wmatejuk commited on
Commit
87cb9df
·
verified ·
1 Parent(s): 543c176

Add C1e14-d56-0.18M

Browse files
C1e14-d56-0.18M/README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ pipeline_tag: text-generation
4
+ tags:
5
+ - midi
6
+ - gpt2
7
+ - scaling-laws
8
+ ---
9
+
10
+ # C1e14-d56-0.18M
11
+
12
+ Checkpoint from the MIDI IsoFLOP scaling-law sweep.
13
+
14
+ | | |
15
+ | --- | --- |
16
+ | parameters (non-embedding) | 182224 |
17
+ | layers / heads / width | 4 / 4 / 56 |
18
+ | compute budget (FLOPs) | 1.000e+14 |
19
+ | tokens seen | 91455488 |
20
+ | final val loss | 2.4656562841208816 |
21
+ | best val loss | 2.4656562841208816 |
22
+
23
+ ```python
24
+ from transformers import AutoModelForCausalLM, AutoTokenizer
25
+ model = AutoModelForCausalLM.from_pretrained("wmatejuk/midi-gpt", subfolder="C1e14-d56-0.18M")
26
+ tokenizer = AutoTokenizer.from_pretrained("wmatejuk/midi-gpt", subfolder="C1e14-d56-0.18M")
27
+ ```
C1e14-d56-0.18M/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 2,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 3,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 56,
16
+ "n_head": 4,
17
+ "n_inner": null,
18
+ "n_layer": 4,
19
+ "n_positions": 512,
20
+ "pad_token_id": 0,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
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": "5.15.1",
32
+ "use_cache": true,
33
+ "vocab_size": 512
34
+ }
C1e14-d56-0.18M/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.15.1",
9
+ "use_cache": true
10
+ }
C1e14-d56-0.18M/midi_codec.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "dyadic",
3
+ "config": {
4
+ "time_unit": 0.01,
5
+ "n_velocity_bins": 32,
6
+ "max_time_step": 1.0
7
+ }
8
+ }
C1e14-d56-0.18M/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba3fad6c1300c0655314d9535504abedf3e03eb2d87bbc5427778993a90c523
3
+ size 848480
C1e14-d56-0.18M/summary.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "run_id": "C1e14-d56-0.18M",
3
+ "n_params": 182224,
4
+ "n_layer": 4,
5
+ "n_head": 4,
6
+ "n_embd": 56,
7
+ "vocab_size": 512,
8
+ "seq_len": 512,
9
+ "batch_size": 16,
10
+ "gradient_accumulation_steps": 2,
11
+ "world_size": 1,
12
+ "tokens_per_step": 16384,
13
+ "iter_num": 5582,
14
+ "tokens_seen": 91455488,
15
+ "flops": 99992309071872.0,
16
+ "budget_flops": 100000000000000.0,
17
+ "final_val_loss": 2.4656562841208816,
18
+ "best_val_loss": 2.4656562841208816,
19
+ "data_source": "packed",
20
+ "tokens_repo": "wmatejuk/midi-tokens-dyadic-tu0.01-vb32-mts1.0-vocab512",
21
+ "wandb_url": "https://wandb.ai/wmatejuk/midi-gpt-scaling/runs/viuhck7e"
22
+ }
C1e14-d56-0.18M/tokenizer.json ADDED
@@ -0,0 +1,592 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<PAD>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<UNK>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<BOS>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<EOS>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "WhitespaceSplit"
46
+ },
47
+ "post_processor": {
48
+ "type": "TemplateProcessing",
49
+ "single": [
50
+ {
51
+ "Sequence": {
52
+ "id": "A",
53
+ "type_id": 0
54
+ }
55
+ }
56
+ ],
57
+ "pair": [
58
+ {
59
+ "Sequence": {
60
+ "id": "A",
61
+ "type_id": 0
62
+ }
63
+ },
64
+ {
65
+ "Sequence": {
66
+ "id": "B",
67
+ "type_id": 1
68
+ }
69
+ }
70
+ ],
71
+ "special_tokens": {}
72
+ },
73
+ "decoder": null,
74
+ "model": {
75
+ "type": "WordLevel",
76
+ "vocab": {
77
+ "<PAD>": 0,
78
+ "<UNK>": 1,
79
+ "<BOS>": 2,
80
+ "<EOS>": 3,
81
+ "NOTE_ON_21": 4,
82
+ "NOTE_OFF_21": 5,
83
+ "NOTE_ON_22": 6,
84
+ "NOTE_OFF_22": 7,
85
+ "NOTE_ON_23": 8,
86
+ "NOTE_OFF_23": 9,
87
+ "NOTE_ON_24": 10,
88
+ "NOTE_OFF_24": 11,
89
+ "NOTE_ON_25": 12,
90
+ "NOTE_OFF_25": 13,
91
+ "NOTE_ON_26": 14,
92
+ "NOTE_OFF_26": 15,
93
+ "NOTE_ON_27": 16,
94
+ "NOTE_OFF_27": 17,
95
+ "NOTE_ON_28": 18,
96
+ "NOTE_OFF_28": 19,
97
+ "NOTE_ON_29": 20,
98
+ "NOTE_OFF_29": 21,
99
+ "NOTE_ON_30": 22,
100
+ "NOTE_OFF_30": 23,
101
+ "NOTE_ON_31": 24,
102
+ "NOTE_OFF_31": 25,
103
+ "NOTE_ON_32": 26,
104
+ "NOTE_OFF_32": 27,
105
+ "NOTE_ON_33": 28,
106
+ "NOTE_OFF_33": 29,
107
+ "NOTE_ON_34": 30,
108
+ "NOTE_OFF_34": 31,
109
+ "NOTE_ON_35": 32,
110
+ "NOTE_OFF_35": 33,
111
+ "NOTE_ON_36": 34,
112
+ "NOTE_OFF_36": 35,
113
+ "NOTE_ON_37": 36,
114
+ "NOTE_OFF_37": 37,
115
+ "NOTE_ON_38": 38,
116
+ "NOTE_OFF_38": 39,
117
+ "NOTE_ON_39": 40,
118
+ "NOTE_OFF_39": 41,
119
+ "NOTE_ON_40": 42,
120
+ "NOTE_OFF_40": 43,
121
+ "NOTE_ON_41": 44,
122
+ "NOTE_OFF_41": 45,
123
+ "NOTE_ON_42": 46,
124
+ "NOTE_OFF_42": 47,
125
+ "NOTE_ON_43": 48,
126
+ "NOTE_OFF_43": 49,
127
+ "NOTE_ON_44": 50,
128
+ "NOTE_OFF_44": 51,
129
+ "NOTE_ON_45": 52,
130
+ "NOTE_OFF_45": 53,
131
+ "NOTE_ON_46": 54,
132
+ "NOTE_OFF_46": 55,
133
+ "NOTE_ON_47": 56,
134
+ "NOTE_OFF_47": 57,
135
+ "NOTE_ON_48": 58,
136
+ "NOTE_OFF_48": 59,
137
+ "NOTE_ON_49": 60,
138
+ "NOTE_OFF_49": 61,
139
+ "NOTE_ON_50": 62,
140
+ "NOTE_OFF_50": 63,
141
+ "NOTE_ON_51": 64,
142
+ "NOTE_OFF_51": 65,
143
+ "NOTE_ON_52": 66,
144
+ "NOTE_OFF_52": 67,
145
+ "NOTE_ON_53": 68,
146
+ "NOTE_OFF_53": 69,
147
+ "NOTE_ON_54": 70,
148
+ "NOTE_OFF_54": 71,
149
+ "NOTE_ON_55": 72,
150
+ "NOTE_OFF_55": 73,
151
+ "NOTE_ON_56": 74,
152
+ "NOTE_OFF_56": 75,
153
+ "NOTE_ON_57": 76,
154
+ "NOTE_OFF_57": 77,
155
+ "NOTE_ON_58": 78,
156
+ "NOTE_OFF_58": 79,
157
+ "NOTE_ON_59": 80,
158
+ "NOTE_OFF_59": 81,
159
+ "NOTE_ON_60": 82,
160
+ "NOTE_OFF_60": 83,
161
+ "NOTE_ON_61": 84,
162
+ "NOTE_OFF_61": 85,
163
+ "NOTE_ON_62": 86,
164
+ "NOTE_OFF_62": 87,
165
+ "NOTE_ON_63": 88,
166
+ "NOTE_OFF_63": 89,
167
+ "NOTE_ON_64": 90,
168
+ "NOTE_OFF_64": 91,
169
+ "NOTE_ON_65": 92,
170
+ "NOTE_OFF_65": 93,
171
+ "NOTE_ON_66": 94,
172
+ "NOTE_OFF_66": 95,
173
+ "NOTE_ON_67": 96,
174
+ "NOTE_OFF_67": 97,
175
+ "NOTE_ON_68": 98,
176
+ "NOTE_OFF_68": 99,
177
+ "NOTE_ON_69": 100,
178
+ "NOTE_OFF_69": 101,
179
+ "NOTE_ON_70": 102,
180
+ "NOTE_OFF_70": 103,
181
+ "NOTE_ON_71": 104,
182
+ "NOTE_OFF_71": 105,
183
+ "NOTE_ON_72": 106,
184
+ "NOTE_OFF_72": 107,
185
+ "NOTE_ON_73": 108,
186
+ "NOTE_OFF_73": 109,
187
+ "NOTE_ON_74": 110,
188
+ "NOTE_OFF_74": 111,
189
+ "NOTE_ON_75": 112,
190
+ "NOTE_OFF_75": 113,
191
+ "NOTE_ON_76": 114,
192
+ "NOTE_OFF_76": 115,
193
+ "NOTE_ON_77": 116,
194
+ "NOTE_OFF_77": 117,
195
+ "NOTE_ON_78": 118,
196
+ "NOTE_OFF_78": 119,
197
+ "NOTE_ON_79": 120,
198
+ "NOTE_OFF_79": 121,
199
+ "NOTE_ON_80": 122,
200
+ "NOTE_OFF_80": 123,
201
+ "NOTE_ON_81": 124,
202
+ "NOTE_OFF_81": 125,
203
+ "NOTE_ON_82": 126,
204
+ "NOTE_OFF_82": 127,
205
+ "NOTE_ON_83": 128,
206
+ "NOTE_OFF_83": 129,
207
+ "NOTE_ON_84": 130,
208
+ "NOTE_OFF_84": 131,
209
+ "NOTE_ON_85": 132,
210
+ "NOTE_OFF_85": 133,
211
+ "NOTE_ON_86": 134,
212
+ "NOTE_OFF_86": 135,
213
+ "NOTE_ON_87": 136,
214
+ "NOTE_OFF_87": 137,
215
+ "NOTE_ON_88": 138,
216
+ "NOTE_OFF_88": 139,
217
+ "NOTE_ON_89": 140,
218
+ "NOTE_OFF_89": 141,
219
+ "NOTE_ON_90": 142,
220
+ "NOTE_OFF_90": 143,
221
+ "NOTE_ON_91": 144,
222
+ "NOTE_OFF_91": 145,
223
+ "NOTE_ON_92": 146,
224
+ "NOTE_OFF_92": 147,
225
+ "NOTE_ON_93": 148,
226
+ "NOTE_OFF_93": 149,
227
+ "NOTE_ON_94": 150,
228
+ "NOTE_OFF_94": 151,
229
+ "NOTE_ON_95": 152,
230
+ "NOTE_OFF_95": 153,
231
+ "NOTE_ON_96": 154,
232
+ "NOTE_OFF_96": 155,
233
+ "NOTE_ON_97": 156,
234
+ "NOTE_OFF_97": 157,
235
+ "NOTE_ON_98": 158,
236
+ "NOTE_OFF_98": 159,
237
+ "NOTE_ON_99": 160,
238
+ "NOTE_OFF_99": 161,
239
+ "NOTE_ON_100": 162,
240
+ "NOTE_OFF_100": 163,
241
+ "NOTE_ON_101": 164,
242
+ "NOTE_OFF_101": 165,
243
+ "NOTE_ON_102": 166,
244
+ "NOTE_OFF_102": 167,
245
+ "NOTE_ON_103": 168,
246
+ "NOTE_OFF_103": 169,
247
+ "NOTE_ON_104": 170,
248
+ "NOTE_OFF_104": 171,
249
+ "NOTE_ON_105": 172,
250
+ "NOTE_OFF_105": 173,
251
+ "NOTE_ON_106": 174,
252
+ "NOTE_OFF_106": 175,
253
+ "NOTE_ON_107": 176,
254
+ "NOTE_OFF_107": 177,
255
+ "NOTE_ON_108": 178,
256
+ "NOTE_OFF_108": 179,
257
+ "VELOCITY_0": 180,
258
+ "VELOCITY_1": 181,
259
+ "VELOCITY_2": 182,
260
+ "VELOCITY_3": 183,
261
+ "VELOCITY_4": 184,
262
+ "VELOCITY_5": 185,
263
+ "VELOCITY_6": 186,
264
+ "VELOCITY_7": 187,
265
+ "VELOCITY_8": 188,
266
+ "VELOCITY_9": 189,
267
+ "VELOCITY_10": 190,
268
+ "VELOCITY_11": 191,
269
+ "VELOCITY_12": 192,
270
+ "VELOCITY_13": 193,
271
+ "VELOCITY_14": 194,
272
+ "VELOCITY_15": 195,
273
+ "VELOCITY_16": 196,
274
+ "VELOCITY_17": 197,
275
+ "VELOCITY_18": 198,
276
+ "VELOCITY_19": 199,
277
+ "VELOCITY_20": 200,
278
+ "VELOCITY_21": 201,
279
+ "VELOCITY_22": 202,
280
+ "VELOCITY_23": 203,
281
+ "VELOCITY_24": 204,
282
+ "VELOCITY_25": 205,
283
+ "VELOCITY_26": 206,
284
+ "VELOCITY_27": 207,
285
+ "VELOCITY_28": 208,
286
+ "VELOCITY_29": 209,
287
+ "VELOCITY_30": 210,
288
+ "VELOCITY_31": 211,
289
+ "1T": 212,
290
+ "2T": 213,
291
+ "4T": 214,
292
+ "8T": 215,
293
+ "16T": 216,
294
+ "32T": 217,
295
+ "64T": 218,
296
+ "<PLACEHOLDER_0>": 219,
297
+ "<PLACEHOLDER_1>": 220,
298
+ "<PLACEHOLDER_2>": 221,
299
+ "<PLACEHOLDER_3>": 222,
300
+ "<PLACEHOLDER_4>": 223,
301
+ "<PLACEHOLDER_5>": 224,
302
+ "<PLACEHOLDER_6>": 225,
303
+ "<PLACEHOLDER_7>": 226,
304
+ "<PLACEHOLDER_8>": 227,
305
+ "<PLACEHOLDER_9>": 228,
306
+ "<PLACEHOLDER_10>": 229,
307
+ "<PLACEHOLDER_11>": 230,
308
+ "<PLACEHOLDER_12>": 231,
309
+ "<PLACEHOLDER_13>": 232,
310
+ "<PLACEHOLDER_14>": 233,
311
+ "<PLACEHOLDER_15>": 234,
312
+ "<PLACEHOLDER_16>": 235,
313
+ "<PLACEHOLDER_17>": 236,
314
+ "<PLACEHOLDER_18>": 237,
315
+ "<PLACEHOLDER_19>": 238,
316
+ "<PLACEHOLDER_20>": 239,
317
+ "<PLACEHOLDER_21>": 240,
318
+ "<PLACEHOLDER_22>": 241,
319
+ "<PLACEHOLDER_23>": 242,
320
+ "<PLACEHOLDER_24>": 243,
321
+ "<PLACEHOLDER_25>": 244,
322
+ "<PLACEHOLDER_26>": 245,
323
+ "<PLACEHOLDER_27>": 246,
324
+ "<PLACEHOLDER_28>": 247,
325
+ "<PLACEHOLDER_29>": 248,
326
+ "<PLACEHOLDER_30>": 249,
327
+ "<PLACEHOLDER_31>": 250,
328
+ "<PLACEHOLDER_32>": 251,
329
+ "<PLACEHOLDER_33>": 252,
330
+ "<PLACEHOLDER_34>": 253,
331
+ "<PLACEHOLDER_35>": 254,
332
+ "<PLACEHOLDER_36>": 255,
333
+ "<PLACEHOLDER_37>": 256,
334
+ "<PLACEHOLDER_38>": 257,
335
+ "<PLACEHOLDER_39>": 258,
336
+ "<PLACEHOLDER_40>": 259,
337
+ "<PLACEHOLDER_41>": 260,
338
+ "<PLACEHOLDER_42>": 261,
339
+ "<PLACEHOLDER_43>": 262,
340
+ "<PLACEHOLDER_44>": 263,
341
+ "<PLACEHOLDER_45>": 264,
342
+ "<PLACEHOLDER_46>": 265,
343
+ "<PLACEHOLDER_47>": 266,
344
+ "<PLACEHOLDER_48>": 267,
345
+ "<PLACEHOLDER_49>": 268,
346
+ "<PLACEHOLDER_50>": 269,
347
+ "<PLACEHOLDER_51>": 270,
348
+ "<PLACEHOLDER_52>": 271,
349
+ "<PLACEHOLDER_53>": 272,
350
+ "<PLACEHOLDER_54>": 273,
351
+ "<PLACEHOLDER_55>": 274,
352
+ "<PLACEHOLDER_56>": 275,
353
+ "<PLACEHOLDER_57>": 276,
354
+ "<PLACEHOLDER_58>": 277,
355
+ "<PLACEHOLDER_59>": 278,
356
+ "<PLACEHOLDER_60>": 279,
357
+ "<PLACEHOLDER_61>": 280,
358
+ "<PLACEHOLDER_62>": 281,
359
+ "<PLACEHOLDER_63>": 282,
360
+ "<PLACEHOLDER_64>": 283,
361
+ "<PLACEHOLDER_65>": 284,
362
+ "<PLACEHOLDER_66>": 285,
363
+ "<PLACEHOLDER_67>": 286,
364
+ "<PLACEHOLDER_68>": 287,
365
+ "<PLACEHOLDER_69>": 288,
366
+ "<PLACEHOLDER_70>": 289,
367
+ "<PLACEHOLDER_71>": 290,
368
+ "<PLACEHOLDER_72>": 291,
369
+ "<PLACEHOLDER_73>": 292,
370
+ "<PLACEHOLDER_74>": 293,
371
+ "<PLACEHOLDER_75>": 294,
372
+ "<PLACEHOLDER_76>": 295,
373
+ "<PLACEHOLDER_77>": 296,
374
+ "<PLACEHOLDER_78>": 297,
375
+ "<PLACEHOLDER_79>": 298,
376
+ "<PLACEHOLDER_80>": 299,
377
+ "<PLACEHOLDER_81>": 300,
378
+ "<PLACEHOLDER_82>": 301,
379
+ "<PLACEHOLDER_83>": 302,
380
+ "<PLACEHOLDER_84>": 303,
381
+ "<PLACEHOLDER_85>": 304,
382
+ "<PLACEHOLDER_86>": 305,
383
+ "<PLACEHOLDER_87>": 306,
384
+ "<PLACEHOLDER_88>": 307,
385
+ "<PLACEHOLDER_89>": 308,
386
+ "<PLACEHOLDER_90>": 309,
387
+ "<PLACEHOLDER_91>": 310,
388
+ "<PLACEHOLDER_92>": 311,
389
+ "<PLACEHOLDER_93>": 312,
390
+ "<PLACEHOLDER_94>": 313,
391
+ "<PLACEHOLDER_95>": 314,
392
+ "<PLACEHOLDER_96>": 315,
393
+ "<PLACEHOLDER_97>": 316,
394
+ "<PLACEHOLDER_98>": 317,
395
+ "<PLACEHOLDER_99>": 318,
396
+ "<PLACEHOLDER_100>": 319,
397
+ "<PLACEHOLDER_101>": 320,
398
+ "<PLACEHOLDER_102>": 321,
399
+ "<PLACEHOLDER_103>": 322,
400
+ "<PLACEHOLDER_104>": 323,
401
+ "<PLACEHOLDER_105>": 324,
402
+ "<PLACEHOLDER_106>": 325,
403
+ "<PLACEHOLDER_107>": 326,
404
+ "<PLACEHOLDER_108>": 327,
405
+ "<PLACEHOLDER_109>": 328,
406
+ "<PLACEHOLDER_110>": 329,
407
+ "<PLACEHOLDER_111>": 330,
408
+ "<PLACEHOLDER_112>": 331,
409
+ "<PLACEHOLDER_113>": 332,
410
+ "<PLACEHOLDER_114>": 333,
411
+ "<PLACEHOLDER_115>": 334,
412
+ "<PLACEHOLDER_116>": 335,
413
+ "<PLACEHOLDER_117>": 336,
414
+ "<PLACEHOLDER_118>": 337,
415
+ "<PLACEHOLDER_119>": 338,
416
+ "<PLACEHOLDER_120>": 339,
417
+ "<PLACEHOLDER_121>": 340,
418
+ "<PLACEHOLDER_122>": 341,
419
+ "<PLACEHOLDER_123>": 342,
420
+ "<PLACEHOLDER_124>": 343,
421
+ "<PLACEHOLDER_125>": 344,
422
+ "<PLACEHOLDER_126>": 345,
423
+ "<PLACEHOLDER_127>": 346,
424
+ "<PLACEHOLDER_128>": 347,
425
+ "<PLACEHOLDER_129>": 348,
426
+ "<PLACEHOLDER_130>": 349,
427
+ "<PLACEHOLDER_131>": 350,
428
+ "<PLACEHOLDER_132>": 351,
429
+ "<PLACEHOLDER_133>": 352,
430
+ "<PLACEHOLDER_134>": 353,
431
+ "<PLACEHOLDER_135>": 354,
432
+ "<PLACEHOLDER_136>": 355,
433
+ "<PLACEHOLDER_137>": 356,
434
+ "<PLACEHOLDER_138>": 357,
435
+ "<PLACEHOLDER_139>": 358,
436
+ "<PLACEHOLDER_140>": 359,
437
+ "<PLACEHOLDER_141>": 360,
438
+ "<PLACEHOLDER_142>": 361,
439
+ "<PLACEHOLDER_143>": 362,
440
+ "<PLACEHOLDER_144>": 363,
441
+ "<PLACEHOLDER_145>": 364,
442
+ "<PLACEHOLDER_146>": 365,
443
+ "<PLACEHOLDER_147>": 366,
444
+ "<PLACEHOLDER_148>": 367,
445
+ "<PLACEHOLDER_149>": 368,
446
+ "<PLACEHOLDER_150>": 369,
447
+ "<PLACEHOLDER_151>": 370,
448
+ "<PLACEHOLDER_152>": 371,
449
+ "<PLACEHOLDER_153>": 372,
450
+ "<PLACEHOLDER_154>": 373,
451
+ "<PLACEHOLDER_155>": 374,
452
+ "<PLACEHOLDER_156>": 375,
453
+ "<PLACEHOLDER_157>": 376,
454
+ "<PLACEHOLDER_158>": 377,
455
+ "<PLACEHOLDER_159>": 378,
456
+ "<PLACEHOLDER_160>": 379,
457
+ "<PLACEHOLDER_161>": 380,
458
+ "<PLACEHOLDER_162>": 381,
459
+ "<PLACEHOLDER_163>": 382,
460
+ "<PLACEHOLDER_164>": 383,
461
+ "<PLACEHOLDER_165>": 384,
462
+ "<PLACEHOLDER_166>": 385,
463
+ "<PLACEHOLDER_167>": 386,
464
+ "<PLACEHOLDER_168>": 387,
465
+ "<PLACEHOLDER_169>": 388,
466
+ "<PLACEHOLDER_170>": 389,
467
+ "<PLACEHOLDER_171>": 390,
468
+ "<PLACEHOLDER_172>": 391,
469
+ "<PLACEHOLDER_173>": 392,
470
+ "<PLACEHOLDER_174>": 393,
471
+ "<PLACEHOLDER_175>": 394,
472
+ "<PLACEHOLDER_176>": 395,
473
+ "<PLACEHOLDER_177>": 396,
474
+ "<PLACEHOLDER_178>": 397,
475
+ "<PLACEHOLDER_179>": 398,
476
+ "<PLACEHOLDER_180>": 399,
477
+ "<PLACEHOLDER_181>": 400,
478
+ "<PLACEHOLDER_182>": 401,
479
+ "<PLACEHOLDER_183>": 402,
480
+ "<PLACEHOLDER_184>": 403,
481
+ "<PLACEHOLDER_185>": 404,
482
+ "<PLACEHOLDER_186>": 405,
483
+ "<PLACEHOLDER_187>": 406,
484
+ "<PLACEHOLDER_188>": 407,
485
+ "<PLACEHOLDER_189>": 408,
486
+ "<PLACEHOLDER_190>": 409,
487
+ "<PLACEHOLDER_191>": 410,
488
+ "<PLACEHOLDER_192>": 411,
489
+ "<PLACEHOLDER_193>": 412,
490
+ "<PLACEHOLDER_194>": 413,
491
+ "<PLACEHOLDER_195>": 414,
492
+ "<PLACEHOLDER_196>": 415,
493
+ "<PLACEHOLDER_197>": 416,
494
+ "<PLACEHOLDER_198>": 417,
495
+ "<PLACEHOLDER_199>": 418,
496
+ "<PLACEHOLDER_200>": 419,
497
+ "<PLACEHOLDER_201>": 420,
498
+ "<PLACEHOLDER_202>": 421,
499
+ "<PLACEHOLDER_203>": 422,
500
+ "<PLACEHOLDER_204>": 423,
501
+ "<PLACEHOLDER_205>": 424,
502
+ "<PLACEHOLDER_206>": 425,
503
+ "<PLACEHOLDER_207>": 426,
504
+ "<PLACEHOLDER_208>": 427,
505
+ "<PLACEHOLDER_209>": 428,
506
+ "<PLACEHOLDER_210>": 429,
507
+ "<PLACEHOLDER_211>": 430,
508
+ "<PLACEHOLDER_212>": 431,
509
+ "<PLACEHOLDER_213>": 432,
510
+ "<PLACEHOLDER_214>": 433,
511
+ "<PLACEHOLDER_215>": 434,
512
+ "<PLACEHOLDER_216>": 435,
513
+ "<PLACEHOLDER_217>": 436,
514
+ "<PLACEHOLDER_218>": 437,
515
+ "<PLACEHOLDER_219>": 438,
516
+ "<PLACEHOLDER_220>": 439,
517
+ "<PLACEHOLDER_221>": 440,
518
+ "<PLACEHOLDER_222>": 441,
519
+ "<PLACEHOLDER_223>": 442,
520
+ "<PLACEHOLDER_224>": 443,
521
+ "<PLACEHOLDER_225>": 444,
522
+ "<PLACEHOLDER_226>": 445,
523
+ "<PLACEHOLDER_227>": 446,
524
+ "<PLACEHOLDER_228>": 447,
525
+ "<PLACEHOLDER_229>": 448,
526
+ "<PLACEHOLDER_230>": 449,
527
+ "<PLACEHOLDER_231>": 450,
528
+ "<PLACEHOLDER_232>": 451,
529
+ "<PLACEHOLDER_233>": 452,
530
+ "<PLACEHOLDER_234>": 453,
531
+ "<PLACEHOLDER_235>": 454,
532
+ "<PLACEHOLDER_236>": 455,
533
+ "<PLACEHOLDER_237>": 456,
534
+ "<PLACEHOLDER_238>": 457,
535
+ "<PLACEHOLDER_239>": 458,
536
+ "<PLACEHOLDER_240>": 459,
537
+ "<PLACEHOLDER_241>": 460,
538
+ "<PLACEHOLDER_242>": 461,
539
+ "<PLACEHOLDER_243>": 462,
540
+ "<PLACEHOLDER_244>": 463,
541
+ "<PLACEHOLDER_245>": 464,
542
+ "<PLACEHOLDER_246>": 465,
543
+ "<PLACEHOLDER_247>": 466,
544
+ "<PLACEHOLDER_248>": 467,
545
+ "<PLACEHOLDER_249>": 468,
546
+ "<PLACEHOLDER_250>": 469,
547
+ "<PLACEHOLDER_251>": 470,
548
+ "<PLACEHOLDER_252>": 471,
549
+ "<PLACEHOLDER_253>": 472,
550
+ "<PLACEHOLDER_254>": 473,
551
+ "<PLACEHOLDER_255>": 474,
552
+ "<PLACEHOLDER_256>": 475,
553
+ "<PLACEHOLDER_257>": 476,
554
+ "<PLACEHOLDER_258>": 477,
555
+ "<PLACEHOLDER_259>": 478,
556
+ "<PLACEHOLDER_260>": 479,
557
+ "<PLACEHOLDER_261>": 480,
558
+ "<PLACEHOLDER_262>": 481,
559
+ "<PLACEHOLDER_263>": 482,
560
+ "<PLACEHOLDER_264>": 483,
561
+ "<PLACEHOLDER_265>": 484,
562
+ "<PLACEHOLDER_266>": 485,
563
+ "<PLACEHOLDER_267>": 486,
564
+ "<PLACEHOLDER_268>": 487,
565
+ "<PLACEHOLDER_269>": 488,
566
+ "<PLACEHOLDER_270>": 489,
567
+ "<PLACEHOLDER_271>": 490,
568
+ "<PLACEHOLDER_272>": 491,
569
+ "<PLACEHOLDER_273>": 492,
570
+ "<PLACEHOLDER_274>": 493,
571
+ "<PLACEHOLDER_275>": 494,
572
+ "<PLACEHOLDER_276>": 495,
573
+ "<PLACEHOLDER_277>": 496,
574
+ "<PLACEHOLDER_278>": 497,
575
+ "<PLACEHOLDER_279>": 498,
576
+ "<PLACEHOLDER_280>": 499,
577
+ "<PLACEHOLDER_281>": 500,
578
+ "<PLACEHOLDER_282>": 501,
579
+ "<PLACEHOLDER_283>": 502,
580
+ "<PLACEHOLDER_284>": 503,
581
+ "<PLACEHOLDER_285>": 504,
582
+ "<PLACEHOLDER_286>": 505,
583
+ "<PLACEHOLDER_287>": 506,
584
+ "<PLACEHOLDER_288>": 507,
585
+ "<PLACEHOLDER_289>": 508,
586
+ "<PLACEHOLDER_290>": 509,
587
+ "<PLACEHOLDER_291>": 510,
588
+ "<PLACEHOLDER_292>": 511
589
+ },
590
+ "unk_token": "<UNK>"
591
+ }
592
+ }
C1e14-d56-0.18M/tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<BOS>",
4
+ "eos_token": "<EOS>",
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "<PAD>",
9
+ "tokenizer_class": "TokenizersBackend",
10
+ "unk_token": "<UNK>"
11
+ }