KomorAI commited on
Commit
069d8a7
·
verified ·
1 Parent(s): 31750b5

Upload model EngRandom_1.0 + quantizations + auto README

Browse files
Files changed (6) hide show
  1. README.md +67 -0
  2. config.json +34 -0
  3. generation_config.json +10 -0
  4. model.safetensors +3 -0
  5. tokenizer.json +470 -0
  6. tokenizer_config.json +8 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - gpt2
5
+ - text-generation
6
+ - experimental
7
+ - toy-model
8
+ - gguf
9
+ language:
10
+ - pl
11
+ - en
12
+ pipeline_tag: text-generation
13
+ ---
14
+
15
+ # EngRandom_1.0
16
+
17
+ **Eksperymentalny, ultra-mały model językowy** wytrenowany od zera na własnym słowniku.
18
+
19
+ ## Opis
20
+
21
+ Model powstał za pomocą skryptu w Google Colab.
22
+ Jest to zabawkowy GPT-2 (2 warstwy, 64 wymiary, kontekst 64 tokenów) przeznaczony głównie do zabawy i nauki.
23
+
24
+ ### Słownik (vocab)
25
+ ```
26
+ hob, twee, dense, run, nuts, fever, fetch, rival, consider, occasionally, upchange, mauve, extricate, pass, pain, dilute, prune, stake, impregnate, oral, tree, holster, donor, ample, petition, mooch, exciting, sob, scan, deaden, runic, wily, lecture, taboo, breakfast, evoke, saver, teeth, void, jolt, grief, ring, black, livid, golem, nearly, imagine, baby, weary, mural, mushy, rank, mod, album, lion, zebra, own, pied, urinate, lambast, ambush, mothball, corner, rash, two, faster, mix, face, ticket, wean, successful, regard, belly, feel, disrobe, ruled, dread, fine, muddy, cat, salon, once, plow, macro, rasp, smoky, shiny, live, view, plan, prize, coerce, grass, mighty, lift, take, entire, rear, smile, round, hasty, comfort, tiger, plump, lane, enjoy, ruminate, glad, damn, rife, indicate, bleat, remount, clump, clock, usually, force, husky, mummy, growl, pony, jolly, line, fantasize, knowledge, spine, achieve, inseminate, tow, gummy, incommode, kill, valet, rosin, hazy, bared, summer, sewn, girl, search, freedom, reason, bet, testy, shed, tidy, tea, vague, skulk, world, retro, some, dead, snow, reset, structure, dab, carbonise, chart, wild, fighting, loud, gent, cross, kick, rocky, blag, tubby, crawl, have, rosy, dial, blear, strap, make, mock, habit, lunge, secede, ego, spumy, warm, raise, bar, pace, rubber, taken, paper, conquer, three, lefty, right, tub, carefully, nick, darn, stonewall, nice, cadet, mince, bated, shut, bumble, sing, job, picture, redeploy, cache, noted, raw, decorate, loamy, seal, lemur, below, fun, hoagy, peal, quick, ready, gate, string, slate, nanna, row, filch, choice, struggle, purloin, space, pat, gesture, lope, hops, recall, abet, pricy, mimer, arm, fated, promo, empty, antic, arrow, four, awash, natural, times, tape, beat, arms, sour, moony, mantle, fashion, showy, shawl, thrill, room, swing, ridge, parts, astir, has, fluid, diet, port, oaken, too, stopped, video, ink, able, frail, favor, catalyze, wacky, factor, limp, rib, zany, chuckle, lay, color, discard, replied, summon, fifth, jumbo, fabricate, fruit, pop, fracture, remix, low, fence, brand, men, basin, kinky, hump, evil, gawky, team, noise, liken, slew, elude, scandalize, tribe, lank, flex, farce, you, timer, shower, sugar, ion, bliss, instrument, dowel, nag, redo, quell, comfortable, fortify, task, elder, expiate, dip, mangy, plane, lent, till, rejoice, drape, cello, flavour, frank, cleft, crisp, tip, halo, television, agonize, wool, muggy, ham, aqua, palmy, found, produce, leach, doing, wits, forum, grain, legitimise, spoil, walk, indeed, clothes, soak, sixty, using, babble, hail, ordinary, shot, ten, barn, gulch, seat, during, acme, vial, herald, tomorrow, fudge, mice, lowly, goon, ace, rake
27
+ ```
28
+ + tokeny specjalne: `[UNK]`, `[PAD]`, `<|endoftext|>`
29
+
30
+ ### Dane treningowe
31
+ Wygenerowane losowe zdania ze słownika użytkownika (200 przykładów)
32
+
33
+ ### Architektura
34
+ - `n_layer = 2`
35
+ - `n_embd = 64`
36
+ - `n_head = 2`
37
+ - `n_positions = 64`
38
+ - `vocab_size = 387`
39
+
40
+ ## Pliki GGUF (kwantyzacje)
41
+
42
+ - (brak plików GGUF)
43
+
44
+ ## Użycie
45
+
46
+ ### Transformers (Python)
47
+ ```python
48
+ from transformers import AutoModelForCausalLM, AutoTokenizer
49
+
50
+ model = AutoModelForCausalLM.from_pretrained("EngRandom_1.0")
51
+ tokenizer = AutoTokenizer.from_pretrained("EngRandom_1.0")
52
+
53
+ inputs = tokenizer("Miau", return_tensors="pt")
54
+ outputs = model.generate(**inputs, max_new_tokens=20)
55
+ print(tokenizer.decode(outputs[0]))
56
+ ```
57
+
58
+ ### llama.cpp / Ollama / LM Studio
59
+ Po prostu wskaż wybrany plik `.gguf`.
60
+
61
+ ## Ograniczenia
62
+ - Model jest **bardzo mały** – generuje głównie sekwencje ze swojego wąskiego słownika.
63
+ - Nie nadaje się do normalnych zadań językowych.
64
+ - Przeznaczony wyłącznie do eksperymentów i edukacji.
65
+
66
+ ## Licencja
67
+ MIT
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 2,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 64,
16
+ "n_head": 2,
17
+ "n_inner": null,
18
+ "n_layer": 2,
19
+ "n_positions": 64,
20
+ "pad_token_id": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.22.1",
32
+ "use_cache": false,
33
+ "vocab_size": 387
34
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.22.1",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e614d50999b48c05a4142d0d4750f04cf466e096dce788c986930676b3484a8
3
+ size 518472
tokenizer.json ADDED
@@ -0,0 +1,470 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 32,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 1,
14
+ "pad_type_id": 0,
15
+ "pad_token": "[PAD]"
16
+ },
17
+ "added_tokens": [
18
+ {
19
+ "id": 0,
20
+ "content": "[UNK]",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "special": true
26
+ },
27
+ {
28
+ "id": 1,
29
+ "content": "[PAD]",
30
+ "single_word": false,
31
+ "lstrip": false,
32
+ "rstrip": false,
33
+ "normalized": false,
34
+ "special": true
35
+ },
36
+ {
37
+ "id": 2,
38
+ "content": "<|endoftext|>",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": false,
43
+ "special": true
44
+ }
45
+ ],
46
+ "normalizer": null,
47
+ "pre_tokenizer": {
48
+ "type": "Whitespace"
49
+ },
50
+ "post_processor": {
51
+ "type": "TemplateProcessing",
52
+ "single": [
53
+ {
54
+ "Sequence": {
55
+ "id": "A",
56
+ "type_id": 0
57
+ }
58
+ }
59
+ ],
60
+ "pair": [
61
+ {
62
+ "Sequence": {
63
+ "id": "A",
64
+ "type_id": 0
65
+ }
66
+ },
67
+ {
68
+ "Sequence": {
69
+ "id": "B",
70
+ "type_id": 1
71
+ }
72
+ }
73
+ ],
74
+ "special_tokens": {}
75
+ },
76
+ "decoder": null,
77
+ "model": {
78
+ "type": "WordLevel",
79
+ "vocab": {
80
+ "[UNK]": 0,
81
+ "[PAD]": 1,
82
+ "<|endoftext|>": 2,
83
+ "hob": 3,
84
+ "twee": 4,
85
+ "dense": 5,
86
+ "run": 6,
87
+ "nuts": 7,
88
+ "fever": 8,
89
+ "fetch": 9,
90
+ "rival": 10,
91
+ "consider": 11,
92
+ "occasionally": 12,
93
+ "upchange": 13,
94
+ "mauve": 14,
95
+ "extricate": 15,
96
+ "pass": 16,
97
+ "pain": 17,
98
+ "dilute": 18,
99
+ "prune": 19,
100
+ "stake": 20,
101
+ "impregnate": 21,
102
+ "oral": 22,
103
+ "tree": 23,
104
+ "holster": 24,
105
+ "donor": 25,
106
+ "ample": 26,
107
+ "petition": 27,
108
+ "mooch": 28,
109
+ "exciting": 29,
110
+ "sob": 30,
111
+ "scan": 31,
112
+ "deaden": 32,
113
+ "runic": 33,
114
+ "wily": 34,
115
+ "lecture": 35,
116
+ "taboo": 36,
117
+ "breakfast": 37,
118
+ "evoke": 38,
119
+ "saver": 39,
120
+ "teeth": 40,
121
+ "void": 41,
122
+ "jolt": 42,
123
+ "grief": 43,
124
+ "ring": 44,
125
+ "black": 45,
126
+ "livid": 46,
127
+ "golem": 47,
128
+ "nearly": 48,
129
+ "imagine": 49,
130
+ "baby": 50,
131
+ "weary": 51,
132
+ "mural": 52,
133
+ "mushy": 53,
134
+ "rank": 54,
135
+ "mod": 55,
136
+ "album": 56,
137
+ "lion": 57,
138
+ "zebra": 58,
139
+ "own": 59,
140
+ "pied": 60,
141
+ "urinate": 61,
142
+ "lambast": 62,
143
+ "ambush": 63,
144
+ "mothball": 64,
145
+ "corner": 65,
146
+ "rash": 66,
147
+ "two": 67,
148
+ "faster": 68,
149
+ "mix": 69,
150
+ "face": 70,
151
+ "ticket": 71,
152
+ "wean": 72,
153
+ "successful": 73,
154
+ "regard": 74,
155
+ "belly": 75,
156
+ "feel": 76,
157
+ "disrobe": 77,
158
+ "ruled": 78,
159
+ "dread": 79,
160
+ "fine": 80,
161
+ "muddy": 81,
162
+ "cat": 82,
163
+ "salon": 83,
164
+ "once": 84,
165
+ "plow": 85,
166
+ "macro": 86,
167
+ "rasp": 87,
168
+ "smoky": 88,
169
+ "shiny": 89,
170
+ "live": 90,
171
+ "view": 91,
172
+ "plan": 92,
173
+ "prize": 93,
174
+ "coerce": 94,
175
+ "grass": 95,
176
+ "mighty": 96,
177
+ "lift": 97,
178
+ "take": 98,
179
+ "entire": 99,
180
+ "rear": 100,
181
+ "smile": 101,
182
+ "round": 102,
183
+ "hasty": 103,
184
+ "comfort": 104,
185
+ "tiger": 105,
186
+ "plump": 106,
187
+ "lane": 107,
188
+ "enjoy": 108,
189
+ "ruminate": 109,
190
+ "glad": 110,
191
+ "damn": 111,
192
+ "rife": 112,
193
+ "indicate": 113,
194
+ "bleat": 114,
195
+ "remount": 115,
196
+ "clump": 116,
197
+ "clock": 117,
198
+ "usually": 118,
199
+ "force": 119,
200
+ "husky": 120,
201
+ "mummy": 121,
202
+ "growl": 122,
203
+ "pony": 123,
204
+ "jolly": 124,
205
+ "line": 125,
206
+ "fantasize": 126,
207
+ "knowledge": 127,
208
+ "spine": 128,
209
+ "achieve": 129,
210
+ "inseminate": 130,
211
+ "tow": 131,
212
+ "gummy": 132,
213
+ "incommode": 133,
214
+ "kill": 134,
215
+ "valet": 135,
216
+ "rosin": 136,
217
+ "hazy": 137,
218
+ "bared": 138,
219
+ "summer": 139,
220
+ "sewn": 140,
221
+ "girl": 141,
222
+ "search": 142,
223
+ "freedom": 143,
224
+ "reason": 144,
225
+ "bet": 145,
226
+ "testy": 146,
227
+ "shed": 147,
228
+ "tidy": 148,
229
+ "tea": 149,
230
+ "vague": 150,
231
+ "skulk": 151,
232
+ "world": 152,
233
+ "retro": 153,
234
+ "some": 154,
235
+ "dead": 155,
236
+ "snow": 156,
237
+ "reset": 157,
238
+ "structure": 158,
239
+ "dab": 159,
240
+ "carbonise": 160,
241
+ "chart": 161,
242
+ "wild": 162,
243
+ "fighting": 163,
244
+ "loud": 164,
245
+ "gent": 165,
246
+ "cross": 166,
247
+ "kick": 167,
248
+ "rocky": 168,
249
+ "blag": 169,
250
+ "tubby": 170,
251
+ "crawl": 171,
252
+ "have": 172,
253
+ "rosy": 173,
254
+ "dial": 174,
255
+ "blear": 175,
256
+ "strap": 176,
257
+ "make": 177,
258
+ "mock": 178,
259
+ "habit": 179,
260
+ "lunge": 180,
261
+ "secede": 181,
262
+ "ego": 182,
263
+ "spumy": 183,
264
+ "warm": 184,
265
+ "raise": 185,
266
+ "bar": 186,
267
+ "pace": 187,
268
+ "rubber": 188,
269
+ "taken": 189,
270
+ "paper": 190,
271
+ "conquer": 191,
272
+ "three": 192,
273
+ "lefty": 193,
274
+ "right": 194,
275
+ "tub": 195,
276
+ "carefully": 196,
277
+ "nick": 197,
278
+ "darn": 198,
279
+ "stonewall": 199,
280
+ "nice": 200,
281
+ "cadet": 201,
282
+ "mince": 202,
283
+ "bated": 203,
284
+ "shut": 204,
285
+ "bumble": 205,
286
+ "sing": 206,
287
+ "job": 207,
288
+ "picture": 208,
289
+ "redeploy": 209,
290
+ "cache": 210,
291
+ "noted": 211,
292
+ "raw": 212,
293
+ "decorate": 213,
294
+ "loamy": 214,
295
+ "seal": 215,
296
+ "lemur": 216,
297
+ "below": 217,
298
+ "fun": 218,
299
+ "hoagy": 219,
300
+ "peal": 220,
301
+ "quick": 221,
302
+ "ready": 222,
303
+ "gate": 223,
304
+ "string": 224,
305
+ "slate": 225,
306
+ "nanna": 226,
307
+ "row": 227,
308
+ "filch": 228,
309
+ "choice": 229,
310
+ "struggle": 230,
311
+ "purloin": 231,
312
+ "space": 232,
313
+ "pat": 233,
314
+ "gesture": 234,
315
+ "lope": 235,
316
+ "hops": 236,
317
+ "recall": 237,
318
+ "abet": 238,
319
+ "pricy": 239,
320
+ "mimer": 240,
321
+ "arm": 241,
322
+ "fated": 242,
323
+ "promo": 243,
324
+ "empty": 244,
325
+ "antic": 245,
326
+ "arrow": 246,
327
+ "four": 247,
328
+ "awash": 248,
329
+ "natural": 249,
330
+ "times": 250,
331
+ "tape": 251,
332
+ "beat": 252,
333
+ "arms": 253,
334
+ "sour": 254,
335
+ "moony": 255,
336
+ "mantle": 256,
337
+ "fashion": 257,
338
+ "showy": 258,
339
+ "shawl": 259,
340
+ "thrill": 260,
341
+ "room": 261,
342
+ "swing": 262,
343
+ "ridge": 263,
344
+ "parts": 264,
345
+ "astir": 265,
346
+ "has": 266,
347
+ "fluid": 267,
348
+ "diet": 268,
349
+ "port": 269,
350
+ "oaken": 270,
351
+ "too": 271,
352
+ "stopped": 272,
353
+ "video": 273,
354
+ "ink": 274,
355
+ "able": 275,
356
+ "frail": 276,
357
+ "favor": 277,
358
+ "catalyze": 278,
359
+ "wacky": 279,
360
+ "factor": 280,
361
+ "limp": 281,
362
+ "rib": 282,
363
+ "zany": 283,
364
+ "chuckle": 284,
365
+ "lay": 285,
366
+ "color": 286,
367
+ "discard": 287,
368
+ "replied": 288,
369
+ "summon": 289,
370
+ "fifth": 290,
371
+ "jumbo": 291,
372
+ "fabricate": 292,
373
+ "fruit": 293,
374
+ "pop": 294,
375
+ "fracture": 295,
376
+ "remix": 296,
377
+ "low": 297,
378
+ "fence": 298,
379
+ "brand": 299,
380
+ "men": 300,
381
+ "basin": 301,
382
+ "kinky": 302,
383
+ "hump": 303,
384
+ "evil": 304,
385
+ "gawky": 305,
386
+ "team": 306,
387
+ "noise": 307,
388
+ "liken": 308,
389
+ "slew": 309,
390
+ "elude": 310,
391
+ "scandalize": 311,
392
+ "tribe": 312,
393
+ "lank": 313,
394
+ "flex": 314,
395
+ "farce": 315,
396
+ "you": 316,
397
+ "timer": 317,
398
+ "shower": 318,
399
+ "sugar": 319,
400
+ "ion": 320,
401
+ "bliss": 321,
402
+ "instrument": 322,
403
+ "dowel": 323,
404
+ "nag": 324,
405
+ "redo": 325,
406
+ "quell": 326,
407
+ "comfortable": 327,
408
+ "fortify": 328,
409
+ "task": 329,
410
+ "elder": 330,
411
+ "expiate": 331,
412
+ "dip": 332,
413
+ "mangy": 333,
414
+ "plane": 334,
415
+ "lent": 335,
416
+ "till": 336,
417
+ "rejoice": 337,
418
+ "drape": 338,
419
+ "cello": 339,
420
+ "flavour": 340,
421
+ "frank": 341,
422
+ "cleft": 342,
423
+ "crisp": 343,
424
+ "tip": 344,
425
+ "halo": 345,
426
+ "television": 346,
427
+ "agonize": 347,
428
+ "wool": 348,
429
+ "muggy": 349,
430
+ "ham": 350,
431
+ "aqua": 351,
432
+ "palmy": 352,
433
+ "found": 353,
434
+ "produce": 354,
435
+ "leach": 355,
436
+ "doing": 356,
437
+ "wits": 357,
438
+ "forum": 358,
439
+ "grain": 359,
440
+ "legitimise": 360,
441
+ "spoil": 361,
442
+ "walk": 362,
443
+ "indeed": 363,
444
+ "clothes": 364,
445
+ "soak": 365,
446
+ "sixty": 366,
447
+ "using": 367,
448
+ "babble": 368,
449
+ "hail": 369,
450
+ "ordinary": 370,
451
+ "shot": 371,
452
+ "ten": 372,
453
+ "barn": 373,
454
+ "gulch": 374,
455
+ "seat": 375,
456
+ "during": 376,
457
+ "acme": 377,
458
+ "vial": 378,
459
+ "herald": 379,
460
+ "tomorrow": 380,
461
+ "fudge": 381,
462
+ "mice": 382,
463
+ "lowly": 383,
464
+ "goon": 384,
465
+ "ace": 385,
466
+ "rake": 386
467
+ },
468
+ "unk_token": "[UNK]"
469
+ }
470
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "eos_token": "<|endoftext|>",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "tokenizer_class": "TokenizersBackend",
7
+ "unk_token": "[UNK]"
8
+ }