codeShare commited on
Commit
abc0b46
1 Parent(s): 48606a6

Upload sd_token_similarity_calculator.ipynb

Browse files
Files changed (1) hide show
  1. sd_token_similarity_calculator.ipynb +2180 -193
sd_token_similarity_calculator.ipynb CHANGED
@@ -11,6 +11,1720 @@
11
  },
12
  "language_info": {
13
  "name": "python"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
15
  },
16
  "cells": [
@@ -67,13 +1781,34 @@
67
  " similarity_pcnt_aprox = round(similarity_pcnt, 3)\n",
68
  " result = f'{similarity_pcnt_aprox} %'\n",
69
  " return result\n",
70
- "#----#"
 
 
 
71
  ],
72
  "metadata": {
73
- "id": "Ch9puvwKH1s3"
 
 
 
 
74
  },
75
- "execution_count": null,
76
- "outputs": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  },
78
  {
79
  "cell_type": "code",
@@ -112,10 +1847,150 @@
112
  "_A = LA.vector_norm(A, ord=2)"
113
  ],
114
  "metadata": {
115
- "id": "RPdkYzT2_X85"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  },
117
- "execution_count": null,
118
- "outputs": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  },
120
  {
121
  "cell_type": "markdown",
@@ -130,7 +2005,7 @@
130
  "cell_type": "code",
131
  "source": [
132
  "mix_with = \"\" # @param {type:'string'}\n",
133
- "mix_method = 'None' # @param [\"None\" , \"Average\", \"Subtract\"] {allow-input: true}\n",
134
  "w = 0.5 # @param {type:\"slider\", min:0, max:1, step:0.01}\n",
135
  "\n",
136
  "\n",
@@ -156,7 +2031,7 @@
156
  "metadata": {
157
  "id": "oXbNSRSKPgRr"
158
  },
159
- "execution_count": 6,
160
  "outputs": []
161
  },
162
  {
@@ -191,10 +2066,22 @@
191
  " print(f'Calculated all cosine-similarities between the token {vocab[id_A]} with ID = {id_A} the rest of the {NUM_TOKENS} tokens as a 1x{sorted.shape[0]} tensor')"
192
  ],
193
  "metadata": {
194
- "id": "juxsvco9B0iV"
 
 
 
 
195
  },
196
- "execution_count": null,
197
- "outputs": []
 
 
 
 
 
 
 
 
198
  },
199
  {
200
  "cell_type": "markdown",
@@ -232,214 +2119,314 @@
232
  "base_uri": "https://localhost:8080/"
233
  },
234
  "collapsed": true,
235
- "outputId": "843fbd7c-b208-49e0-9793-69bb36622c27"
236
  },
237
- "execution_count": 5,
238
  "outputs": [
239
  {
240
  "output_type": "stream",
241
  "name": "stdout",
242
  "text": [
243
  "banana</w>\n",
244
- "similiarity = 74.26 %\n",
245
- "nude</w>\n",
246
- "similiarity = 72.49 %\n",
247
  "bananas</w>\n",
248
- "similiarity = 30.34 %\n",
249
- "nudes</w>\n",
250
- "similiarity = 27.19 %\n",
251
  "banan\n",
252
- "similiarity = 25.08 %\n",
 
253
  "ðŁįĮ</w>\n",
254
- "similiarity = 22.27 %\n",
255
- "naked</w>\n",
256
- "similiarity = 22.12 %\n",
257
- "orange</w>\n",
258
- "similiarity = 19.53 %\n",
259
- "cucumber</w>\n",
260
- "similiarity = 17.36 %\n",
261
- "nutella</w>\n",
262
- "similiarity = 17.33 %\n",
263
- "camel</w>\n",
264
- "similiarity = 17.22 %\n",
265
- "eggplant</w>\n",
266
- "similiarity = 17.13 %\n",
267
- "swimsuit</w>\n",
268
- "similiarity = 16.62 %\n",
269
  "chicken</w>\n",
270
- "similiarity = 16.38 %\n",
271
- "bikini</w>\n",
272
- "similiarity = 16.08 %\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
273
  "grape</w>\n",
274
- "similiarity = 16.01 %\n",
275
- "ballerina</w>\n",
276
- "similiarity = 16.01 %\n",
 
 
 
 
 
 
 
 
 
 
 
277
  "mango</w>\n",
278
- "similiarity = 16.0 %\n",
279
- "manicure</w>\n",
280
- "similiarity = 15.8 %\n",
281
- "pencil</w>\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
282
  "similiarity = 15.62 %\n",
283
- "yoga</w>\n",
284
- "similiarity = 15.56 %\n",
285
- "indian</w>\n",
286
- "similiarity = 15.51 %\n",
287
- "yellow</w>\n",
288
- "similiarity = 15.51 %\n",
289
- "venus</w>\n",
290
- "similiarity = 15.5 %\n",
291
- "snake</w>\n",
292
- "similiarity = 15.41 %\n",
293
- "dunk</w>\n",
294
- "similiarity = 15.39 %\n",
295
- "ters\n",
296
- "similiarity = 15.27 %\n",
297
- "underwear</w>\n",
298
- "similiarity = 15.26 %\n",
299
- "sunbathing</w>\n",
300
- "similiarity = 15.15 %\n",
301
  "potato</w>\n",
302
- "similiarity = 15.04 %\n",
303
- "milk</w>\n",
304
- "similiarity = 14.91 %\n",
305
- "bamboo</w>\n",
306
- "similiarity = 14.85 %\n",
307
- "selfie</w>\n",
308
- "similiarity = 14.85 %\n",
309
- "features</w>\n",
310
- "similiarity = 14.82 %\n",
311
- "know\n",
312
- "similiarity = 14.79 %\n",
313
- "oilpainting</w>\n",
314
- "similiarity = 14.7 %\n",
315
- "reas\n",
316
- "similiarity = 14.63 %\n",
317
  "croissant</w>\n",
318
- "similiarity = 14.61 %\n",
319
- "oranges</w>\n",
320
- "similiarity = 14.59 %\n",
321
- "conversation</w>\n",
322
- "similiarity = 14.57 %\n",
323
- "photoshoot</w>\n",
324
- "similiarity = 14.55 %\n",
325
- "ery\n",
326
- "similiarity = 14.49 %\n",
327
- "pear</w>\n",
328
- "similiarity = 14.42 %\n",
329
- "mcnam\n",
330
- "similiarity = 14.42 %\n",
331
- "dens</w>\n",
332
- "similiarity = 14.38 %\n",
333
- "cigarette</w>\n",
334
- "similiarity = 14.33 %\n",
335
- "tangerine</w>\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
336
  "similiarity = 14.3 %\n",
337
- "aluminum</w>\n",
338
- "similiarity = 14.28 %\n",
339
- "plum</w>\n",
340
- "similiarity = 14.28 %\n",
341
- "rape</w>\n",
342
- "similiarity = 14.24 %\n",
343
- "apple</w>\n",
344
- "similiarity = 14.2 %\n",
345
- "apd</w>\n",
346
- "similiarity = 14.17 %\n",
347
- "safari</w>\n",
348
  "similiarity = 14.09 %\n",
349
- "yolo</w>\n",
350
- "similiarity = 14.06 %\n",
351
- "hoodie</w>\n",
352
- "similiarity = 13.96 %\n",
353
- "cabaret</w>\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
354
  "similiarity = 13.91 %\n",
355
- "superman</w>\n",
 
356
  "similiarity = 13.9 %\n",
357
- "saree</w>\n",
358
- "similiarity = 13.86 %\n",
359
- "mommy</w>\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
360
  "similiarity = 13.78 %\n",
361
- "sausage</w>\n",
362
- "similiarity = 13.76 %\n",
363
- "marshmallow</w>\n",
364
- "similiarity = 13.75 %\n",
365
- "latex</w>\n",
366
- "similiarity = 13.74 %\n",
367
- "blonde</w>\n",
 
 
 
 
368
  "similiarity = 13.69 %\n",
369
- "champagne</w>\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
370
  "similiarity = 13.62 %\n",
371
- "parachute</w>\n",
372
- "similiarity = 13.61 %\n",
373
- "stor</w>\n",
 
 
 
 
 
 
 
 
 
 
 
374
  "similiarity = 13.58 %\n",
375
- "feminine</w>\n",
 
 
 
 
376
  "similiarity = 13.55 %\n",
377
- "ayu</w>\n",
378
- "similiarity = 13.5 %\n",
379
- "âĢ¼ï¸ı</w>\n",
 
 
 
 
 
 
 
 
380
  "similiarity = 13.45 %\n",
381
- "naked\n",
382
- "similiarity = 13.45 %\n",
383
- "poop</w>\n",
384
- "similiarity = 13.44 %\n",
385
- "honeymoon</w>\n",
386
- "similiarity = 13.41 %\n",
387
- "giraffe</w>\n",
388
- "similiarity = 13.37 %\n",
389
- "zebra</w>\n",
390
- "similiarity = 13.35 %\n",
391
- "mud</w>\n",
392
- "similiarity = 13.35 %\n",
393
- "blanket</w>\n",
394
- "similiarity = 13.34 %\n",
395
- "silly</w>\n",
396
- "similiarity = 13.32 %\n",
397
- "animal</w>\n",
398
- "similiarity = 13.31 %\n",
399
- "malayalam</w>\n",
400
- "similiarity = 13.25 %\n",
401
- "mustache</w>\n",
402
- "similiarity = 13.25 %\n",
403
- "mrc</w>\n",
404
- "similiarity = 13.24 %\n",
405
- "yuri</w>\n",
406
- "similiarity = 13.23 %\n",
407
- "japanese</w>\n",
408
- "similiarity = 13.19 %\n",
409
- "gibbs</w>\n",
410
- "similiarity = 13.16 %\n",
411
- "ðŁĻĤ\n",
412
- "similiarity = 13.15 %\n",
413
- "rhubarb</w>\n",
414
- "similiarity = 13.14 %\n",
415
- "trac\n",
416
- "similiarity = 13.13 %\n",
417
- "polaroid</w>\n",
418
- "similiarity = 13.08 %\n",
419
- "lunch</w>\n",
420
- "similiarity = 13.04 %\n",
421
- "sandal</w>\n",
422
- "similiarity = 13.03 %\n",
423
- "popart</w>\n",
424
- "similiarity = 13.02 %\n",
425
- "kissing</w>\n",
426
- "similiarity = 13.02 %\n",
427
- "funeral</w>\n",
428
- "similiarity = 13.02 %\n",
429
- "runway</w>\n",
430
- "similiarity = 13.01 %\n",
431
- "milk\n",
432
- "similiarity = 12.98 %\n",
433
- "tutu</w>\n",
434
- "similiarity = 12.96 %\n",
435
- "flag</w>\n",
436
- "similiarity = 12.95 %\n",
437
- "hours</w>\n",
438
- "similiarity = 12.95 %\n",
439
  "monet</w>\n",
440
- "similiarity = 12.91 %\n",
441
- "ali</w>\n",
442
- "similiarity = 12.89 %\n"
443
  ]
444
  }
445
  ]
 
11
  },
12
  "language_info": {
13
  "name": "python"
14
+ },
15
+ "widgets": {
16
+ "application/vnd.jupyter.widget-state+json": {
17
+ "7b073d9c166a45539c651ecd0b27285c": {
18
+ "model_module": "@jupyter-widgets/controls",
19
+ "model_name": "HBoxModel",
20
+ "model_module_version": "1.5.0",
21
+ "state": {
22
+ "_dom_classes": [],
23
+ "_model_module": "@jupyter-widgets/controls",
24
+ "_model_module_version": "1.5.0",
25
+ "_model_name": "HBoxModel",
26
+ "_view_count": null,
27
+ "_view_module": "@jupyter-widgets/controls",
28
+ "_view_module_version": "1.5.0",
29
+ "_view_name": "HBoxView",
30
+ "box_style": "",
31
+ "children": [
32
+ "IPY_MODEL_ffba5f49ba214984b8329b4e06e40dcf",
33
+ "IPY_MODEL_e69b98b68527488cbb7c1ee5f6011a92",
34
+ "IPY_MODEL_983145e29ab84636b1e266c73eeb6889"
35
+ ],
36
+ "layout": "IPY_MODEL_278c2c021faf4f2696c03070fc3511bf"
37
+ }
38
+ },
39
+ "ffba5f49ba214984b8329b4e06e40dcf": {
40
+ "model_module": "@jupyter-widgets/controls",
41
+ "model_name": "HTMLModel",
42
+ "model_module_version": "1.5.0",
43
+ "state": {
44
+ "_dom_classes": [],
45
+ "_model_module": "@jupyter-widgets/controls",
46
+ "_model_module_version": "1.5.0",
47
+ "_model_name": "HTMLModel",
48
+ "_view_count": null,
49
+ "_view_module": "@jupyter-widgets/controls",
50
+ "_view_module_version": "1.5.0",
51
+ "_view_name": "HTMLView",
52
+ "description": "",
53
+ "description_tooltip": null,
54
+ "layout": "IPY_MODEL_3e9df4ac699843df8ae361aba1337b06",
55
+ "placeholder": "​",
56
+ "style": "IPY_MODEL_8e9cc6914fc14e56945716902fb11fe9",
57
+ "value": "tokenizer_config.json: 100%"
58
+ }
59
+ },
60
+ "e69b98b68527488cbb7c1ee5f6011a92": {
61
+ "model_module": "@jupyter-widgets/controls",
62
+ "model_name": "FloatProgressModel",
63
+ "model_module_version": "1.5.0",
64
+ "state": {
65
+ "_dom_classes": [],
66
+ "_model_module": "@jupyter-widgets/controls",
67
+ "_model_module_version": "1.5.0",
68
+ "_model_name": "FloatProgressModel",
69
+ "_view_count": null,
70
+ "_view_module": "@jupyter-widgets/controls",
71
+ "_view_module_version": "1.5.0",
72
+ "_view_name": "ProgressView",
73
+ "bar_style": "success",
74
+ "description": "",
75
+ "description_tooltip": null,
76
+ "layout": "IPY_MODEL_0ca945d6f8a5457d9706c211869983c8",
77
+ "max": 905,
78
+ "min": 0,
79
+ "orientation": "horizontal",
80
+ "style": "IPY_MODEL_69cf2c7a4ecf4c3188586c86c7056518",
81
+ "value": 905
82
+ }
83
+ },
84
+ "983145e29ab84636b1e266c73eeb6889": {
85
+ "model_module": "@jupyter-widgets/controls",
86
+ "model_name": "HTMLModel",
87
+ "model_module_version": "1.5.0",
88
+ "state": {
89
+ "_dom_classes": [],
90
+ "_model_module": "@jupyter-widgets/controls",
91
+ "_model_module_version": "1.5.0",
92
+ "_model_name": "HTMLModel",
93
+ "_view_count": null,
94
+ "_view_module": "@jupyter-widgets/controls",
95
+ "_view_module_version": "1.5.0",
96
+ "_view_name": "HTMLView",
97
+ "description": "",
98
+ "description_tooltip": null,
99
+ "layout": "IPY_MODEL_1d60ac5b02de4cc7b0d51ed57165ff64",
100
+ "placeholder": "​",
101
+ "style": "IPY_MODEL_e34074fc893d47b8bf75a8089cd8df37",
102
+ "value": " 905/905 [00:00&lt;00:00, 32.4kB/s]"
103
+ }
104
+ },
105
+ "278c2c021faf4f2696c03070fc3511bf": {
106
+ "model_module": "@jupyter-widgets/base",
107
+ "model_name": "LayoutModel",
108
+ "model_module_version": "1.2.0",
109
+ "state": {
110
+ "_model_module": "@jupyter-widgets/base",
111
+ "_model_module_version": "1.2.0",
112
+ "_model_name": "LayoutModel",
113
+ "_view_count": null,
114
+ "_view_module": "@jupyter-widgets/base",
115
+ "_view_module_version": "1.2.0",
116
+ "_view_name": "LayoutView",
117
+ "align_content": null,
118
+ "align_items": null,
119
+ "align_self": null,
120
+ "border": null,
121
+ "bottom": null,
122
+ "display": null,
123
+ "flex": null,
124
+ "flex_flow": null,
125
+ "grid_area": null,
126
+ "grid_auto_columns": null,
127
+ "grid_auto_flow": null,
128
+ "grid_auto_rows": null,
129
+ "grid_column": null,
130
+ "grid_gap": null,
131
+ "grid_row": null,
132
+ "grid_template_areas": null,
133
+ "grid_template_columns": null,
134
+ "grid_template_rows": null,
135
+ "height": null,
136
+ "justify_content": null,
137
+ "justify_items": null,
138
+ "left": null,
139
+ "margin": null,
140
+ "max_height": null,
141
+ "max_width": null,
142
+ "min_height": null,
143
+ "min_width": null,
144
+ "object_fit": null,
145
+ "object_position": null,
146
+ "order": null,
147
+ "overflow": null,
148
+ "overflow_x": null,
149
+ "overflow_y": null,
150
+ "padding": null,
151
+ "right": null,
152
+ "top": null,
153
+ "visibility": null,
154
+ "width": null
155
+ }
156
+ },
157
+ "3e9df4ac699843df8ae361aba1337b06": {
158
+ "model_module": "@jupyter-widgets/base",
159
+ "model_name": "LayoutModel",
160
+ "model_module_version": "1.2.0",
161
+ "state": {
162
+ "_model_module": "@jupyter-widgets/base",
163
+ "_model_module_version": "1.2.0",
164
+ "_model_name": "LayoutModel",
165
+ "_view_count": null,
166
+ "_view_module": "@jupyter-widgets/base",
167
+ "_view_module_version": "1.2.0",
168
+ "_view_name": "LayoutView",
169
+ "align_content": null,
170
+ "align_items": null,
171
+ "align_self": null,
172
+ "border": null,
173
+ "bottom": null,
174
+ "display": null,
175
+ "flex": null,
176
+ "flex_flow": null,
177
+ "grid_area": null,
178
+ "grid_auto_columns": null,
179
+ "grid_auto_flow": null,
180
+ "grid_auto_rows": null,
181
+ "grid_column": null,
182
+ "grid_gap": null,
183
+ "grid_row": null,
184
+ "grid_template_areas": null,
185
+ "grid_template_columns": null,
186
+ "grid_template_rows": null,
187
+ "height": null,
188
+ "justify_content": null,
189
+ "justify_items": null,
190
+ "left": null,
191
+ "margin": null,
192
+ "max_height": null,
193
+ "max_width": null,
194
+ "min_height": null,
195
+ "min_width": null,
196
+ "object_fit": null,
197
+ "object_position": null,
198
+ "order": null,
199
+ "overflow": null,
200
+ "overflow_x": null,
201
+ "overflow_y": null,
202
+ "padding": null,
203
+ "right": null,
204
+ "top": null,
205
+ "visibility": null,
206
+ "width": null
207
+ }
208
+ },
209
+ "8e9cc6914fc14e56945716902fb11fe9": {
210
+ "model_module": "@jupyter-widgets/controls",
211
+ "model_name": "DescriptionStyleModel",
212
+ "model_module_version": "1.5.0",
213
+ "state": {
214
+ "_model_module": "@jupyter-widgets/controls",
215
+ "_model_module_version": "1.5.0",
216
+ "_model_name": "DescriptionStyleModel",
217
+ "_view_count": null,
218
+ "_view_module": "@jupyter-widgets/base",
219
+ "_view_module_version": "1.2.0",
220
+ "_view_name": "StyleView",
221
+ "description_width": ""
222
+ }
223
+ },
224
+ "0ca945d6f8a5457d9706c211869983c8": {
225
+ "model_module": "@jupyter-widgets/base",
226
+ "model_name": "LayoutModel",
227
+ "model_module_version": "1.2.0",
228
+ "state": {
229
+ "_model_module": "@jupyter-widgets/base",
230
+ "_model_module_version": "1.2.0",
231
+ "_model_name": "LayoutModel",
232
+ "_view_count": null,
233
+ "_view_module": "@jupyter-widgets/base",
234
+ "_view_module_version": "1.2.0",
235
+ "_view_name": "LayoutView",
236
+ "align_content": null,
237
+ "align_items": null,
238
+ "align_self": null,
239
+ "border": null,
240
+ "bottom": null,
241
+ "display": null,
242
+ "flex": null,
243
+ "flex_flow": null,
244
+ "grid_area": null,
245
+ "grid_auto_columns": null,
246
+ "grid_auto_flow": null,
247
+ "grid_auto_rows": null,
248
+ "grid_column": null,
249
+ "grid_gap": null,
250
+ "grid_row": null,
251
+ "grid_template_areas": null,
252
+ "grid_template_columns": null,
253
+ "grid_template_rows": null,
254
+ "height": null,
255
+ "justify_content": null,
256
+ "justify_items": null,
257
+ "left": null,
258
+ "margin": null,
259
+ "max_height": null,
260
+ "max_width": null,
261
+ "min_height": null,
262
+ "min_width": null,
263
+ "object_fit": null,
264
+ "object_position": null,
265
+ "order": null,
266
+ "overflow": null,
267
+ "overflow_x": null,
268
+ "overflow_y": null,
269
+ "padding": null,
270
+ "right": null,
271
+ "top": null,
272
+ "visibility": null,
273
+ "width": null
274
+ }
275
+ },
276
+ "69cf2c7a4ecf4c3188586c86c7056518": {
277
+ "model_module": "@jupyter-widgets/controls",
278
+ "model_name": "ProgressStyleModel",
279
+ "model_module_version": "1.5.0",
280
+ "state": {
281
+ "_model_module": "@jupyter-widgets/controls",
282
+ "_model_module_version": "1.5.0",
283
+ "_model_name": "ProgressStyleModel",
284
+ "_view_count": null,
285
+ "_view_module": "@jupyter-widgets/base",
286
+ "_view_module_version": "1.2.0",
287
+ "_view_name": "StyleView",
288
+ "bar_color": null,
289
+ "description_width": ""
290
+ }
291
+ },
292
+ "1d60ac5b02de4cc7b0d51ed57165ff64": {
293
+ "model_module": "@jupyter-widgets/base",
294
+ "model_name": "LayoutModel",
295
+ "model_module_version": "1.2.0",
296
+ "state": {
297
+ "_model_module": "@jupyter-widgets/base",
298
+ "_model_module_version": "1.2.0",
299
+ "_model_name": "LayoutModel",
300
+ "_view_count": null,
301
+ "_view_module": "@jupyter-widgets/base",
302
+ "_view_module_version": "1.2.0",
303
+ "_view_name": "LayoutView",
304
+ "align_content": null,
305
+ "align_items": null,
306
+ "align_self": null,
307
+ "border": null,
308
+ "bottom": null,
309
+ "display": null,
310
+ "flex": null,
311
+ "flex_flow": null,
312
+ "grid_area": null,
313
+ "grid_auto_columns": null,
314
+ "grid_auto_flow": null,
315
+ "grid_auto_rows": null,
316
+ "grid_column": null,
317
+ "grid_gap": null,
318
+ "grid_row": null,
319
+ "grid_template_areas": null,
320
+ "grid_template_columns": null,
321
+ "grid_template_rows": null,
322
+ "height": null,
323
+ "justify_content": null,
324
+ "justify_items": null,
325
+ "left": null,
326
+ "margin": null,
327
+ "max_height": null,
328
+ "max_width": null,
329
+ "min_height": null,
330
+ "min_width": null,
331
+ "object_fit": null,
332
+ "object_position": null,
333
+ "order": null,
334
+ "overflow": null,
335
+ "overflow_x": null,
336
+ "overflow_y": null,
337
+ "padding": null,
338
+ "right": null,
339
+ "top": null,
340
+ "visibility": null,
341
+ "width": null
342
+ }
343
+ },
344
+ "e34074fc893d47b8bf75a8089cd8df37": {
345
+ "model_module": "@jupyter-widgets/controls",
346
+ "model_name": "DescriptionStyleModel",
347
+ "model_module_version": "1.5.0",
348
+ "state": {
349
+ "_model_module": "@jupyter-widgets/controls",
350
+ "_model_module_version": "1.5.0",
351
+ "_model_name": "DescriptionStyleModel",
352
+ "_view_count": null,
353
+ "_view_module": "@jupyter-widgets/base",
354
+ "_view_module_version": "1.2.0",
355
+ "_view_name": "StyleView",
356
+ "description_width": ""
357
+ }
358
+ },
359
+ "26cb34af09544ea1b17526891fd319e3": {
360
+ "model_module": "@jupyter-widgets/controls",
361
+ "model_name": "HBoxModel",
362
+ "model_module_version": "1.5.0",
363
+ "state": {
364
+ "_dom_classes": [],
365
+ "_model_module": "@jupyter-widgets/controls",
366
+ "_model_module_version": "1.5.0",
367
+ "_model_name": "HBoxModel",
368
+ "_view_count": null,
369
+ "_view_module": "@jupyter-widgets/controls",
370
+ "_view_module_version": "1.5.0",
371
+ "_view_name": "HBoxView",
372
+ "box_style": "",
373
+ "children": [
374
+ "IPY_MODEL_71627d67c8ec4993a8b1e4a93d53e8db",
375
+ "IPY_MODEL_ec11e5b722dd4d69bcd758775edd61b6",
376
+ "IPY_MODEL_63f760d16a1249b6a80f7a73989299ac"
377
+ ],
378
+ "layout": "IPY_MODEL_ba3dae52e6bc4a48945ebde7464a5277"
379
+ }
380
+ },
381
+ "71627d67c8ec4993a8b1e4a93d53e8db": {
382
+ "model_module": "@jupyter-widgets/controls",
383
+ "model_name": "HTMLModel",
384
+ "model_module_version": "1.5.0",
385
+ "state": {
386
+ "_dom_classes": [],
387
+ "_model_module": "@jupyter-widgets/controls",
388
+ "_model_module_version": "1.5.0",
389
+ "_model_name": "HTMLModel",
390
+ "_view_count": null,
391
+ "_view_module": "@jupyter-widgets/controls",
392
+ "_view_module_version": "1.5.0",
393
+ "_view_name": "HTMLView",
394
+ "description": "",
395
+ "description_tooltip": null,
396
+ "layout": "IPY_MODEL_e914f0b293b4410a82e02f990b8a9a1d",
397
+ "placeholder": "​",
398
+ "style": "IPY_MODEL_7e18f5165da84f60bea9d9a1819e17df",
399
+ "value": "vocab.json: 100%"
400
+ }
401
+ },
402
+ "ec11e5b722dd4d69bcd758775edd61b6": {
403
+ "model_module": "@jupyter-widgets/controls",
404
+ "model_name": "FloatProgressModel",
405
+ "model_module_version": "1.5.0",
406
+ "state": {
407
+ "_dom_classes": [],
408
+ "_model_module": "@jupyter-widgets/controls",
409
+ "_model_module_version": "1.5.0",
410
+ "_model_name": "FloatProgressModel",
411
+ "_view_count": null,
412
+ "_view_module": "@jupyter-widgets/controls",
413
+ "_view_module_version": "1.5.0",
414
+ "_view_name": "ProgressView",
415
+ "bar_style": "success",
416
+ "description": "",
417
+ "description_tooltip": null,
418
+ "layout": "IPY_MODEL_ba1b3dc7d77b4fee9addea98f60277bc",
419
+ "max": 961143,
420
+ "min": 0,
421
+ "orientation": "horizontal",
422
+ "style": "IPY_MODEL_b40d206858bd46e19ef99aa1de302060",
423
+ "value": 961143
424
+ }
425
+ },
426
+ "63f760d16a1249b6a80f7a73989299ac": {
427
+ "model_module": "@jupyter-widgets/controls",
428
+ "model_name": "HTMLModel",
429
+ "model_module_version": "1.5.0",
430
+ "state": {
431
+ "_dom_classes": [],
432
+ "_model_module": "@jupyter-widgets/controls",
433
+ "_model_module_version": "1.5.0",
434
+ "_model_name": "HTMLModel",
435
+ "_view_count": null,
436
+ "_view_module": "@jupyter-widgets/controls",
437
+ "_view_module_version": "1.5.0",
438
+ "_view_name": "HTMLView",
439
+ "description": "",
440
+ "description_tooltip": null,
441
+ "layout": "IPY_MODEL_92113b912eea41b4b2bfadd3f65cd835",
442
+ "placeholder": "​",
443
+ "style": "IPY_MODEL_bfca51dacc6a4762810309006fc6eca5",
444
+ "value": " 961k/961k [00:00&lt;00:00, 5.41MB/s]"
445
+ }
446
+ },
447
+ "ba3dae52e6bc4a48945ebde7464a5277": {
448
+ "model_module": "@jupyter-widgets/base",
449
+ "model_name": "LayoutModel",
450
+ "model_module_version": "1.2.0",
451
+ "state": {
452
+ "_model_module": "@jupyter-widgets/base",
453
+ "_model_module_version": "1.2.0",
454
+ "_model_name": "LayoutModel",
455
+ "_view_count": null,
456
+ "_view_module": "@jupyter-widgets/base",
457
+ "_view_module_version": "1.2.0",
458
+ "_view_name": "LayoutView",
459
+ "align_content": null,
460
+ "align_items": null,
461
+ "align_self": null,
462
+ "border": null,
463
+ "bottom": null,
464
+ "display": null,
465
+ "flex": null,
466
+ "flex_flow": null,
467
+ "grid_area": null,
468
+ "grid_auto_columns": null,
469
+ "grid_auto_flow": null,
470
+ "grid_auto_rows": null,
471
+ "grid_column": null,
472
+ "grid_gap": null,
473
+ "grid_row": null,
474
+ "grid_template_areas": null,
475
+ "grid_template_columns": null,
476
+ "grid_template_rows": null,
477
+ "height": null,
478
+ "justify_content": null,
479
+ "justify_items": null,
480
+ "left": null,
481
+ "margin": null,
482
+ "max_height": null,
483
+ "max_width": null,
484
+ "min_height": null,
485
+ "min_width": null,
486
+ "object_fit": null,
487
+ "object_position": null,
488
+ "order": null,
489
+ "overflow": null,
490
+ "overflow_x": null,
491
+ "overflow_y": null,
492
+ "padding": null,
493
+ "right": null,
494
+ "top": null,
495
+ "visibility": null,
496
+ "width": null
497
+ }
498
+ },
499
+ "e914f0b293b4410a82e02f990b8a9a1d": {
500
+ "model_module": "@jupyter-widgets/base",
501
+ "model_name": "LayoutModel",
502
+ "model_module_version": "1.2.0",
503
+ "state": {
504
+ "_model_module": "@jupyter-widgets/base",
505
+ "_model_module_version": "1.2.0",
506
+ "_model_name": "LayoutModel",
507
+ "_view_count": null,
508
+ "_view_module": "@jupyter-widgets/base",
509
+ "_view_module_version": "1.2.0",
510
+ "_view_name": "LayoutView",
511
+ "align_content": null,
512
+ "align_items": null,
513
+ "align_self": null,
514
+ "border": null,
515
+ "bottom": null,
516
+ "display": null,
517
+ "flex": null,
518
+ "flex_flow": null,
519
+ "grid_area": null,
520
+ "grid_auto_columns": null,
521
+ "grid_auto_flow": null,
522
+ "grid_auto_rows": null,
523
+ "grid_column": null,
524
+ "grid_gap": null,
525
+ "grid_row": null,
526
+ "grid_template_areas": null,
527
+ "grid_template_columns": null,
528
+ "grid_template_rows": null,
529
+ "height": null,
530
+ "justify_content": null,
531
+ "justify_items": null,
532
+ "left": null,
533
+ "margin": null,
534
+ "max_height": null,
535
+ "max_width": null,
536
+ "min_height": null,
537
+ "min_width": null,
538
+ "object_fit": null,
539
+ "object_position": null,
540
+ "order": null,
541
+ "overflow": null,
542
+ "overflow_x": null,
543
+ "overflow_y": null,
544
+ "padding": null,
545
+ "right": null,
546
+ "top": null,
547
+ "visibility": null,
548
+ "width": null
549
+ }
550
+ },
551
+ "7e18f5165da84f60bea9d9a1819e17df": {
552
+ "model_module": "@jupyter-widgets/controls",
553
+ "model_name": "DescriptionStyleModel",
554
+ "model_module_version": "1.5.0",
555
+ "state": {
556
+ "_model_module": "@jupyter-widgets/controls",
557
+ "_model_module_version": "1.5.0",
558
+ "_model_name": "DescriptionStyleModel",
559
+ "_view_count": null,
560
+ "_view_module": "@jupyter-widgets/base",
561
+ "_view_module_version": "1.2.0",
562
+ "_view_name": "StyleView",
563
+ "description_width": ""
564
+ }
565
+ },
566
+ "ba1b3dc7d77b4fee9addea98f60277bc": {
567
+ "model_module": "@jupyter-widgets/base",
568
+ "model_name": "LayoutModel",
569
+ "model_module_version": "1.2.0",
570
+ "state": {
571
+ "_model_module": "@jupyter-widgets/base",
572
+ "_model_module_version": "1.2.0",
573
+ "_model_name": "LayoutModel",
574
+ "_view_count": null,
575
+ "_view_module": "@jupyter-widgets/base",
576
+ "_view_module_version": "1.2.0",
577
+ "_view_name": "LayoutView",
578
+ "align_content": null,
579
+ "align_items": null,
580
+ "align_self": null,
581
+ "border": null,
582
+ "bottom": null,
583
+ "display": null,
584
+ "flex": null,
585
+ "flex_flow": null,
586
+ "grid_area": null,
587
+ "grid_auto_columns": null,
588
+ "grid_auto_flow": null,
589
+ "grid_auto_rows": null,
590
+ "grid_column": null,
591
+ "grid_gap": null,
592
+ "grid_row": null,
593
+ "grid_template_areas": null,
594
+ "grid_template_columns": null,
595
+ "grid_template_rows": null,
596
+ "height": null,
597
+ "justify_content": null,
598
+ "justify_items": null,
599
+ "left": null,
600
+ "margin": null,
601
+ "max_height": null,
602
+ "max_width": null,
603
+ "min_height": null,
604
+ "min_width": null,
605
+ "object_fit": null,
606
+ "object_position": null,
607
+ "order": null,
608
+ "overflow": null,
609
+ "overflow_x": null,
610
+ "overflow_y": null,
611
+ "padding": null,
612
+ "right": null,
613
+ "top": null,
614
+ "visibility": null,
615
+ "width": null
616
+ }
617
+ },
618
+ "b40d206858bd46e19ef99aa1de302060": {
619
+ "model_module": "@jupyter-widgets/controls",
620
+ "model_name": "ProgressStyleModel",
621
+ "model_module_version": "1.5.0",
622
+ "state": {
623
+ "_model_module": "@jupyter-widgets/controls",
624
+ "_model_module_version": "1.5.0",
625
+ "_model_name": "ProgressStyleModel",
626
+ "_view_count": null,
627
+ "_view_module": "@jupyter-widgets/base",
628
+ "_view_module_version": "1.2.0",
629
+ "_view_name": "StyleView",
630
+ "bar_color": null,
631
+ "description_width": ""
632
+ }
633
+ },
634
+ "92113b912eea41b4b2bfadd3f65cd835": {
635
+ "model_module": "@jupyter-widgets/base",
636
+ "model_name": "LayoutModel",
637
+ "model_module_version": "1.2.0",
638
+ "state": {
639
+ "_model_module": "@jupyter-widgets/base",
640
+ "_model_module_version": "1.2.0",
641
+ "_model_name": "LayoutModel",
642
+ "_view_count": null,
643
+ "_view_module": "@jupyter-widgets/base",
644
+ "_view_module_version": "1.2.0",
645
+ "_view_name": "LayoutView",
646
+ "align_content": null,
647
+ "align_items": null,
648
+ "align_self": null,
649
+ "border": null,
650
+ "bottom": null,
651
+ "display": null,
652
+ "flex": null,
653
+ "flex_flow": null,
654
+ "grid_area": null,
655
+ "grid_auto_columns": null,
656
+ "grid_auto_flow": null,
657
+ "grid_auto_rows": null,
658
+ "grid_column": null,
659
+ "grid_gap": null,
660
+ "grid_row": null,
661
+ "grid_template_areas": null,
662
+ "grid_template_columns": null,
663
+ "grid_template_rows": null,
664
+ "height": null,
665
+ "justify_content": null,
666
+ "justify_items": null,
667
+ "left": null,
668
+ "margin": null,
669
+ "max_height": null,
670
+ "max_width": null,
671
+ "min_height": null,
672
+ "min_width": null,
673
+ "object_fit": null,
674
+ "object_position": null,
675
+ "order": null,
676
+ "overflow": null,
677
+ "overflow_x": null,
678
+ "overflow_y": null,
679
+ "padding": null,
680
+ "right": null,
681
+ "top": null,
682
+ "visibility": null,
683
+ "width": null
684
+ }
685
+ },
686
+ "bfca51dacc6a4762810309006fc6eca5": {
687
+ "model_module": "@jupyter-widgets/controls",
688
+ "model_name": "DescriptionStyleModel",
689
+ "model_module_version": "1.5.0",
690
+ "state": {
691
+ "_model_module": "@jupyter-widgets/controls",
692
+ "_model_module_version": "1.5.0",
693
+ "_model_name": "DescriptionStyleModel",
694
+ "_view_count": null,
695
+ "_view_module": "@jupyter-widgets/base",
696
+ "_view_module_version": "1.2.0",
697
+ "_view_name": "StyleView",
698
+ "description_width": ""
699
+ }
700
+ },
701
+ "a7a66681148748ae94788ee276925bec": {
702
+ "model_module": "@jupyter-widgets/controls",
703
+ "model_name": "HBoxModel",
704
+ "model_module_version": "1.5.0",
705
+ "state": {
706
+ "_dom_classes": [],
707
+ "_model_module": "@jupyter-widgets/controls",
708
+ "_model_module_version": "1.5.0",
709
+ "_model_name": "HBoxModel",
710
+ "_view_count": null,
711
+ "_view_module": "@jupyter-widgets/controls",
712
+ "_view_module_version": "1.5.0",
713
+ "_view_name": "HBoxView",
714
+ "box_style": "",
715
+ "children": [
716
+ "IPY_MODEL_438a2db97b8649cfbd5b6d87aeb4b13a",
717
+ "IPY_MODEL_8608253bb3cc4e93a379b05648e1e35c",
718
+ "IPY_MODEL_aa84ccf805b3476ea155e64ed31edef6"
719
+ ],
720
+ "layout": "IPY_MODEL_851b1acc7d524ec1aabb04012c469432"
721
+ }
722
+ },
723
+ "438a2db97b8649cfbd5b6d87aeb4b13a": {
724
+ "model_module": "@jupyter-widgets/controls",
725
+ "model_name": "HTMLModel",
726
+ "model_module_version": "1.5.0",
727
+ "state": {
728
+ "_dom_classes": [],
729
+ "_model_module": "@jupyter-widgets/controls",
730
+ "_model_module_version": "1.5.0",
731
+ "_model_name": "HTMLModel",
732
+ "_view_count": null,
733
+ "_view_module": "@jupyter-widgets/controls",
734
+ "_view_module_version": "1.5.0",
735
+ "_view_name": "HTMLView",
736
+ "description": "",
737
+ "description_tooltip": null,
738
+ "layout": "IPY_MODEL_2277a0b29cd841a2a1ad5526f39c28a6",
739
+ "placeholder": "​",
740
+ "style": "IPY_MODEL_5f7a4ea2308d4cb2b6e4a0f2f925e2b1",
741
+ "value": "merges.txt: 100%"
742
+ }
743
+ },
744
+ "8608253bb3cc4e93a379b05648e1e35c": {
745
+ "model_module": "@jupyter-widgets/controls",
746
+ "model_name": "FloatProgressModel",
747
+ "model_module_version": "1.5.0",
748
+ "state": {
749
+ "_dom_classes": [],
750
+ "_model_module": "@jupyter-widgets/controls",
751
+ "_model_module_version": "1.5.0",
752
+ "_model_name": "FloatProgressModel",
753
+ "_view_count": null,
754
+ "_view_module": "@jupyter-widgets/controls",
755
+ "_view_module_version": "1.5.0",
756
+ "_view_name": "ProgressView",
757
+ "bar_style": "success",
758
+ "description": "",
759
+ "description_tooltip": null,
760
+ "layout": "IPY_MODEL_dc23a6ac81894fe484247273be9d6a83",
761
+ "max": 524619,
762
+ "min": 0,
763
+ "orientation": "horizontal",
764
+ "style": "IPY_MODEL_d37f42e8924a4b0fafd2e407b1db865b",
765
+ "value": 524619
766
+ }
767
+ },
768
+ "aa84ccf805b3476ea155e64ed31edef6": {
769
+ "model_module": "@jupyter-widgets/controls",
770
+ "model_name": "HTMLModel",
771
+ "model_module_version": "1.5.0",
772
+ "state": {
773
+ "_dom_classes": [],
774
+ "_model_module": "@jupyter-widgets/controls",
775
+ "_model_module_version": "1.5.0",
776
+ "_model_name": "HTMLModel",
777
+ "_view_count": null,
778
+ "_view_module": "@jupyter-widgets/controls",
779
+ "_view_module_version": "1.5.0",
780
+ "_view_name": "HTMLView",
781
+ "description": "",
782
+ "description_tooltip": null,
783
+ "layout": "IPY_MODEL_03fa9da8e5084d688bc7b0f4d8ba3fb5",
784
+ "placeholder": "​",
785
+ "style": "IPY_MODEL_613fa346a05441828356976ea941a7c7",
786
+ "value": " 525k/525k [00:00&lt;00:00, 13.6MB/s]"
787
+ }
788
+ },
789
+ "851b1acc7d524ec1aabb04012c469432": {
790
+ "model_module": "@jupyter-widgets/base",
791
+ "model_name": "LayoutModel",
792
+ "model_module_version": "1.2.0",
793
+ "state": {
794
+ "_model_module": "@jupyter-widgets/base",
795
+ "_model_module_version": "1.2.0",
796
+ "_model_name": "LayoutModel",
797
+ "_view_count": null,
798
+ "_view_module": "@jupyter-widgets/base",
799
+ "_view_module_version": "1.2.0",
800
+ "_view_name": "LayoutView",
801
+ "align_content": null,
802
+ "align_items": null,
803
+ "align_self": null,
804
+ "border": null,
805
+ "bottom": null,
806
+ "display": null,
807
+ "flex": null,
808
+ "flex_flow": null,
809
+ "grid_area": null,
810
+ "grid_auto_columns": null,
811
+ "grid_auto_flow": null,
812
+ "grid_auto_rows": null,
813
+ "grid_column": null,
814
+ "grid_gap": null,
815
+ "grid_row": null,
816
+ "grid_template_areas": null,
817
+ "grid_template_columns": null,
818
+ "grid_template_rows": null,
819
+ "height": null,
820
+ "justify_content": null,
821
+ "justify_items": null,
822
+ "left": null,
823
+ "margin": null,
824
+ "max_height": null,
825
+ "max_width": null,
826
+ "min_height": null,
827
+ "min_width": null,
828
+ "object_fit": null,
829
+ "object_position": null,
830
+ "order": null,
831
+ "overflow": null,
832
+ "overflow_x": null,
833
+ "overflow_y": null,
834
+ "padding": null,
835
+ "right": null,
836
+ "top": null,
837
+ "visibility": null,
838
+ "width": null
839
+ }
840
+ },
841
+ "2277a0b29cd841a2a1ad5526f39c28a6": {
842
+ "model_module": "@jupyter-widgets/base",
843
+ "model_name": "LayoutModel",
844
+ "model_module_version": "1.2.0",
845
+ "state": {
846
+ "_model_module": "@jupyter-widgets/base",
847
+ "_model_module_version": "1.2.0",
848
+ "_model_name": "LayoutModel",
849
+ "_view_count": null,
850
+ "_view_module": "@jupyter-widgets/base",
851
+ "_view_module_version": "1.2.0",
852
+ "_view_name": "LayoutView",
853
+ "align_content": null,
854
+ "align_items": null,
855
+ "align_self": null,
856
+ "border": null,
857
+ "bottom": null,
858
+ "display": null,
859
+ "flex": null,
860
+ "flex_flow": null,
861
+ "grid_area": null,
862
+ "grid_auto_columns": null,
863
+ "grid_auto_flow": null,
864
+ "grid_auto_rows": null,
865
+ "grid_column": null,
866
+ "grid_gap": null,
867
+ "grid_row": null,
868
+ "grid_template_areas": null,
869
+ "grid_template_columns": null,
870
+ "grid_template_rows": null,
871
+ "height": null,
872
+ "justify_content": null,
873
+ "justify_items": null,
874
+ "left": null,
875
+ "margin": null,
876
+ "max_height": null,
877
+ "max_width": null,
878
+ "min_height": null,
879
+ "min_width": null,
880
+ "object_fit": null,
881
+ "object_position": null,
882
+ "order": null,
883
+ "overflow": null,
884
+ "overflow_x": null,
885
+ "overflow_y": null,
886
+ "padding": null,
887
+ "right": null,
888
+ "top": null,
889
+ "visibility": null,
890
+ "width": null
891
+ }
892
+ },
893
+ "5f7a4ea2308d4cb2b6e4a0f2f925e2b1": {
894
+ "model_module": "@jupyter-widgets/controls",
895
+ "model_name": "DescriptionStyleModel",
896
+ "model_module_version": "1.5.0",
897
+ "state": {
898
+ "_model_module": "@jupyter-widgets/controls",
899
+ "_model_module_version": "1.5.0",
900
+ "_model_name": "DescriptionStyleModel",
901
+ "_view_count": null,
902
+ "_view_module": "@jupyter-widgets/base",
903
+ "_view_module_version": "1.2.0",
904
+ "_view_name": "StyleView",
905
+ "description_width": ""
906
+ }
907
+ },
908
+ "dc23a6ac81894fe484247273be9d6a83": {
909
+ "model_module": "@jupyter-widgets/base",
910
+ "model_name": "LayoutModel",
911
+ "model_module_version": "1.2.0",
912
+ "state": {
913
+ "_model_module": "@jupyter-widgets/base",
914
+ "_model_module_version": "1.2.0",
915
+ "_model_name": "LayoutModel",
916
+ "_view_count": null,
917
+ "_view_module": "@jupyter-widgets/base",
918
+ "_view_module_version": "1.2.0",
919
+ "_view_name": "LayoutView",
920
+ "align_content": null,
921
+ "align_items": null,
922
+ "align_self": null,
923
+ "border": null,
924
+ "bottom": null,
925
+ "display": null,
926
+ "flex": null,
927
+ "flex_flow": null,
928
+ "grid_area": null,
929
+ "grid_auto_columns": null,
930
+ "grid_auto_flow": null,
931
+ "grid_auto_rows": null,
932
+ "grid_column": null,
933
+ "grid_gap": null,
934
+ "grid_row": null,
935
+ "grid_template_areas": null,
936
+ "grid_template_columns": null,
937
+ "grid_template_rows": null,
938
+ "height": null,
939
+ "justify_content": null,
940
+ "justify_items": null,
941
+ "left": null,
942
+ "margin": null,
943
+ "max_height": null,
944
+ "max_width": null,
945
+ "min_height": null,
946
+ "min_width": null,
947
+ "object_fit": null,
948
+ "object_position": null,
949
+ "order": null,
950
+ "overflow": null,
951
+ "overflow_x": null,
952
+ "overflow_y": null,
953
+ "padding": null,
954
+ "right": null,
955
+ "top": null,
956
+ "visibility": null,
957
+ "width": null
958
+ }
959
+ },
960
+ "d37f42e8924a4b0fafd2e407b1db865b": {
961
+ "model_module": "@jupyter-widgets/controls",
962
+ "model_name": "ProgressStyleModel",
963
+ "model_module_version": "1.5.0",
964
+ "state": {
965
+ "_model_module": "@jupyter-widgets/controls",
966
+ "_model_module_version": "1.5.0",
967
+ "_model_name": "ProgressStyleModel",
968
+ "_view_count": null,
969
+ "_view_module": "@jupyter-widgets/base",
970
+ "_view_module_version": "1.2.0",
971
+ "_view_name": "StyleView",
972
+ "bar_color": null,
973
+ "description_width": ""
974
+ }
975
+ },
976
+ "03fa9da8e5084d688bc7b0f4d8ba3fb5": {
977
+ "model_module": "@jupyter-widgets/base",
978
+ "model_name": "LayoutModel",
979
+ "model_module_version": "1.2.0",
980
+ "state": {
981
+ "_model_module": "@jupyter-widgets/base",
982
+ "_model_module_version": "1.2.0",
983
+ "_model_name": "LayoutModel",
984
+ "_view_count": null,
985
+ "_view_module": "@jupyter-widgets/base",
986
+ "_view_module_version": "1.2.0",
987
+ "_view_name": "LayoutView",
988
+ "align_content": null,
989
+ "align_items": null,
990
+ "align_self": null,
991
+ "border": null,
992
+ "bottom": null,
993
+ "display": null,
994
+ "flex": null,
995
+ "flex_flow": null,
996
+ "grid_area": null,
997
+ "grid_auto_columns": null,
998
+ "grid_auto_flow": null,
999
+ "grid_auto_rows": null,
1000
+ "grid_column": null,
1001
+ "grid_gap": null,
1002
+ "grid_row": null,
1003
+ "grid_template_areas": null,
1004
+ "grid_template_columns": null,
1005
+ "grid_template_rows": null,
1006
+ "height": null,
1007
+ "justify_content": null,
1008
+ "justify_items": null,
1009
+ "left": null,
1010
+ "margin": null,
1011
+ "max_height": null,
1012
+ "max_width": null,
1013
+ "min_height": null,
1014
+ "min_width": null,
1015
+ "object_fit": null,
1016
+ "object_position": null,
1017
+ "order": null,
1018
+ "overflow": null,
1019
+ "overflow_x": null,
1020
+ "overflow_y": null,
1021
+ "padding": null,
1022
+ "right": null,
1023
+ "top": null,
1024
+ "visibility": null,
1025
+ "width": null
1026
+ }
1027
+ },
1028
+ "613fa346a05441828356976ea941a7c7": {
1029
+ "model_module": "@jupyter-widgets/controls",
1030
+ "model_name": "DescriptionStyleModel",
1031
+ "model_module_version": "1.5.0",
1032
+ "state": {
1033
+ "_model_module": "@jupyter-widgets/controls",
1034
+ "_model_module_version": "1.5.0",
1035
+ "_model_name": "DescriptionStyleModel",
1036
+ "_view_count": null,
1037
+ "_view_module": "@jupyter-widgets/base",
1038
+ "_view_module_version": "1.2.0",
1039
+ "_view_name": "StyleView",
1040
+ "description_width": ""
1041
+ }
1042
+ },
1043
+ "f580a1015d334b398d024357adf898cf": {
1044
+ "model_module": "@jupyter-widgets/controls",
1045
+ "model_name": "HBoxModel",
1046
+ "model_module_version": "1.5.0",
1047
+ "state": {
1048
+ "_dom_classes": [],
1049
+ "_model_module": "@jupyter-widgets/controls",
1050
+ "_model_module_version": "1.5.0",
1051
+ "_model_name": "HBoxModel",
1052
+ "_view_count": null,
1053
+ "_view_module": "@jupyter-widgets/controls",
1054
+ "_view_module_version": "1.5.0",
1055
+ "_view_name": "HBoxView",
1056
+ "box_style": "",
1057
+ "children": [
1058
+ "IPY_MODEL_866f75c147c747f5b9f3d2993440823e",
1059
+ "IPY_MODEL_fe4842b3b96a4c1db17abe9a90e026c3",
1060
+ "IPY_MODEL_69561cfd572c4e0fbc107e25a1e50654"
1061
+ ],
1062
+ "layout": "IPY_MODEL_00bc783a0f344176af0a760569c25ffd"
1063
+ }
1064
+ },
1065
+ "866f75c147c747f5b9f3d2993440823e": {
1066
+ "model_module": "@jupyter-widgets/controls",
1067
+ "model_name": "HTMLModel",
1068
+ "model_module_version": "1.5.0",
1069
+ "state": {
1070
+ "_dom_classes": [],
1071
+ "_model_module": "@jupyter-widgets/controls",
1072
+ "_model_module_version": "1.5.0",
1073
+ "_model_name": "HTMLModel",
1074
+ "_view_count": null,
1075
+ "_view_module": "@jupyter-widgets/controls",
1076
+ "_view_module_version": "1.5.0",
1077
+ "_view_name": "HTMLView",
1078
+ "description": "",
1079
+ "description_tooltip": null,
1080
+ "layout": "IPY_MODEL_dd0a347823244e3a8dbd2f8005f378ac",
1081
+ "placeholder": "​",
1082
+ "style": "IPY_MODEL_84b3abe67c4745fab0d67831a7a3c3d7",
1083
+ "value": "tokenizer.json: 100%"
1084
+ }
1085
+ },
1086
+ "fe4842b3b96a4c1db17abe9a90e026c3": {
1087
+ "model_module": "@jupyter-widgets/controls",
1088
+ "model_name": "FloatProgressModel",
1089
+ "model_module_version": "1.5.0",
1090
+ "state": {
1091
+ "_dom_classes": [],
1092
+ "_model_module": "@jupyter-widgets/controls",
1093
+ "_model_module_version": "1.5.0",
1094
+ "_model_name": "FloatProgressModel",
1095
+ "_view_count": null,
1096
+ "_view_module": "@jupyter-widgets/controls",
1097
+ "_view_module_version": "1.5.0",
1098
+ "_view_name": "ProgressView",
1099
+ "bar_style": "success",
1100
+ "description": "",
1101
+ "description_tooltip": null,
1102
+ "layout": "IPY_MODEL_e4bf0e2ea3904cc68b5dcdabf38169b4",
1103
+ "max": 2224003,
1104
+ "min": 0,
1105
+ "orientation": "horizontal",
1106
+ "style": "IPY_MODEL_8f338304e7e44b5f90c156dddc1a129b",
1107
+ "value": 2224003
1108
+ }
1109
+ },
1110
+ "69561cfd572c4e0fbc107e25a1e50654": {
1111
+ "model_module": "@jupyter-widgets/controls",
1112
+ "model_name": "HTMLModel",
1113
+ "model_module_version": "1.5.0",
1114
+ "state": {
1115
+ "_dom_classes": [],
1116
+ "_model_module": "@jupyter-widgets/controls",
1117
+ "_model_module_version": "1.5.0",
1118
+ "_model_name": "HTMLModel",
1119
+ "_view_count": null,
1120
+ "_view_module": "@jupyter-widgets/controls",
1121
+ "_view_module_version": "1.5.0",
1122
+ "_view_name": "HTMLView",
1123
+ "description": "",
1124
+ "description_tooltip": null,
1125
+ "layout": "IPY_MODEL_c314dafdd3e1472789af4307ed170085",
1126
+ "placeholder": "​",
1127
+ "style": "IPY_MODEL_3311af848aac451e8e9b21fae5e89422",
1128
+ "value": " 2.22M/2.22M [00:00&lt;00:00, 16.3MB/s]"
1129
+ }
1130
+ },
1131
+ "00bc783a0f344176af0a760569c25ffd": {
1132
+ "model_module": "@jupyter-widgets/base",
1133
+ "model_name": "LayoutModel",
1134
+ "model_module_version": "1.2.0",
1135
+ "state": {
1136
+ "_model_module": "@jupyter-widgets/base",
1137
+ "_model_module_version": "1.2.0",
1138
+ "_model_name": "LayoutModel",
1139
+ "_view_count": null,
1140
+ "_view_module": "@jupyter-widgets/base",
1141
+ "_view_module_version": "1.2.0",
1142
+ "_view_name": "LayoutView",
1143
+ "align_content": null,
1144
+ "align_items": null,
1145
+ "align_self": null,
1146
+ "border": null,
1147
+ "bottom": null,
1148
+ "display": null,
1149
+ "flex": null,
1150
+ "flex_flow": null,
1151
+ "grid_area": null,
1152
+ "grid_auto_columns": null,
1153
+ "grid_auto_flow": null,
1154
+ "grid_auto_rows": null,
1155
+ "grid_column": null,
1156
+ "grid_gap": null,
1157
+ "grid_row": null,
1158
+ "grid_template_areas": null,
1159
+ "grid_template_columns": null,
1160
+ "grid_template_rows": null,
1161
+ "height": null,
1162
+ "justify_content": null,
1163
+ "justify_items": null,
1164
+ "left": null,
1165
+ "margin": null,
1166
+ "max_height": null,
1167
+ "max_width": null,
1168
+ "min_height": null,
1169
+ "min_width": null,
1170
+ "object_fit": null,
1171
+ "object_position": null,
1172
+ "order": null,
1173
+ "overflow": null,
1174
+ "overflow_x": null,
1175
+ "overflow_y": null,
1176
+ "padding": null,
1177
+ "right": null,
1178
+ "top": null,
1179
+ "visibility": null,
1180
+ "width": null
1181
+ }
1182
+ },
1183
+ "dd0a347823244e3a8dbd2f8005f378ac": {
1184
+ "model_module": "@jupyter-widgets/base",
1185
+ "model_name": "LayoutModel",
1186
+ "model_module_version": "1.2.0",
1187
+ "state": {
1188
+ "_model_module": "@jupyter-widgets/base",
1189
+ "_model_module_version": "1.2.0",
1190
+ "_model_name": "LayoutModel",
1191
+ "_view_count": null,
1192
+ "_view_module": "@jupyter-widgets/base",
1193
+ "_view_module_version": "1.2.0",
1194
+ "_view_name": "LayoutView",
1195
+ "align_content": null,
1196
+ "align_items": null,
1197
+ "align_self": null,
1198
+ "border": null,
1199
+ "bottom": null,
1200
+ "display": null,
1201
+ "flex": null,
1202
+ "flex_flow": null,
1203
+ "grid_area": null,
1204
+ "grid_auto_columns": null,
1205
+ "grid_auto_flow": null,
1206
+ "grid_auto_rows": null,
1207
+ "grid_column": null,
1208
+ "grid_gap": null,
1209
+ "grid_row": null,
1210
+ "grid_template_areas": null,
1211
+ "grid_template_columns": null,
1212
+ "grid_template_rows": null,
1213
+ "height": null,
1214
+ "justify_content": null,
1215
+ "justify_items": null,
1216
+ "left": null,
1217
+ "margin": null,
1218
+ "max_height": null,
1219
+ "max_width": null,
1220
+ "min_height": null,
1221
+ "min_width": null,
1222
+ "object_fit": null,
1223
+ "object_position": null,
1224
+ "order": null,
1225
+ "overflow": null,
1226
+ "overflow_x": null,
1227
+ "overflow_y": null,
1228
+ "padding": null,
1229
+ "right": null,
1230
+ "top": null,
1231
+ "visibility": null,
1232
+ "width": null
1233
+ }
1234
+ },
1235
+ "84b3abe67c4745fab0d67831a7a3c3d7": {
1236
+ "model_module": "@jupyter-widgets/controls",
1237
+ "model_name": "DescriptionStyleModel",
1238
+ "model_module_version": "1.5.0",
1239
+ "state": {
1240
+ "_model_module": "@jupyter-widgets/controls",
1241
+ "_model_module_version": "1.5.0",
1242
+ "_model_name": "DescriptionStyleModel",
1243
+ "_view_count": null,
1244
+ "_view_module": "@jupyter-widgets/base",
1245
+ "_view_module_version": "1.2.0",
1246
+ "_view_name": "StyleView",
1247
+ "description_width": ""
1248
+ }
1249
+ },
1250
+ "e4bf0e2ea3904cc68b5dcdabf38169b4": {
1251
+ "model_module": "@jupyter-widgets/base",
1252
+ "model_name": "LayoutModel",
1253
+ "model_module_version": "1.2.0",
1254
+ "state": {
1255
+ "_model_module": "@jupyter-widgets/base",
1256
+ "_model_module_version": "1.2.0",
1257
+ "_model_name": "LayoutModel",
1258
+ "_view_count": null,
1259
+ "_view_module": "@jupyter-widgets/base",
1260
+ "_view_module_version": "1.2.0",
1261
+ "_view_name": "LayoutView",
1262
+ "align_content": null,
1263
+ "align_items": null,
1264
+ "align_self": null,
1265
+ "border": null,
1266
+ "bottom": null,
1267
+ "display": null,
1268
+ "flex": null,
1269
+ "flex_flow": null,
1270
+ "grid_area": null,
1271
+ "grid_auto_columns": null,
1272
+ "grid_auto_flow": null,
1273
+ "grid_auto_rows": null,
1274
+ "grid_column": null,
1275
+ "grid_gap": null,
1276
+ "grid_row": null,
1277
+ "grid_template_areas": null,
1278
+ "grid_template_columns": null,
1279
+ "grid_template_rows": null,
1280
+ "height": null,
1281
+ "justify_content": null,
1282
+ "justify_items": null,
1283
+ "left": null,
1284
+ "margin": null,
1285
+ "max_height": null,
1286
+ "max_width": null,
1287
+ "min_height": null,
1288
+ "min_width": null,
1289
+ "object_fit": null,
1290
+ "object_position": null,
1291
+ "order": null,
1292
+ "overflow": null,
1293
+ "overflow_x": null,
1294
+ "overflow_y": null,
1295
+ "padding": null,
1296
+ "right": null,
1297
+ "top": null,
1298
+ "visibility": null,
1299
+ "width": null
1300
+ }
1301
+ },
1302
+ "8f338304e7e44b5f90c156dddc1a129b": {
1303
+ "model_module": "@jupyter-widgets/controls",
1304
+ "model_name": "ProgressStyleModel",
1305
+ "model_module_version": "1.5.0",
1306
+ "state": {
1307
+ "_model_module": "@jupyter-widgets/controls",
1308
+ "_model_module_version": "1.5.0",
1309
+ "_model_name": "ProgressStyleModel",
1310
+ "_view_count": null,
1311
+ "_view_module": "@jupyter-widgets/base",
1312
+ "_view_module_version": "1.2.0",
1313
+ "_view_name": "StyleView",
1314
+ "bar_color": null,
1315
+ "description_width": ""
1316
+ }
1317
+ },
1318
+ "c314dafdd3e1472789af4307ed170085": {
1319
+ "model_module": "@jupyter-widgets/base",
1320
+ "model_name": "LayoutModel",
1321
+ "model_module_version": "1.2.0",
1322
+ "state": {
1323
+ "_model_module": "@jupyter-widgets/base",
1324
+ "_model_module_version": "1.2.0",
1325
+ "_model_name": "LayoutModel",
1326
+ "_view_count": null,
1327
+ "_view_module": "@jupyter-widgets/base",
1328
+ "_view_module_version": "1.2.0",
1329
+ "_view_name": "LayoutView",
1330
+ "align_content": null,
1331
+ "align_items": null,
1332
+ "align_self": null,
1333
+ "border": null,
1334
+ "bottom": null,
1335
+ "display": null,
1336
+ "flex": null,
1337
+ "flex_flow": null,
1338
+ "grid_area": null,
1339
+ "grid_auto_columns": null,
1340
+ "grid_auto_flow": null,
1341
+ "grid_auto_rows": null,
1342
+ "grid_column": null,
1343
+ "grid_gap": null,
1344
+ "grid_row": null,
1345
+ "grid_template_areas": null,
1346
+ "grid_template_columns": null,
1347
+ "grid_template_rows": null,
1348
+ "height": null,
1349
+ "justify_content": null,
1350
+ "justify_items": null,
1351
+ "left": null,
1352
+ "margin": null,
1353
+ "max_height": null,
1354
+ "max_width": null,
1355
+ "min_height": null,
1356
+ "min_width": null,
1357
+ "object_fit": null,
1358
+ "object_position": null,
1359
+ "order": null,
1360
+ "overflow": null,
1361
+ "overflow_x": null,
1362
+ "overflow_y": null,
1363
+ "padding": null,
1364
+ "right": null,
1365
+ "top": null,
1366
+ "visibility": null,
1367
+ "width": null
1368
+ }
1369
+ },
1370
+ "3311af848aac451e8e9b21fae5e89422": {
1371
+ "model_module": "@jupyter-widgets/controls",
1372
+ "model_name": "DescriptionStyleModel",
1373
+ "model_module_version": "1.5.0",
1374
+ "state": {
1375
+ "_model_module": "@jupyter-widgets/controls",
1376
+ "_model_module_version": "1.5.0",
1377
+ "_model_name": "DescriptionStyleModel",
1378
+ "_view_count": null,
1379
+ "_view_module": "@jupyter-widgets/base",
1380
+ "_view_module_version": "1.2.0",
1381
+ "_view_name": "StyleView",
1382
+ "description_width": ""
1383
+ }
1384
+ },
1385
+ "f5dbb938e5f542ef8f2a4a92c98b6ed7": {
1386
+ "model_module": "@jupyter-widgets/controls",
1387
+ "model_name": "HBoxModel",
1388
+ "model_module_version": "1.5.0",
1389
+ "state": {
1390
+ "_dom_classes": [],
1391
+ "_model_module": "@jupyter-widgets/controls",
1392
+ "_model_module_version": "1.5.0",
1393
+ "_model_name": "HBoxModel",
1394
+ "_view_count": null,
1395
+ "_view_module": "@jupyter-widgets/controls",
1396
+ "_view_module_version": "1.5.0",
1397
+ "_view_name": "HBoxView",
1398
+ "box_style": "",
1399
+ "children": [
1400
+ "IPY_MODEL_ee0d678d5b694781a419c4277306204b",
1401
+ "IPY_MODEL_c2d90be349784a16975a07e8aace7567",
1402
+ "IPY_MODEL_a7e7ba1a8e954d71a27210b91456c760"
1403
+ ],
1404
+ "layout": "IPY_MODEL_3b341c3a37414a10832b1dc9fad77298"
1405
+ }
1406
+ },
1407
+ "ee0d678d5b694781a419c4277306204b": {
1408
+ "model_module": "@jupyter-widgets/controls",
1409
+ "model_name": "HTMLModel",
1410
+ "model_module_version": "1.5.0",
1411
+ "state": {
1412
+ "_dom_classes": [],
1413
+ "_model_module": "@jupyter-widgets/controls",
1414
+ "_model_module_version": "1.5.0",
1415
+ "_model_name": "HTMLModel",
1416
+ "_view_count": null,
1417
+ "_view_module": "@jupyter-widgets/controls",
1418
+ "_view_module_version": "1.5.0",
1419
+ "_view_name": "HTMLView",
1420
+ "description": "",
1421
+ "description_tooltip": null,
1422
+ "layout": "IPY_MODEL_2790e327bfd94b66b1ef411489f21d6f",
1423
+ "placeholder": "​",
1424
+ "style": "IPY_MODEL_88a5e37f2eb24ded9e3ec4a7835c34c4",
1425
+ "value": "special_tokens_map.json: 100%"
1426
+ }
1427
+ },
1428
+ "c2d90be349784a16975a07e8aace7567": {
1429
+ "model_module": "@jupyter-widgets/controls",
1430
+ "model_name": "FloatProgressModel",
1431
+ "model_module_version": "1.5.0",
1432
+ "state": {
1433
+ "_dom_classes": [],
1434
+ "_model_module": "@jupyter-widgets/controls",
1435
+ "_model_module_version": "1.5.0",
1436
+ "_model_name": "FloatProgressModel",
1437
+ "_view_count": null,
1438
+ "_view_module": "@jupyter-widgets/controls",
1439
+ "_view_module_version": "1.5.0",
1440
+ "_view_name": "ProgressView",
1441
+ "bar_style": "success",
1442
+ "description": "",
1443
+ "description_tooltip": null,
1444
+ "layout": "IPY_MODEL_b541e9cead9d43179b72d3f966d156bc",
1445
+ "max": 389,
1446
+ "min": 0,
1447
+ "orientation": "horizontal",
1448
+ "style": "IPY_MODEL_9d8b4e12f6fa478eba0624457d8b7804",
1449
+ "value": 389
1450
+ }
1451
+ },
1452
+ "a7e7ba1a8e954d71a27210b91456c760": {
1453
+ "model_module": "@jupyter-widgets/controls",
1454
+ "model_name": "HTMLModel",
1455
+ "model_module_version": "1.5.0",
1456
+ "state": {
1457
+ "_dom_classes": [],
1458
+ "_model_module": "@jupyter-widgets/controls",
1459
+ "_model_module_version": "1.5.0",
1460
+ "_model_name": "HTMLModel",
1461
+ "_view_count": null,
1462
+ "_view_module": "@jupyter-widgets/controls",
1463
+ "_view_module_version": "1.5.0",
1464
+ "_view_name": "HTMLView",
1465
+ "description": "",
1466
+ "description_tooltip": null,
1467
+ "layout": "IPY_MODEL_21311ed9e97e42eab18d6eb58497f125",
1468
+ "placeholder": "​",
1469
+ "style": "IPY_MODEL_65c49dcd741b4101a349752fb9b2db49",
1470
+ "value": " 389/389 [00:00&lt;00:00, 5.78kB/s]"
1471
+ }
1472
+ },
1473
+ "3b341c3a37414a10832b1dc9fad77298": {
1474
+ "model_module": "@jupyter-widgets/base",
1475
+ "model_name": "LayoutModel",
1476
+ "model_module_version": "1.2.0",
1477
+ "state": {
1478
+ "_model_module": "@jupyter-widgets/base",
1479
+ "_model_module_version": "1.2.0",
1480
+ "_model_name": "LayoutModel",
1481
+ "_view_count": null,
1482
+ "_view_module": "@jupyter-widgets/base",
1483
+ "_view_module_version": "1.2.0",
1484
+ "_view_name": "LayoutView",
1485
+ "align_content": null,
1486
+ "align_items": null,
1487
+ "align_self": null,
1488
+ "border": null,
1489
+ "bottom": null,
1490
+ "display": null,
1491
+ "flex": null,
1492
+ "flex_flow": null,
1493
+ "grid_area": null,
1494
+ "grid_auto_columns": null,
1495
+ "grid_auto_flow": null,
1496
+ "grid_auto_rows": null,
1497
+ "grid_column": null,
1498
+ "grid_gap": null,
1499
+ "grid_row": null,
1500
+ "grid_template_areas": null,
1501
+ "grid_template_columns": null,
1502
+ "grid_template_rows": null,
1503
+ "height": null,
1504
+ "justify_content": null,
1505
+ "justify_items": null,
1506
+ "left": null,
1507
+ "margin": null,
1508
+ "max_height": null,
1509
+ "max_width": null,
1510
+ "min_height": null,
1511
+ "min_width": null,
1512
+ "object_fit": null,
1513
+ "object_position": null,
1514
+ "order": null,
1515
+ "overflow": null,
1516
+ "overflow_x": null,
1517
+ "overflow_y": null,
1518
+ "padding": null,
1519
+ "right": null,
1520
+ "top": null,
1521
+ "visibility": null,
1522
+ "width": null
1523
+ }
1524
+ },
1525
+ "2790e327bfd94b66b1ef411489f21d6f": {
1526
+ "model_module": "@jupyter-widgets/base",
1527
+ "model_name": "LayoutModel",
1528
+ "model_module_version": "1.2.0",
1529
+ "state": {
1530
+ "_model_module": "@jupyter-widgets/base",
1531
+ "_model_module_version": "1.2.0",
1532
+ "_model_name": "LayoutModel",
1533
+ "_view_count": null,
1534
+ "_view_module": "@jupyter-widgets/base",
1535
+ "_view_module_version": "1.2.0",
1536
+ "_view_name": "LayoutView",
1537
+ "align_content": null,
1538
+ "align_items": null,
1539
+ "align_self": null,
1540
+ "border": null,
1541
+ "bottom": null,
1542
+ "display": null,
1543
+ "flex": null,
1544
+ "flex_flow": null,
1545
+ "grid_area": null,
1546
+ "grid_auto_columns": null,
1547
+ "grid_auto_flow": null,
1548
+ "grid_auto_rows": null,
1549
+ "grid_column": null,
1550
+ "grid_gap": null,
1551
+ "grid_row": null,
1552
+ "grid_template_areas": null,
1553
+ "grid_template_columns": null,
1554
+ "grid_template_rows": null,
1555
+ "height": null,
1556
+ "justify_content": null,
1557
+ "justify_items": null,
1558
+ "left": null,
1559
+ "margin": null,
1560
+ "max_height": null,
1561
+ "max_width": null,
1562
+ "min_height": null,
1563
+ "min_width": null,
1564
+ "object_fit": null,
1565
+ "object_position": null,
1566
+ "order": null,
1567
+ "overflow": null,
1568
+ "overflow_x": null,
1569
+ "overflow_y": null,
1570
+ "padding": null,
1571
+ "right": null,
1572
+ "top": null,
1573
+ "visibility": null,
1574
+ "width": null
1575
+ }
1576
+ },
1577
+ "88a5e37f2eb24ded9e3ec4a7835c34c4": {
1578
+ "model_module": "@jupyter-widgets/controls",
1579
+ "model_name": "DescriptionStyleModel",
1580
+ "model_module_version": "1.5.0",
1581
+ "state": {
1582
+ "_model_module": "@jupyter-widgets/controls",
1583
+ "_model_module_version": "1.5.0",
1584
+ "_model_name": "DescriptionStyleModel",
1585
+ "_view_count": null,
1586
+ "_view_module": "@jupyter-widgets/base",
1587
+ "_view_module_version": "1.2.0",
1588
+ "_view_name": "StyleView",
1589
+ "description_width": ""
1590
+ }
1591
+ },
1592
+ "b541e9cead9d43179b72d3f966d156bc": {
1593
+ "model_module": "@jupyter-widgets/base",
1594
+ "model_name": "LayoutModel",
1595
+ "model_module_version": "1.2.0",
1596
+ "state": {
1597
+ "_model_module": "@jupyter-widgets/base",
1598
+ "_model_module_version": "1.2.0",
1599
+ "_model_name": "LayoutModel",
1600
+ "_view_count": null,
1601
+ "_view_module": "@jupyter-widgets/base",
1602
+ "_view_module_version": "1.2.0",
1603
+ "_view_name": "LayoutView",
1604
+ "align_content": null,
1605
+ "align_items": null,
1606
+ "align_self": null,
1607
+ "border": null,
1608
+ "bottom": null,
1609
+ "display": null,
1610
+ "flex": null,
1611
+ "flex_flow": null,
1612
+ "grid_area": null,
1613
+ "grid_auto_columns": null,
1614
+ "grid_auto_flow": null,
1615
+ "grid_auto_rows": null,
1616
+ "grid_column": null,
1617
+ "grid_gap": null,
1618
+ "grid_row": null,
1619
+ "grid_template_areas": null,
1620
+ "grid_template_columns": null,
1621
+ "grid_template_rows": null,
1622
+ "height": null,
1623
+ "justify_content": null,
1624
+ "justify_items": null,
1625
+ "left": null,
1626
+ "margin": null,
1627
+ "max_height": null,
1628
+ "max_width": null,
1629
+ "min_height": null,
1630
+ "min_width": null,
1631
+ "object_fit": null,
1632
+ "object_position": null,
1633
+ "order": null,
1634
+ "overflow": null,
1635
+ "overflow_x": null,
1636
+ "overflow_y": null,
1637
+ "padding": null,
1638
+ "right": null,
1639
+ "top": null,
1640
+ "visibility": null,
1641
+ "width": null
1642
+ }
1643
+ },
1644
+ "9d8b4e12f6fa478eba0624457d8b7804": {
1645
+ "model_module": "@jupyter-widgets/controls",
1646
+ "model_name": "ProgressStyleModel",
1647
+ "model_module_version": "1.5.0",
1648
+ "state": {
1649
+ "_model_module": "@jupyter-widgets/controls",
1650
+ "_model_module_version": "1.5.0",
1651
+ "_model_name": "ProgressStyleModel",
1652
+ "_view_count": null,
1653
+ "_view_module": "@jupyter-widgets/base",
1654
+ "_view_module_version": "1.2.0",
1655
+ "_view_name": "StyleView",
1656
+ "bar_color": null,
1657
+ "description_width": ""
1658
+ }
1659
+ },
1660
+ "21311ed9e97e42eab18d6eb58497f125": {
1661
+ "model_module": "@jupyter-widgets/base",
1662
+ "model_name": "LayoutModel",
1663
+ "model_module_version": "1.2.0",
1664
+ "state": {
1665
+ "_model_module": "@jupyter-widgets/base",
1666
+ "_model_module_version": "1.2.0",
1667
+ "_model_name": "LayoutModel",
1668
+ "_view_count": null,
1669
+ "_view_module": "@jupyter-widgets/base",
1670
+ "_view_module_version": "1.2.0",
1671
+ "_view_name": "LayoutView",
1672
+ "align_content": null,
1673
+ "align_items": null,
1674
+ "align_self": null,
1675
+ "border": null,
1676
+ "bottom": null,
1677
+ "display": null,
1678
+ "flex": null,
1679
+ "flex_flow": null,
1680
+ "grid_area": null,
1681
+ "grid_auto_columns": null,
1682
+ "grid_auto_flow": null,
1683
+ "grid_auto_rows": null,
1684
+ "grid_column": null,
1685
+ "grid_gap": null,
1686
+ "grid_row": null,
1687
+ "grid_template_areas": null,
1688
+ "grid_template_columns": null,
1689
+ "grid_template_rows": null,
1690
+ "height": null,
1691
+ "justify_content": null,
1692
+ "justify_items": null,
1693
+ "left": null,
1694
+ "margin": null,
1695
+ "max_height": null,
1696
+ "max_width": null,
1697
+ "min_height": null,
1698
+ "min_width": null,
1699
+ "object_fit": null,
1700
+ "object_position": null,
1701
+ "order": null,
1702
+ "overflow": null,
1703
+ "overflow_x": null,
1704
+ "overflow_y": null,
1705
+ "padding": null,
1706
+ "right": null,
1707
+ "top": null,
1708
+ "visibility": null,
1709
+ "width": null
1710
+ }
1711
+ },
1712
+ "65c49dcd741b4101a349752fb9b2db49": {
1713
+ "model_module": "@jupyter-widgets/controls",
1714
+ "model_name": "DescriptionStyleModel",
1715
+ "model_module_version": "1.5.0",
1716
+ "state": {
1717
+ "_model_module": "@jupyter-widgets/controls",
1718
+ "_model_module_version": "1.5.0",
1719
+ "_model_name": "DescriptionStyleModel",
1720
+ "_view_count": null,
1721
+ "_view_module": "@jupyter-widgets/base",
1722
+ "_view_module_version": "1.2.0",
1723
+ "_view_name": "StyleView",
1724
+ "description_width": ""
1725
+ }
1726
+ }
1727
+ }
1728
  }
1729
  },
1730
  "cells": [
 
1781
  " similarity_pcnt_aprox = round(similarity_pcnt, 3)\n",
1782
  " result = f'{similarity_pcnt_aprox} %'\n",
1783
  " return result\n",
1784
+ "#----#\n",
1785
+ "\n",
1786
+ "mix_with = \"\"\n",
1787
+ "mix_method = \"None\""
1788
  ],
1789
  "metadata": {
1790
+ "id": "Ch9puvwKH1s3",
1791
+ "colab": {
1792
+ "base_uri": "https://localhost:8080/"
1793
+ },
1794
+ "outputId": "46175dd6-a875-4208-a128-fddab8752406"
1795
  },
1796
+ "execution_count": 1,
1797
+ "outputs": [
1798
+ {
1799
+ "output_type": "stream",
1800
+ "name": "stdout",
1801
+ "text": [
1802
+ "Cloning into 'sd_tokens'...\n",
1803
+ "remote: Enumerating objects: 7, done.\u001b[K\n",
1804
+ "remote: Counting objects: 100% (4/4), done.\u001b[K\n",
1805
+ "remote: Compressing objects: 100% (4/4), done.\u001b[K\n",
1806
+ "remote: Total 7 (delta 0), reused 0 (delta 0), pack-reused 3 (from 1)\u001b[K\n",
1807
+ "Unpacking objects: 100% (7/7), 305.93 KiB | 5.67 MiB/s, done.\n",
1808
+ "/content/sd_tokens\n"
1809
+ ]
1810
+ }
1811
+ ]
1812
  },
1813
  {
1814
  "cell_type": "code",
 
1847
  "_A = LA.vector_norm(A, ord=2)"
1848
  ],
1849
  "metadata": {
1850
+ "id": "RPdkYzT2_X85",
1851
+ "colab": {
1852
+ "base_uri": "https://localhost:8080/",
1853
+ "height": 194,
1854
+ "referenced_widgets": [
1855
+ "7b073d9c166a45539c651ecd0b27285c",
1856
+ "ffba5f49ba214984b8329b4e06e40dcf",
1857
+ "e69b98b68527488cbb7c1ee5f6011a92",
1858
+ "983145e29ab84636b1e266c73eeb6889",
1859
+ "278c2c021faf4f2696c03070fc3511bf",
1860
+ "3e9df4ac699843df8ae361aba1337b06",
1861
+ "8e9cc6914fc14e56945716902fb11fe9",
1862
+ "0ca945d6f8a5457d9706c211869983c8",
1863
+ "69cf2c7a4ecf4c3188586c86c7056518",
1864
+ "1d60ac5b02de4cc7b0d51ed57165ff64",
1865
+ "e34074fc893d47b8bf75a8089cd8df37",
1866
+ "26cb34af09544ea1b17526891fd319e3",
1867
+ "71627d67c8ec4993a8b1e4a93d53e8db",
1868
+ "ec11e5b722dd4d69bcd758775edd61b6",
1869
+ "63f760d16a1249b6a80f7a73989299ac",
1870
+ "ba3dae52e6bc4a48945ebde7464a5277",
1871
+ "e914f0b293b4410a82e02f990b8a9a1d",
1872
+ "7e18f5165da84f60bea9d9a1819e17df",
1873
+ "ba1b3dc7d77b4fee9addea98f60277bc",
1874
+ "b40d206858bd46e19ef99aa1de302060",
1875
+ "92113b912eea41b4b2bfadd3f65cd835",
1876
+ "bfca51dacc6a4762810309006fc6eca5",
1877
+ "a7a66681148748ae94788ee276925bec",
1878
+ "438a2db97b8649cfbd5b6d87aeb4b13a",
1879
+ "8608253bb3cc4e93a379b05648e1e35c",
1880
+ "aa84ccf805b3476ea155e64ed31edef6",
1881
+ "851b1acc7d524ec1aabb04012c469432",
1882
+ "2277a0b29cd841a2a1ad5526f39c28a6",
1883
+ "5f7a4ea2308d4cb2b6e4a0f2f925e2b1",
1884
+ "dc23a6ac81894fe484247273be9d6a83",
1885
+ "d37f42e8924a4b0fafd2e407b1db865b",
1886
+ "03fa9da8e5084d688bc7b0f4d8ba3fb5",
1887
+ "613fa346a05441828356976ea941a7c7",
1888
+ "f580a1015d334b398d024357adf898cf",
1889
+ "866f75c147c747f5b9f3d2993440823e",
1890
+ "fe4842b3b96a4c1db17abe9a90e026c3",
1891
+ "69561cfd572c4e0fbc107e25a1e50654",
1892
+ "00bc783a0f344176af0a760569c25ffd",
1893
+ "dd0a347823244e3a8dbd2f8005f378ac",
1894
+ "84b3abe67c4745fab0d67831a7a3c3d7",
1895
+ "e4bf0e2ea3904cc68b5dcdabf38169b4",
1896
+ "8f338304e7e44b5f90c156dddc1a129b",
1897
+ "c314dafdd3e1472789af4307ed170085",
1898
+ "3311af848aac451e8e9b21fae5e89422",
1899
+ "f5dbb938e5f542ef8f2a4a92c98b6ed7",
1900
+ "ee0d678d5b694781a419c4277306204b",
1901
+ "c2d90be349784a16975a07e8aace7567",
1902
+ "a7e7ba1a8e954d71a27210b91456c760",
1903
+ "3b341c3a37414a10832b1dc9fad77298",
1904
+ "2790e327bfd94b66b1ef411489f21d6f",
1905
+ "88a5e37f2eb24ded9e3ec4a7835c34c4",
1906
+ "b541e9cead9d43179b72d3f966d156bc",
1907
+ "9d8b4e12f6fa478eba0624457d8b7804",
1908
+ "21311ed9e97e42eab18d6eb58497f125",
1909
+ "65c49dcd741b4101a349752fb9b2db49"
1910
+ ]
1911
+ },
1912
+ "outputId": "4c2d8236-8af4-4d96-e4f0-c6a4da2d0da2"
1913
  },
1914
+ "execution_count": 2,
1915
+ "outputs": [
1916
+ {
1917
+ "output_type": "display_data",
1918
+ "data": {
1919
+ "text/plain": [
1920
+ "tokenizer_config.json: 0%| | 0.00/905 [00:00<?, ?B/s]"
1921
+ ],
1922
+ "application/vnd.jupyter.widget-view+json": {
1923
+ "version_major": 2,
1924
+ "version_minor": 0,
1925
+ "model_id": "7b073d9c166a45539c651ecd0b27285c"
1926
+ }
1927
+ },
1928
+ "metadata": {}
1929
+ },
1930
+ {
1931
+ "output_type": "display_data",
1932
+ "data": {
1933
+ "text/plain": [
1934
+ "vocab.json: 0%| | 0.00/961k [00:00<?, ?B/s]"
1935
+ ],
1936
+ "application/vnd.jupyter.widget-view+json": {
1937
+ "version_major": 2,
1938
+ "version_minor": 0,
1939
+ "model_id": "26cb34af09544ea1b17526891fd319e3"
1940
+ }
1941
+ },
1942
+ "metadata": {}
1943
+ },
1944
+ {
1945
+ "output_type": "display_data",
1946
+ "data": {
1947
+ "text/plain": [
1948
+ "merges.txt: 0%| | 0.00/525k [00:00<?, ?B/s]"
1949
+ ],
1950
+ "application/vnd.jupyter.widget-view+json": {
1951
+ "version_major": 2,
1952
+ "version_minor": 0,
1953
+ "model_id": "a7a66681148748ae94788ee276925bec"
1954
+ }
1955
+ },
1956
+ "metadata": {}
1957
+ },
1958
+ {
1959
+ "output_type": "display_data",
1960
+ "data": {
1961
+ "text/plain": [
1962
+ "tokenizer.json: 0%| | 0.00/2.22M [00:00<?, ?B/s]"
1963
+ ],
1964
+ "application/vnd.jupyter.widget-view+json": {
1965
+ "version_major": 2,
1966
+ "version_minor": 0,
1967
+ "model_id": "f580a1015d334b398d024357adf898cf"
1968
+ }
1969
+ },
1970
+ "metadata": {}
1971
+ },
1972
+ {
1973
+ "output_type": "display_data",
1974
+ "data": {
1975
+ "text/plain": [
1976
+ "special_tokens_map.json: 0%| | 0.00/389 [00:00<?, ?B/s]"
1977
+ ],
1978
+ "application/vnd.jupyter.widget-view+json": {
1979
+ "version_major": 2,
1980
+ "version_minor": 0,
1981
+ "model_id": "f5dbb938e5f542ef8f2a4a92c98b6ed7"
1982
+ }
1983
+ },
1984
+ "metadata": {}
1985
+ },
1986
+ {
1987
+ "output_type": "stream",
1988
+ "name": "stdout",
1989
+ "text": [
1990
+ "[49406, 8922, 49407]\n"
1991
+ ]
1992
+ }
1993
+ ]
1994
  },
1995
  {
1996
  "cell_type": "markdown",
 
2005
  "cell_type": "code",
2006
  "source": [
2007
  "mix_with = \"\" # @param {type:'string'}\n",
2008
+ "mix_method = \"None\" # @param [\"None\" , \"Average\", \"Subtract\"] {allow-input: true}\n",
2009
  "w = 0.5 # @param {type:\"slider\", min:0, max:1, step:0.01}\n",
2010
  "\n",
2011
  "\n",
 
2031
  "metadata": {
2032
  "id": "oXbNSRSKPgRr"
2033
  },
2034
+ "execution_count": 5,
2035
  "outputs": []
2036
  },
2037
  {
 
2066
  " print(f'Calculated all cosine-similarities between the token {vocab[id_A]} with ID = {id_A} the rest of the {NUM_TOKENS} tokens as a 1x{sorted.shape[0]} tensor')"
2067
  ],
2068
  "metadata": {
2069
+ "id": "juxsvco9B0iV",
2070
+ "colab": {
2071
+ "base_uri": "https://localhost:8080/"
2072
+ },
2073
+ "outputId": "ce920e92-5ff5-412c-98d2-5f2c284ca7b4"
2074
  },
2075
+ "execution_count": 6,
2076
+ "outputs": [
2077
+ {
2078
+ "output_type": "stream",
2079
+ "name": "stdout",
2080
+ "text": [
2081
+ "Calculated all cosine-similarities between the token banana</w> with ID = 8922 the rest of the 49407 tokens as a 1x49407 tensor\n"
2082
+ ]
2083
+ }
2084
+ ]
2085
  },
2086
  {
2087
  "cell_type": "markdown",
 
2119
  "base_uri": "https://localhost:8080/"
2120
  },
2121
  "collapsed": true,
2122
+ "outputId": "a03b49b8-a6ec-457b-f78e-be3cb3029eae"
2123
  },
2124
+ "execution_count": 7,
2125
  "outputs": [
2126
  {
2127
  "output_type": "stream",
2128
  "name": "stdout",
2129
  "text": [
2130
  "banana</w>\n",
2131
+ "similiarity = 100.0 %\n",
2132
+ "--------\n",
 
2133
  "bananas</w>\n",
2134
+ "similiarity = 38.93 %\n",
2135
+ "--------\n",
 
2136
  "banan\n",
2137
+ "similiarity = 30.8 %\n",
2138
+ "--------\n",
2139
  "ðŁįĮ</w>\n",
2140
+ "similiarity = 27.12 %\n",
2141
+ "--------\n",
2142
+ "pineapple</w>\n",
2143
+ "similiarity = 19.7 %\n",
2144
+ "--------\n",
 
 
 
 
 
 
 
 
 
 
2145
  "chicken</w>\n",
2146
+ "similiarity = 19.24 %\n",
2147
+ "--------\n",
2148
+ "potassium</w>\n",
2149
+ "similiarity = 19.21 %\n",
2150
+ "--------\n",
2151
+ "sausage</w>\n",
2152
+ "similiarity = 19.07 %\n",
2153
+ "--------\n",
2154
+ "lemon</w>\n",
2155
+ "similiarity = 18.82 %\n",
2156
+ "--------\n",
2157
+ "orange</w>\n",
2158
+ "similiarity = 18.42 %\n",
2159
+ "--------\n",
2160
+ "peanut</w>\n",
2161
+ "similiarity = 17.84 %\n",
2162
+ "--------\n",
2163
+ "parachute</w>\n",
2164
+ "similiarity = 17.19 %\n",
2165
+ "--------\n",
2166
+ "duck\n",
2167
+ "similiarity = 16.8 %\n",
2168
+ "--------\n",
2169
+ "yellow</w>\n",
2170
+ "similiarity = 16.21 %\n",
2171
+ "--------\n",
2172
  "grape</w>\n",
2173
+ "similiarity = 16.19 %\n",
2174
+ "--------\n",
2175
+ "kangaroo</w>\n",
2176
+ "similiarity = 16.13 %\n",
2177
+ "--------\n",
2178
+ "apple</w>\n",
2179
+ "similiarity = 16.13 %\n",
2180
+ "--------\n",
2181
+ "tangerine</w>\n",
2182
+ "similiarity = 16.08 %\n",
2183
+ "--------\n",
2184
+ "giraffe</w>\n",
2185
+ "similiarity = 16.04 %\n",
2186
+ "--------\n",
2187
  "mango</w>\n",
2188
+ "similiarity = 16.03 %\n",
2189
+ "--------\n",
2190
+ "rubber</w>\n",
2191
+ "similiarity = 15.95 %\n",
2192
+ "--------\n",
2193
+ "bamboo</w>\n",
2194
+ "similiarity = 15.88 %\n",
2195
+ "--------\n",
2196
+ "umbrella</w>\n",
2197
+ "similiarity = 15.82 %\n",
2198
+ "--------\n",
2199
+ "nutella</w>\n",
2200
+ "similiarity = 15.69 %\n",
2201
+ "--------\n",
2202
+ "ferrari</w>\n",
2203
+ "similiarity = 15.69 %\n",
2204
+ "--------\n",
2205
+ "oranges</w>\n",
2206
+ "similiarity = 15.65 %\n",
2207
+ "--------\n",
2208
+ "peanuts</w>\n",
2209
  "similiarity = 15.62 %\n",
2210
+ "--------\n",
2211
+ "ali</w>\n",
2212
+ "similiarity = 15.49 %\n",
2213
+ "--------\n",
2214
+ "dae</w>\n",
2215
+ "similiarity = 15.45 %\n",
2216
+ "--------\n",
2217
+ "apd</w>\n",
2218
+ "similiarity = 15.43 %\n",
2219
+ "--------\n",
2220
+ "cucumber</w>\n",
2221
+ "similiarity = 15.32 %\n",
2222
+ "--------\n",
 
 
 
 
 
2223
  "potato</w>\n",
2224
+ "similiarity = 15.22 %\n",
2225
+ "--------\n",
2226
+ "monkey</w>\n",
2227
+ "similiarity = 15.2 %\n",
2228
+ "--------\n",
 
 
 
 
 
 
 
 
 
 
2229
  "croissant</w>\n",
2230
+ "similiarity = 15.18 %\n",
2231
+ "--------\n",
2232
+ "papaya</w>\n",
2233
+ "similiarity = 15.17 %\n",
2234
+ "--------\n",
2235
+ "christmas</w>\n",
2236
+ "similiarity = 15.12 %\n",
2237
+ "--------\n",
2238
+ "sandwich</w>\n",
2239
+ "similiarity = 15.0 %\n",
2240
+ "--------\n",
2241
+ "rainbow</w>\n",
2242
+ "similiarity = 14.98 %\n",
2243
+ "--------\n",
2244
+ "tomato</w>\n",
2245
+ "similiarity = 14.96 %\n",
2246
+ "--------\n",
2247
+ "martini</w>\n",
2248
+ "similiarity = 14.93 %\n",
2249
+ "--------\n",
2250
+ "cabaret</w>\n",
2251
+ "similiarity = 14.83 %\n",
2252
+ "--------\n",
2253
+ "ginger</w>\n",
2254
+ "similiarity = 14.82 %\n",
2255
+ "--------\n",
2256
+ "µ\n",
2257
+ "similiarity = 14.8 %\n",
2258
+ "--------\n",
2259
+ "animal</w>\n",
2260
+ "similiarity = 14.76 %\n",
2261
+ "--------\n",
2262
+ "vanilla</w>\n",
2263
+ "similiarity = 14.73 %\n",
2264
+ "--------\n",
2265
+ "ells</w>\n",
2266
+ "similiarity = 14.66 %\n",
2267
+ "--------\n",
2268
+ "mustache</w>\n",
2269
+ "similiarity = 14.64 %\n",
2270
+ "--------\n",
2271
+ "lime</w>\n",
2272
+ "similiarity = 14.62 %\n",
2273
+ "--------\n",
2274
+ "sickle</w>\n",
2275
+ "similiarity = 14.6 %\n",
2276
+ "--------\n",
2277
+ "vista</w>\n",
2278
+ "similiarity = 14.53 %\n",
2279
+ "--------\n",
2280
+ "coconut</w>\n",
2281
+ "similiarity = 14.52 %\n",
2282
+ "--------\n",
2283
+ "kara</w>\n",
2284
+ "similiarity = 14.46 %\n",
2285
+ "--------\n",
2286
+ "alligator</w>\n",
2287
+ "similiarity = 14.39 %\n",
2288
+ "--------\n",
2289
+ "blueberry</w>\n",
2290
+ "similiarity = 14.34 %\n",
2291
+ "--------\n",
2292
+ "ðŁĻĤ\n",
2293
  "similiarity = 14.3 %\n",
2294
+ "--------\n",
2295
+ "squirrel</w>\n",
2296
+ "similiarity = 14.29 %\n",
2297
+ "--------\n",
2298
+ "atore</w>\n",
2299
+ "similiarity = 14.19 %\n",
2300
+ "--------\n",
2301
+ "watermelon</w>\n",
2302
+ "similiarity = 14.13 %\n",
2303
+ "--------\n",
2304
+ "nana</w>\n",
2305
  "similiarity = 14.09 %\n",
2306
+ "--------\n",
2307
+ "latex</w>\n",
2308
+ "similiarity = 14.08 %\n",
2309
+ "--------\n",
2310
+ "reas\n",
2311
+ "similiarity = 14.07 %\n",
2312
+ "--------\n",
2313
+ "agricultural</w>\n",
2314
+ "similiarity = 14.02 %\n",
2315
+ "--------\n",
2316
+ "davis\n",
2317
+ "similiarity = 14.0 %\n",
2318
+ "--------\n",
2319
+ "zucchini</w>\n",
2320
+ "similiarity = 14.0 %\n",
2321
+ "--------\n",
2322
+ "saxophone</w>\n",
2323
+ "similiarity = 13.93 %\n",
2324
+ "--------\n",
2325
+ "rough\n",
2326
+ "similiarity = 13.92 %\n",
2327
+ "--------\n",
2328
+ "mozzarella</w>\n",
2329
  "similiarity = 13.91 %\n",
2330
+ "--------\n",
2331
+ "eggplant</w>\n",
2332
  "similiarity = 13.9 %\n",
2333
+ "--------\n",
2334
+ "pickle</w>\n",
2335
+ "similiarity = 13.89 %\n",
2336
+ "--------\n",
2337
+ "tortilla</w>\n",
2338
+ "similiarity = 13.88 %\n",
2339
+ "--------\n",
2340
+ "maniac</w>\n",
2341
+ "similiarity = 13.84 %\n",
2342
+ "--------\n",
2343
+ "milk</w>\n",
2344
+ "similiarity = 13.83 %\n",
2345
+ "--------\n",
2346
+ "ylde</w>\n",
2347
+ "similiarity = 13.82 %\n",
2348
+ "--------\n",
2349
+ "cellphone</w>\n",
2350
  "similiarity = 13.78 %\n",
2351
+ "--------\n",
2352
+ "duck</w>\n",
2353
+ "similiarity = 13.73 %\n",
2354
+ "--------\n",
2355
+ "finely</w>\n",
2356
+ "similiarity = 13.72 %\n",
2357
+ "--------\n",
2358
+ "umbrel\n",
2359
+ "similiarity = 13.71 %\n",
2360
+ "--------\n",
2361
+ "fanny</w>\n",
2362
  "similiarity = 13.69 %\n",
2363
+ "--------\n",
2364
+ "navis</w>\n",
2365
+ "similiarity = 13.68 %\n",
2366
+ "--------\n",
2367
+ "twister</w>\n",
2368
+ "similiarity = 13.67 %\n",
2369
+ "--------\n",
2370
+ "moustache</w>\n",
2371
+ "similiarity = 13.66 %\n",
2372
+ "--------\n",
2373
+ "manafort</w>\n",
2374
+ "similiarity = 13.66 %\n",
2375
+ "--------\n",
2376
+ "nod</w>\n",
2377
  "similiarity = 13.62 %\n",
2378
+ "--------\n",
2379
+ "dros</w>\n",
2380
+ "similiarity = 13.6 %\n",
2381
+ "--------\n",
2382
+ "grapefruit</w>\n",
2383
+ "similiarity = 13.6 %\n",
2384
+ "--------\n",
2385
+ "broom</w>\n",
2386
+ "similiarity = 13.59 %\n",
2387
+ "--------\n",
2388
+ "scorpion</w>\n",
2389
+ "similiarity = 13.59 %\n",
2390
+ "--------\n",
2391
+ "د\n",
2392
  "similiarity = 13.58 %\n",
2393
+ "--------\n",
2394
+ "fruit\n",
2395
+ "similiarity = 13.57 %\n",
2396
+ "--------\n",
2397
+ "dv\n",
2398
  "similiarity = 13.55 %\n",
2399
+ "--------\n",
2400
+ "agan\n",
2401
+ "similiarity = 13.53 %\n",
2402
+ "--------\n",
2403
+ "sunflower</w>\n",
2404
+ "similiarity = 13.49 %\n",
2405
+ "--------\n",
2406
+ "banc\n",
2407
+ "similiarity = 13.46 %\n",
2408
+ "--------\n",
2409
+ "literature</w>\n",
2410
  "similiarity = 13.45 %\n",
2411
+ "--------\n",
2412
+ "pelican</w>\n",
2413
+ "similiarity = 13.43 %\n",
2414
+ "--------\n",
2415
+ "breakfast</w>\n",
2416
+ "similiarity = 13.42 %\n",
2417
+ "--------\n",
2418
+ "pear</w>\n",
2419
+ "similiarity = 13.42 %\n",
2420
+ "--------\n",
2421
+ "gri\n",
2422
+ "similiarity = 13.42 %\n",
2423
+ "--------\n",
2424
+ "orange\n",
2425
+ "similiarity = 13.4 %\n",
2426
+ "--------\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2427
  "monet</w>\n",
2428
+ "similiarity = 13.4 %\n",
2429
+ "--------\n"
 
2430
  ]
2431
  }
2432
  ]