mer ic
569
+ at ing
570
+ Ġin ter
571
+ ĠL e
572
+ ĠA meric
573
+ Ġ ra
574
+ Ġs ome
575
+ Ġc o
576
+ Ġl ar
577
+ Ġb u
578
+ Ġde f
579
+ b um
580
+ Ġa c
581
+ Ġm us
582
+ Ġf ollow
583
+ ĠA t
584
+ in s
585
+ iv ed
586
+ if ic
587
+ u al
588
+ Ġa m
589
+ Ġsu ch
590
+ Ġsec ond
591
+ i ke
592
+ Ġf our
593
+ Ġin d
594
+ an n
595
+ he n
596
+ Ġus ed
597
+ ĠR e
598
+ ic s
599
+ le ct
600
+ Ġd ay
601
+ i el
602
+ il y
603
+ ĠTh is
604
+ Ġ 0
605
+ Ġp ubl
606
+ Ġc all
607
+ ĠJ o
608
+ l l
609
+ Ġal bum
610
+ Ġ00 0
611
+ ran s
612
+ Ġd o
613
+ an y
614
+ Ġbe fore
615
+ ro s
616
+ ĠS h
617
+ Ġs y
618
+ a id
619
+ ĠEn g
620
+ Ġbe ing
621
+ Ġ1 0
622
+ u c
623
+ Ġe p
624
+ Ġsu pp
625
+ Ġthe re
626
+ Ġyear s
627
+ ar s
628
+ ow ever
629
+ Ġ ent
630
+ if e
631
+ Ġh igh
632
+ Ġf ound
633
+ ir d
634
+ Ġn o
635
+ Ġs et
636
+ in es
637
+ iv er
638
+ i o
639
+ ot her
640
+ j ect
641
+ Ġs ur
642
+ a j
643
+ t en
644
+ Ġt ra
645
+ Ġ1 2
646
+ is ed
647
+ it ies
648
+ vel op
649
+ Ġb l
650
+ al e
651
+ Ġser ies
652
+ Ġl oc
653
+ Ġnum ber
654
+ Ġp res
655
+ an e
656
+ aus e
657
+ od e
658
+ e k
659
+ t on
660
+ ĠS c
661
+ i er
662
+ is e
663
+ Ġse ver
664
+ in ce
665
+ Ġb oth
666
+ an k
667
+ ro w
668
+ ire ct
669
+ s on
670
+ Ġthe n
671
+ ĠB rit
672
+ i et
673
+ Ġ1 6
674
+ Ġep is
675
+ Ġinclud ing
676
+ it s
677
+ ig in
678
+ p r
679
+ Ġ /
680
+ Ġagain st
681
+ Ġw ell
682
+ Ġbec ame
683
+ Ġex p
684
+ Ġkn own
685
+ Ġt rans
686
+ Ġchar ac
687
+ ĠâĢ Ķ
688
+ r am
689
+ Ġb ack
690
+ Ġad d
691
+ Ġp op
692
+ Ġg o
693
+ ur ch
694
+ Ġdes c
695
+ Ġs ing
696
+ iel d
697
+ Ġper form
698
+ ain ed
699
+ Ġre ce
700
+ id ent
701
+ Ġe m
702
+ er t
703
+ u res
704
+ Ġin v
705
+ Ġde p
706
+ Ġ19 8
707
+ a ir
708
+ er n
709
+ at her
710
+ f ul
711
+ Ġ Z
712
+ Ġm on
713
+ Ġman y
714
+ Ġm ain
715
+ Ġst ud
716
+ Ġl ong
717
+ in n
718
+ th ough
719
+ u p
720
+ o ol
721
+ ĠUn ited
722
+ l ed
723
+ em ent
724
+ Ġ1 5
725
+ ow er
726
+ ĠJo hn
727
+ Ġo p
728
+ Ġ1 1
729
+ in ed
730
+ Ġm et
731
+ o ber
732
+ le y
733
+ Ġ1 7
734
+ Ġcent ury
735
+ Ġte am
736
+ Ġ est
737
+ ĠA fter
738
+ y l
739
+ Ġm in
740
+ u ch
741
+ ut e
742
+ Ġde velop
743
+ ĠS he
744
+ i am
745
+ Ġsh ow
746
+ el f
747
+ Ġre p
748
+ Ġcon c
749
+ at ive
750
+ Ġc re
751
+ over n
752
+ a red
753
+ Ġ19 4
754
+ Ġor igin
755
+ Ġs m
756
+ iv ers
757
+ a z
758
+ Ġle ad
759
+ Ġsever al
760
+ a h
761
+ Ġo b
762
+ Ġre v
763
+ Ġm ill
764
+ er m
765
+ u ally
766
+ o ot
767
+ Ġbe gan
768
+ Ġ19 6
769
+ i red
770
+ Ġd if
771
+ Ġcont in
772
+ Ġs ign
773
+ i k
774
+ ĠI nd
775
+ ment s
776
+ iz ed
777
+ Ġ19 7
778
+ Ġd irect
779
+ a u
780
+ Ġex t
781
+ ros s
782
+ em b
783
+ d er
784
+ Ġp ol
785
+ Ġm ay
786
+ a pt
787
+ el s
788
+ ĠW h
789
+ Ġcomp le
790
+ Ġar t
791
+ ĠB r
792
+ ĠI s
793
+ un e
794
+ t il
795
+ Ġc rit
796
+ Ġh ist
797
+ Ġear ly
798
+ Ġc ould
799
+ ĠC on
800
+ Ġd id
801
+ Ġb el
802
+ Ġcall ed
803
+ u ed
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
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": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 77,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "unk_token": "<unk>"
57
+ }
tokenizer/vocab.json ADDED
@@ -0,0 +1,1002 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 5,
3
+ "\"": 6,
4
+ "#": 7,
5
+ "$": 8,
6
+ "%": 9,
7
+ "&": 10,
8
+ "'": 11,
9
+ "(": 12,
10
+ ")": 13,
11
+ "*": 14,
12
+ "+": 15,
13
+ ",": 16,
14
+ ",@": 565,
15
+ "-": 17,
16
+ "-@": 280,
17
+ ".": 18,
18
+ ".@": 514,
19
+ "/": 19,
20
+ "0": 20,
21
+ "00": 336,
22
+ "1": 21,
23
+ "2": 22,
24
+ "3": 23,
25
+ "4": 24,
26
+ "5": 25,
27
+ "6": 26,
28
+ "7": 27,
29
+ "8": 28,
30
+ "9": 29,
31
+ ":": 30,
32
+ ";": 31,
33
+ "<": 32,
34
+ "</s>": 2,
35
+ "<mask>": 4,
36
+ "<pad>": 1,
37
+ "<s>": 0,
38
+ "<unk>": 3,
39
+ "=": 33,
40
+ ">": 34,
41
+ "?": 35,
42
+ "@": 36,
43
+ "A": 37,
44
+ "B": 38,
45
+ "C": 39,
46
+ "D": 40,
47
+ "E": 41,
48
+ "F": 42,
49
+ "G": 43,
50
+ "H": 44,
51
+ "I": 45,
52
+ "J": 46,
53
+ "K": 47,
54
+ "L": 48,
55
+ "M": 49,
56
+ "N": 50,
57
+ "O": 51,
58
+ "P": 52,
59
+ "Q": 53,
60
+ "R": 54,
61
+ "S": 55,
62
+ "T": 56,
63
+ "U": 57,
64
+ "V": 58,
65
+ "W": 59,
66
+ "X": 60,
67
+ "Y": 61,
68
+ "Z": 62,
69
+ "[": 63,
70
+ "\\": 64,
71
+ "]": 65,
72
+ "^": 66,
73
+ "_": 67,
74
+ "`": 68,
75
+ "a": 69,
76
+ "ab": 376,
77
+ "able": 618,
78
+ "ac": 261,
79
+ "ace": 575,
80
+ "ach": 536,
81
+ "ack": 398,
82
+ "act": 542,
83
+ "ad": 260,
84
+ "ade": 538,
85
+ "ag": 334,
86
+ "age": 495,
87
+ "ah": 956,
88
+ "aid": 814,
89
+ "ail": 655,
90
+ "ain": 338,
91
+ "ained": 894,
92
+ "air": 903,
93
+ "aj": 838,
94
+ "ak": 372,
95
+ "ake": 661,
96
+ "al": 226,
97
+ "ale": 846,
98
+ "all": 370,
99
+ "ally": 421,
100
+ "als": 641,
101
+ "am": 255,
102
+ "ame": 390,
103
+ "ames": 732,
104
+ "amp": 604,
105
+ "an": 224,
106
+ "ance": 571,
107
+ "and": 329,
108
+ "ane": 851,
109
+ "ang": 572,
110
+ "ank": 862,
111
+ "ann": 790,
112
+ "ans": 742,
113
+ "ant": 377,
114
+ "any": 809,
115
+ "ap": 426,
116
+ "apt": 982,
117
+ "ar": 221,
118
+ "ard": 368,
119
+ "are": 535,
120
+ "ared": 948,
121
+ "ark": 576,
122
+ "ars": 823,
123
+ "art": 371,
124
+ "ary": 434,
125
+ "as": 230,
126
+ "ase": 630,
127
+ "ased": 624,
128
+ "ason": 603,
129
+ "ass": 485,
130
+ "ast": 408,
131
+ "at": 212,
132
+ "ate": 369,
133
+ "ated": 384,
134
+ "ater": 479,
135
+ "ates": 635,
136
+ "ath": 637,
137
+ "ather": 905,
138
+ "ating": 765,
139
+ "ation": 295,
140
+ "ational": 702,
141
+ "ations": 528,
142
+ "ative": 945,
143
+ "att": 672,
144
+ "au": 975,
145
+ "aus": 662,
146
+ "ause": 852,
147
+ "av": 340,
148
+ "ave": 433,
149
+ "aw": 659,
150
+ "ay": 292,
151
+ "az": 953,
152
+ "b": 70,
153
+ "ber": 380,
154
+ "bum": 775,
155
+ "c": 71,
156
+ "cc": 442,
157
+ "ce": 302,
158
+ "ced": 589,
159
+ "ces": 617,
160
+ "ch": 313,
161
+ "ct": 325,
162
+ "ction": 561,
163
+ "d": 72,
164
+ "der": 979,
165
+ "du": 505,
166
+ "e": 73,
167
+ "ear": 387,
168
+ "ec": 266,
169
+ "ect": 399,
170
+ "ed": 208,
171
+ "ek": 854,
172
+ "el": 252,
173
+ "elf": 942,
174
+ "ell": 420,
175
+ "els": 983,
176
+ "ely": 543,
177
+ "em": 307,
178
+ "emb": 978,
179
+ "ember": 580,
180
+ "ement": 919,
181
+ "en": 217,
182
+ "ence": 511,
183
+ "end": 487,
184
+ "ener": 761,
185
+ "ens": 583,
186
+ "ent": 246,
187
+ "ents": 622,
188
+ "ep": 653,
189
+ "er": 203,
190
+ "ere": 354,
191
+ "ered": 669,
192
+ "erm": 960,
193
+ "ern": 904,
194
+ "ers": 324,
195
+ "ert": 898,
196
+ "es": 220,
197
+ "ess": 386,
198
+ "est": 332,
199
+ "et": 273,
200
+ "ever": 621,
201
+ "ew": 365,
202
+ "ey": 643,
203
+ "f": 74,
204
+ "fer": 656,
205
+ "ff": 469,
206
+ "fore": 721,
207
+ "form": 654,
208
+ "ft": 682,
209
+ "fter": 455,
210
+ "ful": 906,
211
+ "g": 75,
212
+ "gan": 647,
213
+ "ge": 415,
214
+ "gh": 382,
215
+ "h": 76,
216
+ "he": 199,
217
+ "hed": 462,
218
+ "hen": 791,
219
+ "her": 298,
220
+ "hes": 763,
221
+ "hip": 709,
222
+ "hn": 714,
223
+ "i": 77,
224
+ "ia": 431,
225
+ "ial": 457,
226
+ "iam": 940,
227
+ "ian": 410,
228
+ "ib": 555,
229
+ "ic": 233,
230
+ "ical": 456,
231
+ "ice": 574,
232
+ "ich": 373,
233
+ "ick": 677,
234
+ "ics": 794,
235
+ "ict": 644,
236
+ "id": 275,
237
+ "ide": 450,
238
+ "ident": 896,
239
+ "ie": 482,
240
+ "ied": 610,
241
+ "iel": 797,
242
+ "ield": 892,
243
+ "ier": 857,
244
+ "ies": 350,
245
+ "iet": 868,
246
+ "iew": 719,
247
+ "if": 351,
248
+ "ife": 826,
249
+ "ific": 782,
250
+ "ig": 282,
251
+ "igh": 367,
252
+ "ight": 424,
253
+ "igin": 873,
254
+ "ign": 478,
255
+ "ik": 969,
256
+ "ike": 787,
257
+ "il": 247,
258
+ "ild": 631,
259
+ "ile": 519,
260
+ "ill": 355,
261
+ "ilm": 670,
262
+ "ily": 798,
263
+ "im": 277,
264
+ "ime": 509,
265
+ "in": 201,
266
+ "ince": 860,
267
+ "ind": 696,
268
+ "ine": 419,
269
+ "ined": 925,
270
+ "ines": 832,
271
+ "ing": 227,
272
+ "ings": 615,
273
+ "inn": 913,
274
+ "ins": 780,
275
+ "int": 598,
276
+ "io": 834,
277
+ "ion": 237,
278
+ "ions": 447,
279
+ "ious": 636,
280
+ "ip": 418,
281
+ "ir": 279,
282
+ "ird": 829,
283
+ "ire": 486,
284
+ "irect": 864,
285
+ "ired": 965,
286
+ "irst": 440,
287
+ "is": 219,
288
+ "ise": 858,
289
+ "ised": 842,
290
+ "ish": 428,
291
+ "ished": 740,
292
+ "ision": 723,
293
+ "iss": 642,
294
+ "ist": 337,
295
+ "it": 215,
296
+ "ite": 564,
297
+ "ited": 620,
298
+ "ith": 291,
299
+ "ities": 843,
300
+ "ition": 526,
301
+ "its": 872,
302
+ "ity": 383,
303
+ "iv": 276,
304
+ "ive": 392,
305
+ "ived": 781,
306
+ "iver": 833,
307
+ "ivers": 952,
308
+ "ix": 629,
309
+ "iz": 533,
310
+ "ized": 972,
311
+ "j": 78,
312
+ "ject": 836,
313
+ "k": 79,
314
+ "ke": 563,
315
+ "l": 80,
316
+ "land": 512,
317
+ "ld": 356,
318
+ "le": 238,
319
+ "lect": 795,
320
+ "led": 918,
321
+ "les": 597,
322
+ "ley": 928,
323
+ "ll": 804,
324
+ "low": 502,
325
+ "lud": 537,
326
+ "ly": 268,
327
+ "m": 81,
328
+ "man": 584,
329
+ "ment": 412,
330
+ "ments": 971,
331
+ "mer": 499,
332
+ "meric": 764,
333
+ "n": 82,
334
+ "nd": 211,
335
+ "nder": 587,
336
+ "o": 83,
337
+ "ob": 710,
338
+ "ober": 927,
339
+ "oc": 379,
340
+ "ock": 726,
341
+ "od": 339,
342
+ "ode": 853,
343
+ "og": 436,
344
+ "ok": 474,
345
+ "ol": 274,
346
+ "old": 640,
347
+ "ollow": 689,
348
+ "olog": 731,
349
+ "om": 253,
350
+ "ome": 483,
351
+ "on": 204,
352
+ "ond": 501,
353
+ "one": 592,
354
+ "ong": 366,
355
+ "ons": 679,
356
+ "ood": 627,
357
+ "ook": 684,
358
+ "ool": 916,
359
+ "oot": 962,
360
+ "op": 347,
361
+ "or": 214,
362
+ "ord": 416,
363
+ "ore": 360,
364
+ "ork": 484,
365
+ "orld": 754,
366
+ "orm": 481,
367
+ "orn": 724,
368
+ "ors": 625,
369
+ "ort": 353,
370
+ "orth": 667,
371
+ "ory": 525,
372
+ "os": 320,
373
+ "ose": 611,
374
+ "ost": 423,
375
+ "ot": 283,
376
+ "oth": 683,
377
+ "other": 835,
378
+ "ou": 239,
379
+ "ough": 518,
380
+ "ould": 460,
381
+ "oun": 430,
382
+ "ound": 553,
383
+ "ount": 549,
384
+ "our": 422,
385
+ "ous": 439,
386
+ "out": 466,
387
+ "outh": 690,
388
+ "ov": 406,
389
+ "over": 556,
390
+ "overn": 947,
391
+ "ow": 288,
392
+ "ower": 921,
393
+ "owever": 824,
394
+ "own": 473,
395
+ "oy": 626,
396
+ "p": 84,
397
+ "per": 477,
398
+ "ph": 579,
399
+ "pl": 524,
400
+ "port": 593,
401
+ "pp": 358,
402
+ "pr": 874,
403
+ "pt": 385,
404
+ "q": 85,
405
+ "qu": 391,
406
+ "r": 86,
407
+ "ra": 318,
408
+ "ral": 700,
409
+ "ram": 884,
410
+ "ran": 480,
411
+ "rans": 807,
412
+ "re": 206,
413
+ "reat": 686,
414
+ "red": 405,
415
+ "ree": 517,
416
+ "ren": 596,
417
+ "res": 349,
418
+ "ress": 570,
419
+ "ri": 341,
420
+ "rib": 612,
421
+ "ric": 527,
422
+ "rit": 417,
423
+ "ro": 232,
424
+ "rom": 328,
425
+ "ron": 720,
426
+ "rop": 639,
427
+ "ros": 811,
428
+ "ross": 977,
429
+ "rou": 393,
430
+ "rough": 588,
431
+ "round": 594,
432
+ "row": 863,
433
+ "ru": 446,
434
+ "ry": 492,
435
+ "s": 87,
436
+ "se": 403,
437
+ "so": 452,
438
+ "son": 865,
439
+ "st": 250,
440
+ "t": 88,
441
+ "te": 567,
442
+ "ted": 748,
443
+ "ten": 839,
444
+ "ter": 284,
445
+ "tern": 616,
446
+ "ters": 694,
447
+ "th": 303,
448
+ "ther": 425,
449
+ "though": 914,
450
+ "til": 990,
451
+ "ton": 855,
452
+ "ts": 749,
453
+ "u": 89,
454
+ "ual": 783,
455
+ "ually": 961,
456
+ "ub": 467,
457
+ "ubl": 658,
458
+ "uc": 818,
459
+ "uch": 936,
460
+ "ud": 378,
461
+ "ue": 471,
462
+ "ued": 999,
463
+ "ug": 680,
464
+ "ul": 310,
465
+ "ular": 704,
466
+ "ult": 516,
467
+ "um": 331,
468
+ "un": 306,
469
+ "une": 989,
470
+ "up": 915,
471
+ "ur": 264,
472
+ "urch": 889,
473
+ "ure": 451,
474
+ "ures": 899,
475
+ "uring": 523,
476
+ "urn": 568,
477
+ "ury": 747,
478
+ "us": 287,
479
+ "ust": 435,
480
+ "ut": 290,
481
+ "ute": 937,
482
+ "v": 90,
483
+ "ve": 715,
484
+ "ved": 671,
485
+ "vel": 600,
486
+ "velop": 844,
487
+ "ver": 296,
488
+ "w": 91,
489
+ "ward": 607,
490
+ "way": 687,
491
+ "we": 595,
492
+ "ween": 691,
493
+ "wn": 578,
494
+ "wo": 465,
495
+ "x": 92,
496
+ "y": 93,
497
+ "yl": 934,
498
+ "z": 94,
499
+ "|": 95,
500
+ "}": 96,
501
+ "~": 97,
502
+ "¡": 98,
503
+ "¢": 99,
504
+ "£": 100,
505
+ "¤": 101,
506
+ "¥": 102,
507
+ "¦": 103,
508
+ "§": 104,
509
+ "¨": 105,
510
+ "©": 106,
511
+ "ª": 107,
512
+ "«": 108,
513
+ "¬": 109,
514
+ "®": 110,
515
+ "¯": 111,
516
+ "°": 112,
517
+ "±": 113,
518
+ "²": 114,
519
+ "³": 115,
520
+ "´": 116,
521
+ "µ": 117,
522
+ "¶": 118,
523
+ "·": 119,
524
+ "¸": 120,
525
+ "¹": 121,
526
+ "º": 122,
527
+ "»": 123,
528
+ "¼": 124,
529
+ "½": 125,
530
+ "¾": 126,
531
+ "¿": 127,
532
+ "Â": 128,
533
+ "Ã": 129,
534
+ "Ä": 130,
535
+ "Å": 131,
536
+ "Æ": 132,
537
+ "Ç": 133,
538
+ "È": 134,
539
+ "É": 135,
540
+ "Ê": 136,
541
+ "Ë": 137,
542
+ "Ì": 138,
543
+ "Í": 139,
544
+ "Î": 140,
545
+ "Ï": 141,
546
+ "Ð": 142,
547
+ "Ñ": 143,
548
+ "Ö": 144,
549
+ "×": 145,
550
+ "Ø": 146,
551
+ "Ù": 147,
552
+ "Ü": 148,
553
+ "à": 149,
554
+ "á": 150,
555
+ "â": 151,
556
+ "ã": 152,
557
+ "ä": 153,
558
+ "å": 154,
559
+ "æ": 155,
560
+ "ç": 156,
561
+ "è": 157,
562
+ "é": 158,
563
+ "ë": 159,
564
+ "ì": 160,
565
+ "ï": 161,
566
+ "Ċ": 162,
567
+ "Ġ": 163,
568
+ "Ġ\"": 243,
569
+ "Ġ'": 272,
570
+ "Ġ(": 315,
571
+ "Ġ)": 314,
572
+ "Ġ,": 205,
573
+ "Ġ.": 213,
574
+ "Ġ/": 875,
575
+ "Ġ0": 800,
576
+ "Ġ00": 725,
577
+ "Ġ000": 806,
578
+ "Ġ1": 249,
579
+ "Ġ10": 817,
580
+ "Ġ11": 924,
581
+ "Ġ12": 841,
582
+ "Ġ15": 920,
583
+ "Ġ16": 869,
584
+ "Ġ17": 929,
585
+ "Ġ18": 513,
586
+ "Ġ19": 327,
587
+ "Ġ194": 949,
588
+ "Ġ196": 964,
589
+ "Ġ197": 973,
590
+ "Ġ198": 902,
591
+ "Ġ199": 693,
592
+ "Ġ2": 293,
593
+ "Ġ20": 468,
594
+ "Ġ200": 437,
595
+ "Ġ201": 550,
596
+ "Ġ3": 432,
597
+ "Ġ4": 497,
598
+ "Ġ5": 506,
599
+ "Ġ6": 609,
600
+ "Ġ7": 633,
601
+ "Ġ8": 676,
602
+ "Ġ9": 674,
603
+ "Ġ:": 470,
604
+ "Ġ;": 444,
605
+ "Ġ=": 242,
606
+ "Ġ@": 259,
607
+ "Ġ@,@": 566,
608
+ "Ġ@-@": 281,
609
+ "Ġ@.@": 515,
610
+ "ĠA": 244,
611
+ "ĠAfter": 933,
612
+ "ĠAl": 521,
613
+ "ĠAmeric": 768,
614
+ "ĠAn": 632,
615
+ "ĠAr": 708,
616
+ "ĠAs": 666,
617
+ "ĠAt": 779,
618
+ "ĠB": 269,
619
+ "ĠBr": 987,
620
+ "ĠBrit": 867,
621
+ "ĠC": 251,
622
+ "ĠCh": 429,
623
+ "ĠCom": 707,
624
+ "ĠCon": 995,
625
+ "ĠD": 304,
626
+ "ĠE": 342,
627
+ "ĠEn": 692,
628
+ "ĠEng": 815,
629
+ "ĠF": 308,
630
+ "ĠG": 319,
631
+ "ĠH": 286,
632
+ "ĠHe": 496,
633
+ "ĠI": 270,
634
+ "ĠIn": 361,
635
+ "ĠInd": 970,
636
+ "ĠIs": 988,
637
+ "ĠIt": 534,
638
+ "ĠJ": 333,
639
+ "ĠJo": 803,
640
+ "ĠJohn": 922,
641
+ "ĠK": 388,
642
+ "ĠL": 321,
643
+ "ĠLe": 767,
644
+ "ĠM": 263,
645
+ "ĠMar": 685,
646
+ "ĠN": 322,
647
+ "ĠNew": 756,
648
+ "ĠO": 343,
649
+ "ĠOn": 599,
650
+ "ĠP": 294,
651
+ "ĠR": 301,
652
+ "ĠRe": 793,
653
+ "ĠS": 245,
654
+ "ĠSc": 856,
655
+ "ĠSe": 746,
656
+ "ĠSh": 812,
657
+ "ĠShe": 939,
658
+ "ĠSt": 407,
659
+ "ĠT": 240,
660
+ "ĠTh": 504,
661
+ "ĠThe": 265,
662
+ "ĠThis": 799,
663
+ "ĠU": 401,
664
+ "ĠUn": 613,
665
+ "ĠUnited": 917,
666
+ "ĠV": 441,
667
+ "ĠW": 316,
668
+ "ĠWh": 984,
669
+ "ĠY": 562,
670
+ "ĠZ": 907,
671
+ "Ġa": 200,
672
+ "Ġab": 489,
673
+ "Ġabout": 697,
674
+ "Ġac": 776,
675
+ "Ġacc": 758,
676
+ "Ġact": 737,
677
+ "Ġad": 490,
678
+ "Ġadd": 886,
679
+ "Ġafter": 554,
680
+ "Ġag": 546,
681
+ "Ġagain": 699,
682
+ "Ġagainst": 876,
683
+ "Ġal": 312,
684
+ "Ġalbum": 805,
685
+ "Ġall": 614,
686
+ "Ġalso": 475,
687
+ "Ġam": 784,
688
+ "Ġan": 330,
689
+ "Ġand": 229,
690
+ "Ġapp": 532,
691
+ "Ġar": 458,
692
+ "Ġare": 394,
693
+ "Ġart": 986,
694
+ "Ġas": 285,
695
+ "Ġass": 745,
696
+ "Ġat": 323,
697
+ "Ġatt": 573,
698
+ "Ġb": 223,
699
+ "Ġback": 885,
700
+ "Ġbe": 297,
701
+ "Ġbec": 531,
702
+ "Ġbecame": 878,
703
+ "Ġbeen": 508,
704
+ "Ġbefore": 810,
705
+ "Ġbegan": 963,
706
+ "Ġbeing": 816,
707
+ "Ġbel": 997,
708
+ "Ġbet": 649,
709
+ "Ġbetween": 712,
710
+ "Ġbl": 845,
711
+ "Ġboth": 861,
712
+ "Ġbu": 773,
713
+ "Ġbut": 449,
714
+ "Ġby": 311,
715
+ "Ġc": 216,
716
+ "Ġcall": 802,
717
+ "Ġcalled": 998,
718
+ "Ġcan": 688,
719
+ "Ġcent": 628,
720
+ "Ġcentury": 930,
721
+ "Ġch": 374,
722
+ "Ġchar": 716,
723
+ "Ġcharac": 882,
724
+ "Ġcl": 476,
725
+ "Ġco": 771,
726
+ "Ġcol": 717,
727
+ "Ġcom": 345,
728
+ "Ġcomm": 601,
729
+ "Ġcomp": 445,
730
+ "Ġcomple": 985,
731
+ "Ġcon": 317,
732
+ "Ġconc": 944,
733
+ "Ġcons": 664,
734
+ "Ġcont": 453,
735
+ "Ġcontin": 967,
736
+ "Ġcould": 994,
737
+ "Ġcre": 946,
738
+ "Ġcrit": 991,
739
+ "Ġd": 235,
740
+ "Ġday": 796,
741
+ "Ġde": 357,
742
+ "Ġdec": 675,
743
+ "Ġdef": 774,
744
+ "Ġdep": 901,
745
+ "Ġdes": 545,
746
+ "Ġdesc": 890,
747
+ "Ġdevelop": 938,
748
+ "Ġdid": 996,
749
+ "Ġdif": 966,
750
+ "Ġdirect": 974,
751
+ "Ġdis": 529,
752
+ "Ġdo": 808,
753
+ "Ġduring": 665,
754
+ "Ġe": 257,
755
+ "Ġear": 657,
756
+ "Ġearly": 993,
757
+ "Ġem": 897,
758
+ "Ġen": 558,
759
+ "Ġend": 730,
760
+ "Ġent": 825,
761
+ "Ġep": 819,
762
+ "Ġepis": 870,
763
+ "Ġest": 932,
764
+ "Ġev": 585,
765
+ "Ġex": 381,
766
+ "Ġexp": 879,
767
+ "Ġext": 976,
768
+ "Ġf": 218,
769
+ "Ġfe": 645,
770
+ "Ġfilm": 739,
771
+ "Ġfin": 590,
772
+ "Ġfirst": 459,
773
+ "Ġfl": 713,
774
+ "Ġfollow": 778,
775
+ "Ġfor": 278,
776
+ "Ġform": 744,
777
+ "Ġfound": 828,
778
+ "Ġfour": 788,
779
+ "Ġfrom": 344,
780
+ "Ġg": 271,
781
+ "Ġgame": 678,
782
+ "Ġgo": 888,
783
+ "Ġh": 236,
784
+ "Ġhad": 402,
785
+ "Ġhas": 503,
786
+ "Ġhave": 494,
787
+ "Ġhe": 335,
788
+ "Ġher": 472,
789
+ "Ġhigh": 827,
790
+ "Ġhim": 623,
791
+ "Ġhis": 346,
792
+ "Ġhist": 992,
793
+ "Ġim": 560,
794
+ "Ġin": 225,
795
+ "Ġinc": 443,
796
+ "Ġinclud": 569,
797
+ "Ġincluding": 871,
798
+ "Ġind": 789,
799
+ "Ġint": 454,
800
+ "Ġinter": 766,
801
+ "Ġinto": 591,
802
+ "Ġinv": 900,
803
+ "Ġis": 305,
804
+ "Ġit": 326,
805
+ "Ġits": 461,
806
+ "Ġj": 540,
807
+ "Ġk": 397,
808
+ "Ġkn": 660,
809
+ "Ġknown": 880,
810
+ "Ġl": 254,
811
+ "Ġlar": 772,
812
+ "Ġlater": 728,
813
+ "Ġle": 413,
814
+ "Ġlead": 954,
815
+ "Ġloc": 848,
816
+ "Ġlong": 912,
817
+ "Ġm": 234,
818
+ "Ġmade": 750,
819
+ "Ġmain": 910,
820
+ "Ġman": 541,
821
+ "Ġmany": 909,
822
+ "Ġmay": 981,
823
+ "Ġme": 705,
824
+ "Ġmet": 926,
825
+ "Ġmill": 959,
826
+ "Ġmin": 935,
827
+ "Ġmon": 908,
828
+ "Ġmore": 608,
829
+ "Ġmost": 663,
830
+ "Ġmov": 762,
831
+ "Ġmus": 777,
832
+ "Ġn": 258,
833
+ "Ġne": 711,
834
+ "Ġnew": 668,
835
+ "Ġno": 830,
836
+ "Ġnot": 414,
837
+ "Ġnum": 729,
838
+ "Ġnumber": 849,
839
+ "Ġo": 209,
840
+ "Ġob": 957,
841
+ "Ġof": 222,
842
+ "Ġoff": 559,
843
+ "Ġon": 267,
844
+ "Ġone": 500,
845
+ "Ġonly": 673,
846
+ "Ġop": 923,
847
+ "Ġor": 375,
848
+ "Ġorigin": 950,
849
+ "Ġother": 552,
850
+ "Ġout": 577,
851
+ "Ġover": 551,
852
+ "Ġp": 228,
853
+ "Ġpart": 544,
854
+ "Ġpe": 752,
855
+ "Ġper": 507,
856
+ "Ġperform": 893,
857
+ "Ġpl": 389,
858
+ "Ġplay": 539,
859
+ "Ġpo": 638,
860
+ "Ġpol": 980,
861
+ "Ġpop": 887,
862
+ "Ġpos": 733,
863
+ "Ġpr": 741,
864
+ "Ġpre": 581,
865
+ "Ġpres": 850,
866
+ "Ġpro": 348,
867
+ "Ġprodu": 735,
868
+ "Ġpubl": 801,
869
+ "Ġqu": 759,
870
+ "Ġr": 362,
871
+ "Ġra": 769,
872
+ "Ġre": 241,
873
+ "Ġrec": 493,
874
+ "Ġrece": 895,
875
+ "Ġrecord": 718,
876
+ "Ġreg": 743,
877
+ "Ġrel": 695,
878
+ "Ġrele": 738,
879
+ "Ġrem": 652,
880
+ "Ġrep": 943,
881
+ "Ġres": 488,
882
+ "Ġret": 755,
883
+ "Ġrev": 958,
884
+ "Ġro": 498,
885
+ "Ġs": 207,
886
+ "Ġsc": 522,
887
+ "Ġse": 363,
888
+ "Ġseason": 698,
889
+ "Ġsec": 648,
890
+ "Ġsecond": 786,
891
+ "Ġser": 557,
892
+ "Ġseries": 847,
893
+ "Ġset": 831,
894
+ "Ġsever": 859,
895
+ "Ġseveral": 955,
896
+ "Ġsh": 396,
897
+ "Ġshe": 602,
898
+ "Ġshow": 941,
899
+ "Ġsign": 968,
900
+ "Ġsing": 891,
901
+ "Ġsm": 951,
902
+ "Ġso": 753,
903
+ "Ġsome": 770,
904
+ "Ġsong": 651,
905
+ "Ġsp": 409,
906
+ "Ġspec": 757,
907
+ "Ġst": 289,
908
+ "Ġstud": 911,
909
+ "Ġsu": 359,
910
+ "Ġsub": 751,
911
+ "Ġsuch": 785,
912
+ "Ġsupp": 820,
913
+ "Ġsur": 837,
914
+ "Ġsy": 813,
915
+ "Ġt": 198,
916
+ "Ġte": 605,
917
+ "Ġteam": 931,
918
+ "Ġth": 248,
919
+ "Ġthan": 706,
920
+ "Ġthat": 299,
921
+ "Ġthe": 202,
922
+ "Ġtheir": 448,
923
+ "Ġthem": 646,
924
+ "Ġthen": 866,
925
+ "Ġthere": 821,
926
+ "Ġthey": 547,
927
+ "Ġthis": 530,
928
+ "Ġthree": 701,
929
+ "Ġthrough": 722,
930
+ "Ġtime": 586,
931
+ "Ġto": 231,
932
+ "Ġtr": 681,
933
+ "Ġtra": 840,
934
+ "Ġtrans": 881,
935
+ "Ġtwo": 510,
936
+ "Ġu": 427,
937
+ "Ġun": 438,
938
+ "Ġunder": 703,
939
+ "Ġup": 582,
940
+ "Ġus": 491,
941
+ "Ġused": 792,
942
+ "Ġv": 352,
943
+ "Ġver": 727,
944
+ "Ġw": 210,
945
+ "Ġwas": 262,
946
+ "Ġwe": 619,
947
+ "Ġwell": 877,
948
+ "Ġwere": 364,
949
+ "Ġwh": 309,
950
+ "Ġwhe": 464,
951
+ "Ġwhen": 650,
952
+ "Ġwhere": 760,
953
+ "Ġwhich": 404,
954
+ "Ġwhile": 736,
955
+ "Ġwho": 520,
956
+ "Ġwith": 300,
957
+ "Ġwork": 634,
958
+ "Ġwould": 606,
959
+ "Ġwrit": 734,
960
+ "Ġy": 411,
961
+ "Ġyear": 548,
962
+ "Ġyears": 822,
963
+ "Ġâ": 395,
964
+ "ĠâĢ": 400,
965
+ "ĠâĢĵ": 463,
966
+ "ĠâĢĶ": 883,
967
+ "ĠĊ": 256,
968
+ "Ģ": 164,
969
+ "ģ": 165,
970
+ "Ĥ": 166,
971
+ "ĥ": 167,
972
+ "Ħ": 168,
973
+ "ħ": 169,
974
+ "Ĩ": 170,
975
+ "ĩ": 171,
976
+ "Ī": 172,
977
+ "ī": 173,
978
+ "Ĭ": 174,
979
+ "ĭ": 175,
980
+ "Į": 176,
981
+ "į": 177,
982
+ "İ": 178,
983
+ "ı": 179,
984
+ "IJ": 180,
985
+ "ij": 181,
986
+ "Ĵ": 182,
987
+ "ĵ": 183,
988
+ "Ķ": 184,
989
+ "ķ": 185,
990
+ "ĸ": 186,
991
+ "Ĺ": 187,
992
+ "ĺ": 188,
993
+ "Ļ": 189,
994
+ "ļ": 190,
995
+ "Ľ": 191,
996
+ "ľ": 192,
997
+ "Ŀ": 193,
998
+ "ŀ": 194,
999
+ "Ł": 195,
1000
+ "ł": 196,
1001
+ "Ń": 197
1002
+ }
tokenizer_2/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
tokenizer_2/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
+ }
tokenizer_2/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 77,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
unet/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AudioLDM2UNet2DConditionModel",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": 8,
6
+ "block_out_channels": [
7
+ 8,
8
+ 16
9
+ ],
10
+ "class_embed_type": null,
11
+ "class_embeddings_concat": false,
12
+ "conv_in_kernel": 3,
13
+ "conv_out_kernel": 3,
14
+ "cross_attention_dim": [
15
+ 8,
16
+ 16
17
+ ],
18
+ "down_block_types": [
19
+ "DownBlock2D",
20
+ "CrossAttnDownBlock2D"
21
+ ],
22
+ "downsample_padding": 1,
23
+ "flip_sin_to_cos": true,
24
+ "freq_shift": 0,
25
+ "in_channels": 4,
26
+ "layers_per_block": 1,
27
+ "mid_block_scale_factor": 1,
28
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
29
+ "norm_eps": 1e-05,
30
+ "norm_num_groups": 8,
31
+ "num_attention_heads": null,
32
+ "num_class_embeds": null,
33
+ "only_cross_attention": false,
34
+ "out_channels": 4,
35
+ "projection_class_embeddings_input_dim": null,
36
+ "resnet_time_scale_shift": "default",
37
+ "sample_size": 32,
38
+ "time_cond_proj_dim": null,
39
+ "time_embedding_act_fn": null,
40
+ "time_embedding_dim": null,
41
+ "time_embedding_type": "positional",
42
+ "timestep_post_act": null,
43
+ "transformer_layers_per_block": 1,
44
+ "up_block_types": [
45
+ "CrossAttnUpBlock2D",
46
+ "UpBlock2D"
47
+ ],
48
+ "upcast_attention": false,
49
+ "use_linear_projection": false
50
+ }
unet/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bdf30e3217cfb45db2520c0f3f6312289d997399e7bfbc7287e78c2b0c2c3d
3
+ size 329462
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 8,
7
+ 16
8
+ ],
9
+ "down_block_types": [
10
+ "DownEncoderBlock2D",
11
+ "DownEncoderBlock2D"
12
+ ],
13
+ "force_upcast": true,
14
+ "in_channels": 1,
15
+ "latent_channels": 4,
16
+ "latents_mean": null,
17
+ "latents_std": null,
18
+ "layers_per_block": 1,
19
+ "mid_block_add_attention": true,
20
+ "norm_num_groups": 8,
21
+ "out_channels": 1,
22
+ "sample_size": 32,
23
+ "scaling_factor": 0.18215,
24
+ "shift_factor": null,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ],
29
+ "use_post_quant_conv": true,
30
+ "use_quant_conv": true
31
+ }
vae/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82278485227c838795e37f0fcd7e2bbf17dea7bb37bec688d820b112ec9c99c8
3
+ size 214586
vocoder/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechT5HifiGan"
4
+ ],
5
+ "initializer_range": 0.01,
6
+ "leaky_relu_slope": 0.1,
7
+ "model_in_dim": 8,
8
+ "model_type": "hifigan",
9
+ "normalize_before": false,
10
+ "resblock_dilation_sizes": [
11
+ [
12
+ 1,
13
+ 3,
14
+ 5
15
+ ],
16
+ [
17
+ 1,
18
+ 3,
19
+ 5
20
+ ]
21
+ ],
22
+ "resblock_kernel_sizes": [
23
+ 3,
24
+ 7
25
+ ],
26
+ "sampling_rate": 16000,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.50.0.dev0",
29
+ "upsample_initial_channel": 16,
30
+ "upsample_kernel_sizes": [
31
+ 4,
32
+ 4
33
+ ],
34
+ "upsample_rates": [
35
+ 2,
36
+ 2
37
+ ]
38
+ }
vocoder/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b03f9b0ae7cb86d98edb4b8ec0010c0edea8759cad27462cf612a1adcab25620
3
+ size 43602