Hugging Face's logo

RaphaelMourad
/
Mistral-Prot-v1-15M

Text Generation
Transformers
Safetensors
mixtral
pretrained
mistral
protein
text-generation-inference
Model card Files
xet
 Community
RaphaelMourad commited on
Commit
b7b6cf2
·
verified ·
1 Parent(s): 344e2b8

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +30 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +2091 -0
  8. tokenizer_config.json +52 -0
  9. trainer_state.json +393 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "data/models/Mixtral-8x7B-v0.1-prot",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 256,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 256,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 8,
16
+ "num_experts_per_tok": 1,
17
+ "num_hidden_layers": 8,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.37.2",
28
+ "use_cache": true,
29
+ "vocab_size": 1024
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e43be781fa4022ac89cf327e9d26fa5262da3ee82620837914218d77e63152b
3
+ size 30480368
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3fcd536a84053ef5e50c55cf33d490764fc847e4336d0e4903b704e487cdb9
3
+ size 14308
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdab64b8110eed3c22ca8353445d05698be82fa26d1c6dd01fc983e50695283d
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,2091 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "Whitespace"
55
+ },
56
+ "post_processor": null,
57
+ "decoder": null,
58
+ "model": {
59
+ "type": "BPE",
60
+ "dropout": null,
61
+ "unk_token": "[UNK]",
62
+ "continuing_subword_prefix": null,
63
+ "end_of_word_suffix": null,
64
+ "fuse_unk": false,
65
+ "byte_fallback": false,
66
+ "vocab": {
67
+ "[UNK]": 0,
68
+ "[CLS]": 1,
69
+ "[SEP]": 2,
70
+ "[PAD]": 3,
71
+ "[MASK]": 4,
72
+ "A": 5,
73
+ "B": 6,
74
+ "C": 7,
75
+ "D": 8,
76
+ "E": 9,
77
+ "F": 10,
78
+ "G": 11,
79
+ "H": 12,
80
+ "I": 13,
81
+ "K": 14,
82
+ "L": 15,
83
+ "M": 16,
84
+ "N": 17,
85
+ "P": 18,
86
+ "Q": 19,
87
+ "R": 20,
88
+ "S": 21,
89
+ "T": 22,
90
+ "V": 23,
91
+ "W": 24,
92
+ "X": 25,
93
+ "Y": 26,
94
+ "Z": 27,
95
+ "AA": 28,
96
+ "SS": 29,
97
+ "TT": 30,
98
+ "GG": 31,
99
+ "LL": 32,
100
+ "AG": 33,
101
+ "LS": 34,
102
+ "TV": 35,
103
+ "AV": 36,
104
+ "AL": 37,
105
+ "AS": 38,
106
+ "DG": 39,
107
+ "TG": 40,
108
+ "EE": 41,
109
+ "TL": 42,
110
+ "TS": 43,
111
+ "DV": 44,
112
+ "AE": 45,
113
+ "DL": 46,
114
+ "SG": 47,
115
+ "AP": 48,
116
+ "RL": 49,
117
+ "VV": 50,
118
+ "SL": 51,
119
+ "TP": 52,
120
+ "TI": 53,
121
+ "EL": 54,
122
+ "SV": 55,
123
+ "AD": 56,
124
+ "NG": 57,
125
+ "AR": 58,
126
+ "EV": 59,
127
+ "QL": 60,
128
+ "TD": 61,
129
+ "AI": 62,
130
+ "NL": 63,
131
+ "EG": 64,
132
+ "PV": 65,
133
+ "KL": 66,
134
+ "PG": 67,
135
+ "EI": 68,
136
+ "NV": 69,
137
+ "DI": 70,
138
+ "PL": 71,
139
+ "DS": 72,
140
+ "KK": 73,
141
+ "RV": 74,
142
+ "NI": 75,
143
+ "AQ": 76,
144
+ "PS": 77,
145
+ "AT": 78,
146
+ "EK": 79,
147
+ "ES": 80,
148
+ "RG": 81,
149
+ "QQ": 82,
150
+ "NS": 83,
151
+ "DD": 84,
152
+ "AK": 85,
153
+ "RR": 86,
154
+ "VL": 87,
155
+ "AF": 88,
156
+ "TF": 89,
157
+ "RI": 90,
158
+ "PP": 91,
159
+ "QV": 92,
160
+ "TE": 93,
161
+ "AN": 94,
162
+ "SI": 95,
163
+ "KV": 96,
164
+ "QG": 97,
165
+ "KI": 98,
166
+ "RS": 99,
167
+ "TY": 100,
168
+ "DP": 101,
169
+ "NN": 102,
170
+ "KG": 103,
171
+ "DE": 104,
172
+ "QI": 105,
173
+ "FG": 106,
174
+ "VG": 107,
175
+ "YL": 108,
176
+ "FL": 109,
177
+ "TN": 110,
178
+ "PI": 111,
179
+ "KS": 112,
180
+ "QS": 113,
181
+ "PE": 114,
182
+ "AY": 115,
183
+ "HL": 116,
184
+ "RE": 117,
185
+ "FS": 118,
186
+ "FV": 119,
187
+ "TK": 120,
188
+ "GL": 121,
189
+ "VS": 122,
190
+ "TQ": 123,
191
+ "DN": 124,
192
+ "IL": 125,
193
+ "RP": 126,
194
+ "GS": 127,
195
+ "KE": 128,
196
+ "IS": 129,
197
+ "DF": 130,
198
+ "TR": 131,
199
+ "DR": 132,
200
+ "DY": 133,
201
+ "AH": 134,
202
+ "DK": 135,
203
+ "IG": 136,
204
+ "QE": 137,
205
+ "AM": 138,
206
+ "YG": 139,
207
+ "NE": 140,
208
+ "IV": 141,
209
+ "YS": 142,
210
+ "NP": 143,
211
+ "ER": 144,
212
+ "QP": 145,
213
+ "YV": 146,
214
+ "ML": 147,
215
+ "TA": 148,
216
+ "QR": 149,
217
+ "GV": 150,
218
+ "ND": 151,
219
+ "KP": 152,
220
+ "FE": 153,
221
+ "FI": 154,
222
+ "NK": 155,
223
+ "HS": 156,
224
+ "HG": 157,
225
+ "QK": 158,
226
+ "CL": 159,
227
+ "HV": 160,
228
+ "NY": 161,
229
+ "IE": 162,
230
+ "DQ": 163,
231
+ "WL": 164,
232
+ "RK": 165,
233
+ "CS": 166,
234
+ "NF": 167,
235
+ "RD": 168,
236
+ "EP": 169,
237
+ "RF": 170,
238
+ "AAL": 171,
239
+ "ED": 172,
240
+ "II": 173,
241
+ "TM": 174,
242
+ "TC": 175,
243
+ "NQ": 176,
244
+ "TH": 177,
245
+ "AGG": 178,
246
+ "FD": 179,
247
+ "AAG": 180,
248
+ "RQ": 181,
249
+ "AC": 182,
250
+ "PD": 183,
251
+ "VI": 184,
252
+ "EQ": 185,
253
+ "LG": 186,
254
+ "YI": 187,
255
+ "AW": 188,
256
+ "MS": 189,
257
+ "MV": 190,
258
+ "KD": 191,
259
+ "LV": 192,
260
+ "SSS": 193,
261
+ "NR": 194,
262
+ "CG": 195,
263
+ "HI": 196,
264
+ "PK": 197,
265
+ "TW": 198,
266
+ "RY": 199,
267
+ "EF": 200,
268
+ "EN": 201,
269
+ "ADG": 202,
270
+ "ALL": 203,
271
+ "PQ": 204,
272
+ "EY": 205,
273
+ "CV": 206,
274
+ "TAA": 207,
275
+ "PF": 208,
276
+ "XX": 209,
277
+ "TSS": 210,
278
+ "MG": 211,
279
+ "KQ": 212,
280
+ "ID": 213,
281
+ "PR": 214,
282
+ "TLS": 215,
283
+ "ASS": 216,
284
+ "QD": 217,
285
+ "RN": 218,
286
+ "WS": 219,
287
+ "RH": 220,
288
+ "FK": 221,
289
+ "VD": 222,
290
+ "VE": 223,
291
+ "KN": 224,
292
+ "TGG": 225,
293
+ "FF": 226,
294
+ "ASG": 227,
295
+ "QN": 228,
296
+ "ATT": 229,
297
+ "QY": 230,
298
+ "HP": 231,
299
+ "ATG": 232,
300
+ "ATV": 233,
301
+ "KY": 234,
302
+ "VP": 235,
303
+ "ALS": 236,
304
+ "QF": 237,
305
+ "IN": 238,
306
+ "TAG": 239,
307
+ "IK": 240,
308
+ "TAS": 241,
309
+ "SP": 242,
310
+ "YY": 243,
311
+ "FN": 244,
312
+ "LP": 245,
313
+ "IP": 246,
314
+ "YD": 247,
315
+ "EH": 248,
316
+ "TAV": 249,
317
+ "KR": 250,
318
+ "SD": 251,
319
+ "VR": 252,
320
+ "ATL": 253,
321
+ "GD": 254,
322
+ "EM": 255,
323
+ "TLL": 256,
324
+ "QH": 257,
325
+ "LD": 258,
326
+ "YR": 259,
327
+ "AAV": 260,
328
+ "TAL": 261,
329
+ "ATS": 262,
330
+ "KF": 263,
331
+ "GGG": 264,
332
+ "CP": 265,
333
+ "ADV": 266,
334
+ "SE": 267,
335
+ "LSG": 268,
336
+ "AEL": 269,
337
+ "AGL": 270,
338
+ "SF": 271,
339
+ "YN": 272,
340
+ "DH": 273,
341
+ "PN": 274,
342
+ "TAP": 275,
343
+ "VN": 276,
344
+ "ADL": 277,
345
+ "LLL": 278,
346
+ "SSG": 279,
347
+ "ASL": 280,
348
+ "SSL": 281,
349
+ "FR": 282,
350
+ "YE": 283,
351
+ "IR": 284,
352
+ "YK": 285,
353
+ "ARL": 286,
354
+ "DM": 287,
355
+ "HH": 288,
356
+ "WG": 289,
357
+ "FP": 290,
358
+ "VK": 291,
359
+ "EEL": 292,
360
+ "IQ": 293,
361
+ "AAS": 294,
362
+ "LSL": 295,
363
+ "CR": 296,
364
+ "TDG": 297,
365
+ "TSG": 298,
366
+ "MP": 299,
367
+ "ALG": 300,
368
+ "ANG": 301,
369
+ "AVL": 302,
370
+ "HR": 303,
371
+ "CI": 304,
372
+ "AAAA": 305,
373
+ "VF": 306,
374
+ "TTG": 307,
375
+ "ME": 308,
376
+ "YF": 309,
377
+ "SN": 310,
378
+ "MK": 311,
379
+ "TAE": 312,
380
+ "AEE": 313,
381
+ "YP": 314,
382
+ "HE": 315,
383
+ "MI": 316,
384
+ "CE": 317,
385
+ "VQ": 318,
386
+ "TAT": 319,
387
+ "YQ": 320,
388
+ "ATP": 321,
389
+ "TTS": 322,
390
+ "GE": 323,
391
+ "LLS": 324,
392
+ "AGS": 325,
393
+ "TEE": 326,
394
+ "FQ": 327,
395
+ "AGV": 328,
396
+ "GR": 329,
397
+ "WV": 330,
398
+ "XXXX": 331,
399
+ "TTL": 332,
400
+ "TVS": 333,
401
+ "GI": 334,
402
+ "CD": 335,
403
+ "TSL": 336,
404
+ "HD": 337,
405
+ "TDV": 338,
406
+ "MD": 339,
407
+ "ATI": 340,
408
+ "CK": 341,
409
+ "ATD": 342,
410
+ "TTV": 343,
411
+ "TGL": 344,
412
+ "MR": 345,
413
+ "TAD": 346,
414
+ "HF": 347,
415
+ "DGS": 348,
416
+ "SGS": 349,
417
+ "HQ": 350,
418
+ "CQ": 351,
419
+ "GGS": 352,
420
+ "WR": 353,
421
+ "IF": 354,
422
+ "LLG": 355,
423
+ "TDL": 356,
424
+ "DSDS": 357,
425
+ "AQL": 358,
426
+ "DVL": 359,
427
+ "MN": 360,
428
+ "MQ": 361,
429
+ "ASV": 362,
430
+ "TGS": 363,
431
+ "TVL": 364,
432
+ "HK": 365,
433
+ "GN": 366,
434
+ "DGL": 367,
435
+ "IY": 368,
436
+ "TEL": 369,
437
+ "DW": 370,
438
+ "TAI": 371,
439
+ "GP": 372,
440
+ "AVV": 373,
441
+ "GGL": 374,
442
+ "EVL": 375,
443
+ "SGL": 376,
444
+ "CN": 377,
445
+ "FY": 378,
446
+ "DAA": 379,
447
+ "SSV": 380,
448
+ "HY": 381,
449
+ "AVG": 382,
450
+ "HN": 383,
451
+ "PY": 384,
452
+ "SR": 385,
453
+ "SK": 386,
454
+ "APG": 387,
455
+ "ALV": 388,
456
+ "DGG": 389,
457
+ "SVL": 390,
458
+ "APL": 391,
459
+ "RVL": 392,
460
+ "LSV": 393,
461
+ "TEV": 394,
462
+ "RM": 395,
463
+ "ALP": 396,
464
+ "RW": 397,
465
+ "AVS": 398,
466
+ "DGV": 399,
467
+ "TPL": 400,
468
+ "AKL": 401,
469
+ "TSV": 402,
470
+ "AAP": 403,
471
+ "VVL": 404,
472
+ "ALR": 405,
473
+ "EC": 406,
474
+ "TEI": 407,
475
+ "TTTT": 408,
476
+ "SVS": 409,
477
+ "TAR": 410,
478
+ "TNG": 411,
479
+ "TEG": 412,
480
+ "EW": 413,
481
+ "AEG": 414,
482
+ "APV": 415,
483
+ "QM": 416,
484
+ "TVV": 417,
485
+ "TAQ": 418,
486
+ "PH": 419,
487
+ "CF": 420,
488
+ "ANL": 421,
489
+ "TES": 422,
490
+ "KM": 423,
491
+ "TPS": 424,
492
+ "GGV": 425,
493
+ "RLV": 426,
494
+ "NM": 427,
495
+ "PVL": 428,
496
+ "TLG": 429,
497
+ "DAG": 430,
498
+ "SSSS": 431,
499
+ "DC": 432,
500
+ "WI": 433,
501
+ "ELL": 434,
502
+ "EGL": 435,
503
+ "RLL": 436,
504
+ "ELG": 437,
505
+ "ANV": 438,
506
+ "SY": 439,
507
+ "EAA": 440,
508
+ "NH": 441,
509
+ "TVG": 442,
510
+ "SLV": 443,
511
+ "QQQQ": 444,
512
+ "PAA": 445,
513
+ "WQ": 446,
514
+ "EAL": 447,
515
+ "KH": 448,
516
+ "TNV": 449,
517
+ "SQ": 450,
518
+ "TGV": 451,
519
+ "MF": 452,
520
+ "DAL": 453,
521
+ "PAG": 454,
522
+ "DAV": 455,
523
+ "DLS": 456,
524
+ "TPV": 457,
525
+ "AEV": 458,
526
+ "DIL": 459,
527
+ "TNL": 460,
528
+ "PSP": 461,
529
+ "TLV": 462,
530
+ "WN": 463,
531
+ "WK": 464,
532
+ "TRL": 465,
533
+ "TTP": 466,
534
+ "ARG": 467,
535
+ "RC": 468,
536
+ "DLL": 469,
537
+ "DLV": 470,
538
+ "TAK": 471,
539
+ "PGL": 472,
540
+ "DLG": 473,
541
+ "SLG": 474,
542
+ "RAA": 475,
543
+ "DVV": 476,
544
+ "NGG": 477,
545
+ "SGV": 478,
546
+ "SSI": 479,
547
+ "TIS": 480,
548
+ "TPG": 481,
549
+ "RGL": 482,
550
+ "NC": 483,
551
+ "EEV": 484,
552
+ "TEK": 485,
553
+ "VVV": 486,
554
+ "FH": 487,
555
+ "YH": 488,
556
+ "EIL": 489,
557
+ "TAN": 490,
558
+ "NGL": 491,
559
+ "APS": 492,
560
+ "IH": 493,
561
+ "WE": 494,
562
+ "TQL": 495,
563
+ "RLG": 496,
564
+ "VVG": 497,
565
+ "TNI": 498,
566
+ "TLP": 499,
567
+ "SSP": 500,
568
+ "TTI": 501,
569
+ "DAS": 502,
570
+ "TKL": 503,
571
+ "NVL": 504,
572
+ "QLL": 505,
573
+ "TDS": 506,
574
+ "AIL": 507,
575
+ "AKK": 508,
576
+ "PLP": 509,
577
+ "QC": 510,
578
+ "DSL": 511,
579
+ "ELV": 512,
580
+ "DVS": 513,
581
+ "ANI": 514,
582
+ "NW": 515,
583
+ "ANS": 516,
584
+ "QW": 517,
585
+ "TSP": 518,
586
+ "QAA": 519,
587
+ "TNS": 520,
588
+ "DSS": 521,
589
+ "TAF": 522,
590
+ "PGS": 523,
591
+ "DSG": 524,
592
+ "VVS": 525,
593
+ "PM": 526,
594
+ "GK": 527,
595
+ "DAD": 528,
596
+ "LLV": 529,
597
+ "AGN": 530,
598
+ "LSP": 531,
599
+ "ESL": 532,
600
+ "NGS": 533,
601
+ "DDV": 534,
602
+ "EAV": 535,
603
+ "DEL": 536,
604
+ "TIL": 537,
605
+ "SVG": 538,
606
+ "NGV": 539,
607
+ "EEI": 540,
608
+ "AIG": 541,
609
+ "XXXXXXXX": 542,
610
+ "DDL": 543,
611
+ "AGI": 544,
612
+ "ASI": 545,
613
+ "CY": 546,
614
+ "FM": 547,
615
+ "AAR": 548,
616
+ "AAE": 549,
617
+ "AAI": 550,
618
+ "NIL": 551,
619
+ "TKK": 552,
620
+ "TSI": 553,
621
+ "TKV": 554,
622
+ "TVN": 555,
623
+ "DTL": 556,
624
+ "MY": 557,
625
+ "QGL": 558,
626
+ "AGE": 559,
627
+ "DEE": 560,
628
+ "ADS": 561,
629
+ "AGR": 562,
630
+ "SLP": 563,
631
+ "AES": 564,
632
+ "ASP": 565,
633
+ "LLE": 566,
634
+ "LSI": 567,
635
+ "DTV": 568,
636
+ "DTT": 569,
637
+ "PVG": 570,
638
+ "GGGG": 571,
639
+ "TRV": 572,
640
+ "PGV": 573,
641
+ "RAL": 574,
642
+ "PVS": 575,
643
+ "EVS": 576,
644
+ "AYL": 577,
645
+ "KC": 578,
646
+ "ADI": 579,
647
+ "WF": 580,
648
+ "NSS": 581,
649
+ "TQV": 582,
650
+ "DSI": 583,
651
+ "QAL": 584,
652
+ "PPP": 585,
653
+ "ARV": 586,
654
+ "EEE": 587,
655
+ "NTL": 588,
656
+ "DDG": 589,
657
+ "PDG": 590,
658
+ "RLR": 591,
659
+ "LLR": 592,
660
+ "DSV": 593,
661
+ "TTE": 594,
662
+ "EEG": 595,
663
+ "CH": 596,
664
+ "KW": 597,
665
+ "TKI": 598,
666
+ "AEI": 599,
667
+ "LSE": 600,
668
+ "MM": 601,
669
+ "AQG": 602,
670
+ "NVS": 603,
671
+ "DLP": 604,
672
+ "EGV": 605,
673
+ "DEV": 606,
674
+ "QQL": 607,
675
+ "EKL": 608,
676
+ "YW": 609,
677
+ "REL": 610,
678
+ "RIL": 611,
679
+ "LLP": 612,
680
+ "PLV": 613,
681
+ "DIS": 614,
682
+ "TAY": 615,
683
+ "AFL": 616,
684
+ "PVP": 617,
685
+ "QSL": 618,
686
+ "TVP": 619,
687
+ "NAA": 620,
688
+ "AIS": 621,
689
+ "ERL": 622,
690
+ "NLG": 623,
691
+ "RAV": 624,
692
+ "AQV": 625,
693
+ "EES": 626,
694
+ "DGI": 627,
695
+ "TIG": 628,
696
+ "EGS": 629,
697
+ "APP": 630,
698
+ "PLG": 631,
699
+ "LLK": 632,
700
+ "NLS": 633,
701
+ "TDI": 634,
702
+ "NLV": 635,
703
+ "QLV": 636,
704
+ "TPP": 637,
705
+ "RLS": 638,
706
+ "EEK": 639,
707
+ "DRL": 640,
708
+ "ETL": 641,
709
+ "VLG": 642,
710
+ "TRS": 643,
711
+ "TGN": 644,
712
+ "TQI": 645,
713
+ "TRG": 646,
714
+ "AHL": 647,
715
+ "ELP": 648,
716
+ "FC": 649,
717
+ "TNN": 650,
718
+ "DSDSDSDS": 651,
719
+ "TGI": 652,
720
+ "DTS": 653,
721
+ "RVS": 654,
722
+ "EIS": 655,
723
+ "MH": 656,
724
+ "KGL": 657,
725
+ "TIV": 658,
726
+ "TVE": 659,
727
+ "TLN": 660,
728
+ "DDI": 661,
729
+ "QLG": 662,
730
+ "DAE": 663,
731
+ "TVI": 664,
732
+ "DVG": 665,
733
+ "TQG": 666,
734
+ "FGL": 667,
735
+ "TKS": 668,
736
+ "QAV": 669,
737
+ "ARS": 670,
738
+ "KLV": 671,
739
+ "NIS": 672,
740
+ "DAP": 673,
741
+ "TQS": 674,
742
+ "DLI": 675,
743
+ "RGG": 676,
744
+ "WP": 677,
745
+ "AIV": 678,
746
+ "NSL": 679,
747
+ "DGK": 680,
748
+ "YM": 681,
749
+ "ESI": 682,
750
+ "RRL": 683,
751
+ "RSL": 684,
752
+ "ELS": 685,
753
+ "PSS": 686,
754
+ "EGG": 687,
755
+ "EKV": 688,
756
+ "QLS": 689,
757
+ "NTT": 690,
758
+ "RSS": 691,
759
+ "ESS": 692,
760
+ "ETT": 693,
761
+ "QSS": 694,
762
+ "TRI": 695,
763
+ "PGG": 696,
764
+ "EAE": 697,
765
+ "KIL": 698,
766
+ "FSS": 699,
767
+ "EIV": 700,
768
+ "SIL": 701,
769
+ "TDP": 702,
770
+ "NSG": 703,
771
+ "RGS": 704,
772
+ "TRR": 705,
773
+ "ADP": 706,
774
+ "QVV": 707,
775
+ "RVG": 708,
776
+ "TQQ": 709,
777
+ "DIV": 710,
778
+ "NVG": 711,
779
+ "KEL": 712,
780
+ "TLI": 713,
781
+ "QRL": 714,
782
+ "EAG": 715,
783
+ "AKV": 716,
784
+ "QIL": 717,
785
+ "AVI": 718,
786
+ "NLL": 719,
787
+ "NAG": 720,
788
+ "YC": 721,
789
+ "DTG": 722,
790
+ "NAS": 723,
791
+ "RAG": 724,
792
+ "NSI": 725,
793
+ "TVTV": 726,
794
+ "QGG": 727,
795
+ "SGI": 728,
796
+ "KGV": 729,
797
+ "HM": 730,
798
+ "QVL": 731,
799
+ "FGG": 732,
800
+ "EVV": 733,
801
+ "ESV": 734,
802
+ "QEL": 735,
803
+ "KEE": 736,
804
+ "DVI": 737,
805
+ "ETV": 738,
806
+ "PC": 739,
807
+ "AFG": 740,
808
+ "EKI": 741,
809
+ "ALI": 742,
810
+ "HC": 743,
811
+ "EQL": 744,
812
+ "TFS": 745,
813
+ "TPI": 746,
814
+ "SIS": 747,
815
+ "FW": 748,
816
+ "RGV": 749,
817
+ "NIG": 750,
818
+ "QTL": 751,
819
+ "EAS": 752,
820
+ "KLK": 753,
821
+ "NLI": 754,
822
+ "FSG": 755,
823
+ "RSG": 756,
824
+ "FDL": 757,
825
+ "PSI": 758,
826
+ "AVP": 759,
827
+ "TKG": 760,
828
+ "EDL": 761,
829
+ "KKKK": 762,
830
+ "RAR": 763,
831
+ "QAG": 764,
832
+ "EKS": 765,
833
+ "EVG": 766,
834
+ "TVK": 767,
835
+ "NAL": 768,
836
+ "DAI": 769,
837
+ "VGL": 770,
838
+ "NGI": 771,
839
+ "DEI": 772,
840
+ "AKG": 773,
841
+ "TLK": 774,
842
+ "EDV": 775,
843
+ "ETS": 776,
844
+ "ESG": 777,
845
+ "PTT": 778,
846
+ "WY": 779,
847
+ "KAL": 780,
848
+ "TVD": 781,
849
+ "KLG": 782,
850
+ "RDL": 783,
851
+ "QSV": 784,
852
+ "YLG": 785,
853
+ "LSF": 786,
854
+ "DQL": 787,
855
+ "TSGS": 788,
856
+ "CSS": 789,
857
+ "DDS": 790,
858
+ "DAR": 791,
859
+ "PAP": 792,
860
+ "RVV": 793,
861
+ "NTS": 794,
862
+ "PAV": 795,
863
+ "QAS": 796,
864
+ "AQS": 797,
865
+ "LSK": 798,
866
+ "EDG": 799,
867
+ "CC": 800,
868
+ "SLI": 801,
869
+ "DTI": 802,
870
+ "NTG": 803,
871
+ "RRS": 804,
872
+ "ELI": 805,
873
+ "NAV": 806,
874
+ "EVI": 807,
875
+ "QSG": 808,
876
+ "KLL": 809,
877
+ "DNL": 810,
878
+ "GGI": 811,
879
+ "KSS": 812,
880
+ "AAF": 813,
881
+ "RLP": 814,
882
+ "QTV": 815,
883
+ "QVS": 816,
884
+ "PVI": 817,
885
+ "VLV": 818,
886
+ "AHG": 819,
887
+ "TFL": 820,
888
+ "NSV": 821,
889
+ "DPS": 822,
890
+ "AKS": 823,
891
+ "RAE": 824,
892
+ "PSG": 825,
893
+ "QTT": 826,
894
+ "EKG": 827,
895
+ "KLI": 828,
896
+ "ENL": 829,
897
+ "RTL": 830,
898
+ "KKK": 831,
899
+ "LLI": 832,
900
+ "DRV": 833,
901
+ "FTG": 834,
902
+ "DAT": 835,
903
+ "NVV": 836,
904
+ "DVP": 837,
905
+ "AFV": 838,
906
+ "KSL": 839,
907
+ "DIG": 840,
908
+ "HW": 841,
909
+ "EPG": 842,
910
+ "DTD": 843,
911
+ "RRG": 844,
912
+ "PIL": 845,
913
+ "AAK": 846,
914
+ "FLG": 847,
915
+ "EII": 848,
916
+ "QGS": 849,
917
+ "NNI": 850,
918
+ "NNL": 851,
919
+ "NVI": 852,
920
+ "SIG": 853,
921
+ "TGK": 854,
922
+ "RTV": 855,
923
+ "NDG": 856,
924
+ "KKS": 857,
925
+ "AAQ": 858,
926
+ "FTV": 859,
927
+ "NDL": 860,
928
+ "DES": 861,
929
+ "RSV": 862,
930
+ "LLQ": 863,
931
+ "RDG": 864,
932
+ "ALK": 865,
933
+ "DEG": 866,
934
+ "ALE": 867,
935
+ "PEP": 868,
936
+ "TGP": 869,
937
+ "RAS": 870,
938
+ "ELK": 871,
939
+ "GLG": 872,
940
+ "DPV": 873,
941
+ "EKP": 874,
942
+ "DKL": 875,
943
+ "REE": 876,
944
+ "RVI": 877,
945
+ "NTV": 878,
946
+ "KVS": 879,
947
+ "DII": 880,
948
+ "KKI": 881,
949
+ "AML": 882,
950
+ "TYL": 883,
951
+ "EIG": 884,
952
+ "FSL": 885,
953
+ "AYV": 886,
954
+ "FAA": 887,
955
+ "QVG": 888,
956
+ "SVI": 889,
957
+ "ETI": 890,
958
+ "YGG": 891,
959
+ "VGV": 892,
960
+ "TYS": 893,
961
+ "KKV": 894,
962
+ "QTI": 895,
963
+ "NTI": 896,
964
+ "FGS": 897,
965
+ "AFS": 898,
966
+ "EEEE": 899,
967
+ "RLI": 900,
968
+ "RDV": 901,
969
+ "VGS": 902,
970
+ "TFG": 903,
971
+ "AGP": 904,
972
+ "RQL": 905,
973
+ "TRE": 906,
974
+ "RPG": 907,
975
+ "KIS": 908,
976
+ "ALQ": 909,
977
+ "HLL": 910,
978
+ "ARI": 911,
979
+ "EAP": 912,
980
+ "NNS": 913,
981
+ "QTS": 914,
982
+ "EGI": 915,
983
+ "FDV": 916,
984
+ "EPV": 917,
985
+ "TRP": 918,
986
+ "VVI": 919,
987
+ "NIV": 920,
988
+ "KAG": 921,
989
+ "NDV": 922,
990
+ "DNG": 923,
991
+ "QQV": 924,
992
+ "KKG": 925,
993
+ "QSI": 926,
994
+ "NEL": 927,
995
+ "QGV": 928,
996
+ "DNV": 929,
997
+ "KLS": 930,
998
+ "TAH": 931,
999
+ "QEE": 932,
1000
+ "SVP": 933,
1001
+ "ASF": 934,
1002
+ "API": 935,
1003
+ "KDL": 936,
1004
+ "QAE": 937,
1005
+ "EDI": 938,
1006
+ "RPV": 939,
1007
+ "RPL": 940,
1008
+ "WH": 941,
1009
+ "YTL": 942,
1010
+ "DPG": 943,
1011
+ "NNG": 944,
1012
+ "YSG": 945,
1013
+ "DPL": 946,
1014
+ "RIV": 947,
1015
+ "NII": 948,
1016
+ "EAI": 949,
1017
+ "ETG": 950,
1018
+ "RIS": 951,
1019
+ "EPL": 952,
1020
+ "DKV": 953,
1021
+ "PLL": 954,
1022
+ "YTV": 955,
1023
+ "PIG": 956,
1024
+ "FTL": 957,
1025
+ "PSL": 958,
1026
+ "AQI": 959,
1027
+ "WM": 960,
1028
+ "NAT": 961,
1029
+ "THL": 962,
1030
+ "DNS": 963,
1031
+ "QDL": 964,
1032
+ "QAR": 965,
1033
+ "QPG": 966,
1034
+ "PAL": 967,
1035
+ "CM": 968,
1036
+ "YTG": 969,
1037
+ "TFV": 970,
1038
+ "YSS": 971,
1039
+ "RTG": 972,
1040
+ "QIS": 973,
1041
+ "FVS": 974,
1042
+ "PAS": 975,
1043
+ "KEK": 976,
1044
+ "QPV": 977,
1045
+ "KDG": 978,
1046
+ "KAV": 979,
1047
+ "TII": 980,
1048
+ "QLI": 981,
1049
+ "FAG": 982,
1050
+ "DAN": 983,
1051
+ "AKI": 984,
1052
+ "RIG": 985,
1053
+ "NDI": 986,
1054
+ "QPL": 987,
1055
+ "RTT": 988,
1056
+ "PLS": 989,
1057
+ "ERV": 990,
1058
+ "PW": 991,
1059
+ "NAI": 992,
1060
+ "QTG": 993,
1061
+ "QKL": 994,
1062
+ "TYG": 995,
1063
+ "EKK": 996,
1064
+ "EAR": 997,
1065
+ "TAM": 998,
1066
+ "KVL": 999,
1067
+ "FDG": 1000,
1068
+ "KTL": 1001,
1069
+ "KGS": 1002,
1070
+ "XXXXXXXXXXXXXXXX": 1003,
1071
+ "PTE": 1004,
1072
+ "REV": 1005,
1073
+ "DKI": 1006,
1074
+ "QQG": 1007,
1075
+ "DAF": 1008,
1076
+ "KKL": 1009,
1077
+ "DAQ": 1010,
1078
+ "KAA": 1011,
1079
+ "PSV": 1012,
1080
+ "FSV": 1013,
1081
+ "DNI": 1014,
1082
+ "FGV": 1015,
1083
+ "DTP": 1016,
1084
+ "PIS": 1017,
1085
+ "FLS": 1018,
1086
+ "PEE": 1019,
1087
+ "QEV": 1020,
1088
+ "KEI": 1021,
1089
+ "GLV": 1022,
1090
+ "FAE": 1023
1091
+ },
1092
+ "merges": [
1093
+ "A A",
1094
+ "S S",
1095
+ "T T",
1096
+ "G G",
1097
+ "L L",
1098
+ "A G",
1099
+ "L S",
1100
+ "T V",
1101
+ "A V",
1102
+ "A L",
1103
+ "A S",
1104
+ "D G",
1105
+ "T G",
1106
+ "E E",
1107
+ "T L",
1108
+ "T S",
1109
+ "D V",
1110
+ "A E",
1111
+ "D L",
1112
+ "S G",
1113
+ "A P",
1114
+ "R L",
1115
+ "V V",
1116
+ "S L",
1117
+ "T P",
1118
+ "T I",
1119
+ "E L",
1120
+ "S V",
1121
+ "A D",
1122
+ "N G",
1123
+ "A R",
1124
+ "E V",
1125
+ "Q L",
1126
+ "T D",
1127
+ "A I",
1128
+ "N L",
1129
+ "E G",
1130
+ "P V",
1131
+ "K L",
1132
+ "P G",
1133
+ "E I",
1134
+ "N V",
1135
+ "D I",
1136
+ "P L",
1137
+ "D S",
1138
+ "K K",
1139
+ "R V",
1140
+ "N I",
1141
+ "A Q",
1142
+ "P S",
1143
+ "A T",
1144
+ "E K",
1145
+ "E S",
1146
+ "R G",
1147
+ "Q Q",
1148
+ "N S",
1149
+ "D D",
1150
+ "A K",
1151
+ "R R",
1152
+ "V L",
1153
+ "A F",
1154
+ "T F",
1155
+ "R I",
1156
+ "P P",
1157
+ "Q V",
1158
+ "T E",
1159
+ "A N",
1160
+ "S I",
1161
+ "K V",
1162
+ "Q G",
1163
+ "K I",
1164
+ "R S",
1165
+ "T Y",
1166
+ "D P",
1167
+ "N N",
1168
+ "K G",
1169
+ "D E",
1170
+ "Q I",
1171
+ "F G",
1172
+ "V G",
1173
+ "Y L",
1174
+ "F L",
1175
+ "T N",
1176
+ "P I",
1177
+ "K S",
1178
+ "Q S",
1179
+ "P E",
1180
+ "A Y",
1181
+ "H L",
1182
+ "R E",
1183
+ "F S",
1184
+ "F V",
1185
+ "T K",
1186
+ "G L",
1187
+ "V S",
1188
+ "T Q",
1189
+ "D N",
1190
+ "I L",
1191
+ "R P",
1192
+ "G S",
1193
+ "K E",
1194
+ "I S",
1195
+ "D F",
1196
+ "T R",
1197
+ "D R",
1198
+ "D Y",
1199
+ "A H",
1200
+ "D K",
1201
+ "I G",
1202
+ "Q E",
1203
+ "A M",
1204
+ "Y G",
1205
+ "N E",
1206
+ "I V",
1207
+ "Y S",
1208
+ "N P",
1209
+ "E R",
1210
+ "Q P",
1211
+ "Y V",
1212
+ "M L",
1213
+ "T A",
1214
+ "Q R",
1215
+ "G V",
1216
+ "N D",
1217
+ "K P",
1218
+ "F E",
1219
+ "F I",
1220
+ "N K",
1221
+ "H S",
1222
+ "H G",
1223
+ "Q K",
1224
+ "C L",
1225
+ "H V",
1226
+ "N Y",
1227
+ "I E",
1228
+ "D Q",
1229
+ "W L",
1230
+ "R K",
1231
+ "C S",
1232
+ "N F",
1233
+ "R D",
1234
+ "E P",
1235
+ "R F",
1236
+ "AA L",
1237
+ "E D",
1238
+ "I I",
1239
+ "T M",
1240
+ "T C",
1241
+ "N Q",
1242
+ "T H",
1243
+ "A GG",
1244
+ "F D",
1245
+ "AA G",
1246
+ "R Q",
1247
+ "A C",
1248
+ "P D",
1249
+ "V I",
1250
+ "E Q",
1251
+ "L G",
1252
+ "Y I",
1253
+ "A W",
1254
+ "M S",
1255
+ "M V",
1256
+ "K D",
1257
+ "L V",
1258
+ "SS S",
1259
+ "N R",
1260
+ "C G",
1261
+ "H I",
1262
+ "P K",
1263
+ "T W",
1264
+ "R Y",
1265
+ "E F",
1266
+ "E N",
1267
+ "A DG",
1268
+ "A LL",
1269
+ "P Q",
1270
+ "E Y",
1271
+ "C V",
1272
+ "T AA",
1273
+ "P F",
1274
+ "X X",
1275
+ "T SS",
1276
+ "M G",
1277
+ "K Q",
1278
+ "I D",
1279
+ "P R",
1280
+ "T LS",
1281
+ "A SS",
1282
+ "Q D",
1283
+ "R N",
1284
+ "W S",
1285
+ "R H",
1286
+ "F K",
1287
+ "V D",
1288
+ "V E",
1289
+ "K N",
1290
+ "T GG",
1291
+ "F F",
1292
+ "AS G",
1293
+ "Q N",
1294
+ "A TT",
1295
+ "Q Y",
1296
+ "H P",
1297
+ "A TG",
1298
+ "A TV",
1299
+ "K Y",
1300
+ "V P",
1301
+ "A LS",
1302
+ "Q F",
1303
+ "I N",
1304
+ "T AG",
1305
+ "I K",
1306
+ "T AS",
1307
+ "S P",
1308
+ "Y Y",
1309
+ "F N",
1310
+ "L P",
1311
+ "I P",
1312
+ "Y D",
1313
+ "E H",
1314
+ "T AV",
1315
+ "K R",
1316
+ "S D",
1317
+ "V R",
1318
+ "A TL",
1319
+ "G D",
1320
+ "E M",
1321
+ "T LL",
1322
+ "Q H",
1323
+ "L D",
1324
+ "Y R",
1325
+ "AA V",
1326
+ "T AL",
1327
+ "A TS",
1328
+ "K F",
1329
+ "GG G",
1330
+ "C P",
1331
+ "A DV",
1332
+ "S E",
1333
+ "LS G",
1334
+ "AE L",
1335
+ "AG L",
1336
+ "S F",
1337
+ "Y N",
1338
+ "D H",
1339
+ "P N",
1340
+ "T AP",
1341
+ "V N",
1342
+ "A DL",
1343
+ "LL L",
1344
+ "SS G",
1345
+ "AS L",
1346
+ "SS L",
1347
+ "F R",
1348
+ "Y E",
1349
+ "I R",
1350
+ "Y K",
1351
+ "A RL",
1352
+ "D M",
1353
+ "H H",
1354
+ "W G",
1355
+ "F P",
1356
+ "V K",
1357
+ "EE L",
1358
+ "I Q",
1359
+ "AA S",
1360
+ "LS L",
1361
+ "C R",
1362
+ "T DG",
1363
+ "TS G",
1364
+ "M P",
1365
+ "AL G",
1366
+ "A NG",
1367
+ "AV L",
1368
+ "H R",
1369
+ "C I",
1370
+ "AA AA",
1371
+ "V F",
1372
+ "TT G",
1373
+ "M E",
1374
+ "Y F",
1375
+ "S N",
1376
+ "M K",
1377
+ "T AE",
1378
+ "A EE",
1379
+ "Y P",
1380
+ "H E",
1381
+ "M I",
1382
+ "C E",
1383
+ "V Q",
1384
+ "T AT",
1385
+ "Y Q",
1386
+ "A TP",
1387
+ "TT S",
1388
+ "G E",
1389
+ "LL S",
1390
+ "AG S",
1391
+ "T EE",
1392
+ "F Q",
1393
+ "AG V",
1394
+ "G R",
1395
+ "W V",
1396
+ "XX XX",
1397
+ "TT L",
1398
+ "TV S",
1399
+ "G I",
1400
+ "C D",
1401
+ "TS L",
1402
+ "H D",
1403
+ "T DV",
1404
+ "M D",
1405
+ "A TI",
1406
+ "C K",
1407
+ "A TD",
1408
+ "TT V",
1409
+ "TG L",
1410
+ "M R",
1411
+ "T AD",
1412
+ "H F",
1413
+ "DG S",
1414
+ "SG S",
1415
+ "H Q",
1416
+ "C Q",
1417
+ "GG S",
1418
+ "W R",
1419
+ "I F",
1420
+ "LL G",
1421
+ "T DL",
1422
+ "DS DS",
1423
+ "A QL",
1424
+ "DV L",
1425
+ "M N",
1426
+ "M Q",
1427
+ "AS V",
1428
+ "TG S",
1429
+ "TV L",
1430
+ "H K",
1431
+ "G N",
1432
+ "DG L",
1433
+ "I Y",
1434
+ "T EL",
1435
+ "D W",
1436
+ "T AI",
1437
+ "G P",
1438
+ "AV V",
1439
+ "GG L",
1440
+ "EV L",
1441
+ "SG L",
1442
+ "C N",
1443
+ "F Y",
1444
+ "D AA",
1445
+ "SS V",
1446
+ "H Y",
1447
+ "AV G",
1448
+ "H N",
1449
+ "P Y",
1450
+ "S R",
1451
+ "S K",
1452
+ "AP G",
1453
+ "AL V",
1454
+ "D GG",
1455
+ "SV L",
1456
+ "AP L",
1457
+ "RV L",
1458
+ "LS V",
1459
+ "T EV",
1460
+ "R M",
1461
+ "AL P",
1462
+ "R W",
1463
+ "AV S",
1464
+ "DG V",
1465
+ "TP L",
1466
+ "A KL",
1467
+ "TS V",
1468
+ "AA P",
1469
+ "VV L",
1470
+ "AL R",
1471
+ "E C",
1472
+ "T EI",
1473
+ "TT TT",
1474
+ "SV S",
1475
+ "T AR",
1476
+ "T NG",
1477
+ "T EG",
1478
+ "E W",
1479
+ "AE G",
1480
+ "AP V",
1481
+ "Q M",
1482
+ "TV V",
1483
+ "T AQ",
1484
+ "P H",
1485
+ "C F",
1486
+ "A NL",
1487
+ "T ES",
1488
+ "K M",
1489
+ "TP S",
1490
+ "GG V",
1491
+ "RL V",
1492
+ "N M",
1493
+ "PV L",
1494
+ "TL G",
1495
+ "D AG",
1496
+ "SS SS",
1497
+ "D C",
1498
+ "W I",
1499
+ "E LL",
1500
+ "EG L",
1501
+ "R LL",
1502
+ "EL G",
1503
+ "A NV",
1504
+ "S Y",
1505
+ "E AA",
1506
+ "N H",
1507
+ "TV G",
1508
+ "SL V",
1509
+ "QQ QQ",
1510
+ "P AA",
1511
+ "W Q",
1512
+ "E AL",
1513
+ "K H",
1514
+ "T NV",
1515
+ "S Q",
1516
+ "TG V",
1517
+ "M F",
1518
+ "D AL",
1519
+ "P AG",
1520
+ "D AV",
1521
+ "D LS",
1522
+ "TP V",
1523
+ "AE V",
1524
+ "DI L",
1525
+ "T NL",
1526
+ "PS P",
1527
+ "TL V",
1528
+ "W N",
1529
+ "W K",
1530
+ "T RL",
1531
+ "TT P",
1532
+ "AR G",
1533
+ "R C",
1534
+ "D LL",
1535
+ "DL V",
1536
+ "T AK",
1537
+ "PG L",
1538
+ "DL G",
1539
+ "SL G",
1540
+ "R AA",
1541
+ "DV V",
1542
+ "N GG",
1543
+ "SG V",
1544
+ "SS I",
1545
+ "TI S",
1546
+ "TP G",
1547
+ "RG L",
1548
+ "N C",
1549
+ "EE V",
1550
+ "T EK",
1551
+ "VV V",
1552
+ "F H",
1553
+ "Y H",
1554
+ "EI L",
1555
+ "T AN",
1556
+ "NG L",
1557
+ "AP S",
1558
+ "I H",
1559
+ "W E",
1560
+ "T QL",
1561
+ "RL G",
1562
+ "VV G",
1563
+ "T NI",
1564
+ "TL P",
1565
+ "SS P",
1566
+ "TT I",
1567
+ "D AS",
1568
+ "T KL",
1569
+ "NV L",
1570
+ "Q LL",
1571
+ "TD S",
1572
+ "AI L",
1573
+ "A KK",
1574
+ "PL P",
1575
+ "Q C",
1576
+ "D SL",
1577
+ "EL V",
1578
+ "DV S",
1579
+ "A NI",
1580
+ "N W",
1581
+ "A NS",
1582
+ "Q W",
1583
+ "TS P",
1584
+ "Q AA",
1585
+ "T NS",
1586
+ "D SS",
1587
+ "T AF",
1588
+ "PG S",
1589
+ "D SG",
1590
+ "VV S",
1591
+ "P M",
1592
+ "G K",
1593
+ "D AD",
1594
+ "LL V",
1595
+ "AG N",
1596
+ "LS P",
1597
+ "E SL",
1598
+ "NG S",
1599
+ "D DV",
1600
+ "E AV",
1601
+ "D EL",
1602
+ "TI L",
1603
+ "SV G",
1604
+ "NG V",
1605
+ "EE I",
1606
+ "AI G",
1607
+ "XXXX XXXX",
1608
+ "D DL",
1609
+ "AG I",
1610
+ "AS I",
1611
+ "C Y",
1612
+ "F M",
1613
+ "AA R",
1614
+ "AA E",
1615
+ "AA I",
1616
+ "NI L",
1617
+ "T KK",
1618
+ "TS I",
1619
+ "T KV",
1620
+ "TV N",
1621
+ "D TL",
1622
+ "M Y",
1623
+ "QG L",
1624
+ "AG E",
1625
+ "D EE",
1626
+ "AD S",
1627
+ "AG R",
1628
+ "SL P",
1629
+ "AE S",
1630
+ "AS P",
1631
+ "LL E",
1632
+ "LS I",
1633
+ "D TV",
1634
+ "D TT",
1635
+ "PV G",
1636
+ "GG GG",
1637
+ "T RV",
1638
+ "PG V",
1639
+ "R AL",
1640
+ "PV S",
1641
+ "EV S",
1642
+ "A YL",
1643
+ "K C",
1644
+ "AD I",
1645
+ "W F",
1646
+ "N SS",
1647
+ "T QV",
1648
+ "DS I",
1649
+ "Q AL",
1650
+ "PP P",
1651
+ "AR V",
1652
+ "EE E",
1653
+ "N TL",
1654
+ "D DG",
1655
+ "P DG",
1656
+ "RL R",
1657
+ "LL R",
1658
+ "D SV",
1659
+ "TT E",
1660
+ "EE G",
1661
+ "C H",
1662
+ "K W",
1663
+ "T KI",
1664
+ "AE I",
1665
+ "LS E",
1666
+ "M M",
1667
+ "AQ G",
1668
+ "NV S",
1669
+ "DL P",
1670
+ "EG V",
1671
+ "D EV",
1672
+ "Q QL",
1673
+ "E KL",
1674
+ "Y W",
1675
+ "R EL",
1676
+ "RI L",
1677
+ "LL P",
1678
+ "PL V",
1679
+ "DI S",
1680
+ "T AY",
1681
+ "AF L",
1682
+ "PV P",
1683
+ "Q SL",
1684
+ "TV P",
1685
+ "N AA",
1686
+ "AI S",
1687
+ "E RL",
1688
+ "NL G",
1689
+ "R AV",
1690
+ "AQ V",
1691
+ "EE S",
1692
+ "DG I",
1693
+ "TI G",
1694
+ "EG S",
1695
+ "AP P",
1696
+ "PL G",
1697
+ "LL K",
1698
+ "N LS",
1699
+ "TD I",
1700
+ "NL V",
1701
+ "QL V",
1702
+ "TP P",
1703
+ "R LS",
1704
+ "EE K",
1705
+ "D RL",
1706
+ "E TL",
1707
+ "VL G",
1708
+ "T RS",
1709
+ "TG N",
1710
+ "T QI",
1711
+ "T RG",
1712
+ "A HL",
1713
+ "EL P",
1714
+ "F C",
1715
+ "T NN",
1716
+ "DSDS DSDS",
1717
+ "TG I",
1718
+ "D TS",
1719
+ "RV S",
1720
+ "EI S",
1721
+ "M H",
1722
+ "KG L",
1723
+ "TI V",
1724
+ "TV E",
1725
+ "TL N",
1726
+ "D DI",
1727
+ "QL G",
1728
+ "D AE",
1729
+ "TV I",
1730
+ "DV G",
1731
+ "T QG",
1732
+ "FG L",
1733
+ "T KS",
1734
+ "Q AV",
1735
+ "AR S",
1736
+ "KL V",
1737
+ "NI S",
1738
+ "D AP",
1739
+ "T QS",
1740
+ "DL I",
1741
+ "R GG",
1742
+ "W P",
1743
+ "AI V",
1744
+ "N SL",
1745
+ "DG K",
1746
+ "Y M",
1747
+ "ES I",
1748
+ "R RL",
1749
+ "R SL",
1750
+ "E LS",
1751
+ "P SS",
1752
+ "E GG",
1753
+ "EK V",
1754
+ "Q LS",
1755
+ "N TT",
1756
+ "R SS",
1757
+ "E SS",
1758
+ "E TT",
1759
+ "Q SS",
1760
+ "T RI",
1761
+ "P GG",
1762
+ "E AE",
1763
+ "KI L",
1764
+ "F SS",
1765
+ "EI V",
1766
+ "SI L",
1767
+ "TD P",
1768
+ "N SG",
1769
+ "RG S",
1770
+ "T RR",
1771
+ "AD P",
1772
+ "Q VV",
1773
+ "RV G",
1774
+ "T QQ",
1775
+ "DI V",
1776
+ "NV G",
1777
+ "K EL",
1778
+ "TL I",
1779
+ "Q RL",
1780
+ "E AG",
1781
+ "AK V",
1782
+ "QI L",
1783
+ "AV I",
1784
+ "N LL",
1785
+ "N AG",
1786
+ "Y C",
1787
+ "D TG",
1788
+ "N AS",
1789
+ "R AG",
1790
+ "NS I",
1791
+ "TV TV",
1792
+ "Q GG",
1793
+ "SG I",
1794
+ "KG V",
1795
+ "H M",
1796
+ "Q VL",
1797
+ "F GG",
1798
+ "E VV",
1799
+ "E SV",
1800
+ "Q EL",
1801
+ "K EE",
1802
+ "DV I",
1803
+ "E TV",
1804
+ "P C",
1805
+ "AF G",
1806
+ "EK I",
1807
+ "AL I",
1808
+ "H C",
1809
+ "E QL",
1810
+ "TF S",
1811
+ "TP I",
1812
+ "SI S",
1813
+ "F W",
1814
+ "RG V",
1815
+ "NI G",
1816
+ "Q TL",
1817
+ "E AS",
1818
+ "KL K",
1819
+ "NL I",
1820
+ "F SG",
1821
+ "R SG",
1822
+ "F DL",
1823
+ "PS I",
1824
+ "AV P",
1825
+ "T KG",
1826
+ "E DL",
1827
+ "KK KK",
1828
+ "R AR",
1829
+ "Q AG",
1830
+ "EK S",
1831
+ "EV G",
1832
+ "TV K",
1833
+ "N AL",
1834
+ "D AI",
1835
+ "VG L",
1836
+ "NG I",
1837
+ "D EI",
1838
+ "AK G",
1839
+ "TL K",
1840
+ "E DV",
1841
+ "E TS",
1842
+ "E SG",
1843
+ "P TT",
1844
+ "W Y",
1845
+ "K AL",
1846
+ "TV D",
1847
+ "KL G",
1848
+ "R DL",
1849
+ "Q SV",
1850
+ "YL G",
1851
+ "LS F",
1852
+ "D QL",
1853
+ "TS GS",
1854
+ "C SS",
1855
+ "D DS",
1856
+ "D AR",
1857
+ "P AP",
1858
+ "R VV",
1859
+ "N TS",
1860
+ "P AV",
1861
+ "Q AS",
1862
+ "AQ S",
1863
+ "LS K",
1864
+ "E DG",
1865
+ "C C",
1866
+ "SL I",
1867
+ "D TI",
1868
+ "N TG",
1869
+ "RR S",
1870
+ "EL I",
1871
+ "N AV",
1872
+ "EV I",
1873
+ "Q SG",
1874
+ "K LL",
1875
+ "D NL",
1876
+ "GG I",
1877
+ "K SS",
1878
+ "AA F",
1879
+ "RL P",
1880
+ "Q TV",
1881
+ "QV S",
1882
+ "PV I",
1883
+ "VL V",
1884
+ "AH G",
1885
+ "TF L",
1886
+ "N SV",
1887
+ "D PS",
1888
+ "AK S",
1889
+ "R AE",
1890
+ "P SG",
1891
+ "Q TT",
1892
+ "EK G",
1893
+ "KL I",
1894
+ "E NL",
1895
+ "R TL",
1896
+ "KK K",
1897
+ "LL I",
1898
+ "D RV",
1899
+ "F TG",
1900
+ "D AT",
1901
+ "N VV",
1902
+ "DV P",
1903
+ "AF V",
1904
+ "K SL",
1905
+ "DI G",
1906
+ "H W",
1907
+ "E PG",
1908
+ "D TD",
1909
+ "R RG",
1910
+ "PI L",
1911
+ "AA K",
1912
+ "FL G",
1913
+ "EI I",
1914
+ "QG S",
1915
+ "N NI",
1916
+ "N NL",
1917
+ "NV I",
1918
+ "SI G",
1919
+ "TG K",
1920
+ "R TV",
1921
+ "N DG",
1922
+ "KK S",
1923
+ "AA Q",
1924
+ "F TV",
1925
+ "N DL",
1926
+ "D ES",
1927
+ "R SV",
1928
+ "LL Q",
1929
+ "R DG",
1930
+ "AL K",
1931
+ "D EG",
1932
+ "AL E",
1933
+ "PE P",
1934
+ "TG P",
1935
+ "R AS",
1936
+ "EL K",
1937
+ "GL G",
1938
+ "D PV",
1939
+ "EK P",
1940
+ "D KL",
1941
+ "R EE",
1942
+ "RV I",
1943
+ "N TV",
1944
+ "KV S",
1945
+ "DI I",
1946
+ "KK I",
1947
+ "AM L",
1948
+ "TY L",
1949
+ "EI G",
1950
+ "F SL",
1951
+ "AY V",
1952
+ "F AA",
1953
+ "QV G",
1954
+ "SV I",
1955
+ "E TI",
1956
+ "Y GG",
1957
+ "VG V",
1958
+ "TY S",
1959
+ "KK V",
1960
+ "Q TI",
1961
+ "N TI",
1962
+ "FG S",
1963
+ "AF S",
1964
+ "EE EE",
1965
+ "RL I",
1966
+ "R DV",
1967
+ "VG S",
1968
+ "TF G",
1969
+ "AG P",
1970
+ "R QL",
1971
+ "T RE",
1972
+ "R PG",
1973
+ "KI S",
1974
+ "AL Q",
1975
+ "H LL",
1976
+ "AR I",
1977
+ "E AP",
1978
+ "N NS",
1979
+ "Q TS",
1980
+ "EG I",
1981
+ "F DV",
1982
+ "E PV",
1983
+ "T RP",
1984
+ "VV I",
1985
+ "NI V",
1986
+ "K AG",
1987
+ "N DV",
1988
+ "D NG",
1989
+ "QQ V",
1990
+ "KK G",
1991
+ "Q SI",
1992
+ "N EL",
1993
+ "QG V",
1994
+ "D NV",
1995
+ "K LS",
1996
+ "T AH",
1997
+ "Q EE",
1998
+ "SV P",
1999
+ "AS F",
2000
+ "AP I",
2001
+ "K DL",
2002
+ "Q AE",
2003
+ "E DI",
2004
+ "R PV",
2005
+ "R PL",
2006
+ "W H",
2007
+ "Y TL",
2008
+ "D PG",
2009
+ "N NG",
2010
+ "Y SG",
2011
+ "D PL",
2012
+ "RI V",
2013
+ "NI I",
2014
+ "E AI",
2015
+ "E TG",
2016
+ "RI S",
2017
+ "E PL",
2018
+ "D KV",
2019
+ "P LL",
2020
+ "Y TV",
2021
+ "PI G",
2022
+ "F TL",
2023
+ "P SL",
2024
+ "AQ I",
2025
+ "W M",
2026
+ "N AT",
2027
+ "T HL",
2028
+ "D NS",
2029
+ "Q DL",
2030
+ "Q AR",
2031
+ "Q PG",
2032
+ "P AL",
2033
+ "C M",
2034
+ "Y TG",
2035
+ "TF V",
2036
+ "Y SS",
2037
+ "R TG",
2038
+ "QI S",
2039
+ "FV S",
2040
+ "P AS",
2041
+ "K EK",
2042
+ "Q PV",
2043
+ "K DG",
2044
+ "K AV",
2045
+ "TI I",
2046
+ "QL I",
2047
+ "F AG",
2048
+ "D AN",
2049
+ "AK I",
2050
+ "RI G",
2051
+ "N DI",
2052
+ "Q PL",
2053
+ "R TT",
2054
+ "P LS",
2055
+ "E RV",
2056
+ "P W",
2057
+ "N AI",
2058
+ "Q TG",
2059
+ "Q KL",
2060
+ "TY G",
2061
+ "E KK",
2062
+ "E AR",
2063
+ "T AM",
2064
+ "K VL",
2065
+ "F DG",
2066
+ "K TL",
2067
+ "KG S",
2068
+ "XXXXXXXX XXXXXXXX",
2069
+ "P TE",
2070
+ "R EV",
2071
+ "D KI",
2072
+ "QQ G",
2073
+ "D AF",
2074
+ "K KL",
2075
+ "D AQ",
2076
+ "K AA",
2077
+ "P SV",
2078
+ "F SV",
2079
+ "D NI",
2080
+ "FG V",
2081
+ "D TP",
2082
+ "PI S",
2083
+ "F LS",
2084
+ "P EE",
2085
+ "Q EV",
2086
+ "K EI",
2087
+ "GL V",
2088
+ "F AE"
2089
+ ]
2090
+ }
2091
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "mask_token": "[MASK]",
47
+ "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "[PAD]",
49
+ "sep_token": "[SEP]",
50
+ "tokenizer_class": "PreTrainedTokenizerFast",
51
+ "unk_token": "[UNK]"
52
+ }
trainer_state.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5.84649133682251,
3
+ "best_model_checkpoint": "./results/models/checkpoint-23424",
4
+ "epoch": 12.0,
5
+ "eval_steps": 500,
6
+ "global_step": 23424,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.26,
13
+ "learning_rate": 0.009948770491803278,
14
+ "loss": 5.9831,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.51,
19
+ "learning_rate": 0.009897540983606557,
20
+ "loss": 5.9498,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.77,
25
+ "learning_rate": 0.009846311475409836,
26
+ "loss": 5.9616,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_loss": 5.937765121459961,
32
+ "eval_runtime": 3.4294,
33
+ "eval_samples_per_second": 291.596,
34
+ "eval_steps_per_second": 0.583,
35
+ "step": 1952
36
+ },
37
+ {
38
+ "epoch": 1.02,
39
+ "learning_rate": 0.009795081967213116,
40
+ "loss": 5.9374,
41
+ "step": 2000
42
+ },
43
+ {
44
+ "epoch": 1.28,
45
+ "learning_rate": 0.009743852459016393,
46
+ "loss": 5.9391,
47
+ "step": 2500
48
+ },
49
+ {
50
+ "epoch": 1.54,
51
+ "learning_rate": 0.009692622950819673,
52
+ "loss": 5.9287,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.79,
57
+ "learning_rate": 0.00964139344262295,
58
+ "loss": 5.9149,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 2.0,
63
+ "eval_loss": 5.907990455627441,
64
+ "eval_runtime": 3.1854,
65
+ "eval_samples_per_second": 313.928,
66
+ "eval_steps_per_second": 0.628,
67
+ "step": 3904
68
+ },
69
+ {
70
+ "epoch": 2.05,
71
+ "learning_rate": 0.00959016393442623,
72
+ "loss": 5.9179,
73
+ "step": 4000
74
+ },
75
+ {
76
+ "epoch": 2.31,
77
+ "learning_rate": 0.009538934426229509,
78
+ "loss": 5.9105,
79
+ "step": 4500
80
+ },
81
+ {
82
+ "epoch": 2.56,
83
+ "learning_rate": 0.009487704918032787,
84
+ "loss": 5.9086,
85
+ "step": 5000
86
+ },
87
+ {
88
+ "epoch": 2.82,
89
+ "learning_rate": 0.009436475409836066,
90
+ "loss": 5.899,
91
+ "step": 5500
92
+ },
93
+ {
94
+ "epoch": 3.0,
95
+ "eval_loss": 5.894569396972656,
96
+ "eval_runtime": 3.0831,
97
+ "eval_samples_per_second": 324.347,
98
+ "eval_steps_per_second": 0.649,
99
+ "step": 5856
100
+ },
101
+ {
102
+ "epoch": 3.07,
103
+ "learning_rate": 0.009385245901639345,
104
+ "loss": 5.8975,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 3.33,
109
+ "learning_rate": 0.009334016393442625,
110
+ "loss": 5.8936,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 3.59,
115
+ "learning_rate": 0.009282786885245902,
116
+ "loss": 5.8886,
117
+ "step": 7000
118
+ },
119
+ {
120
+ "epoch": 3.84,
121
+ "learning_rate": 0.00923155737704918,
122
+ "loss": 5.8882,
123
+ "step": 7500
124
+ },
125
+ {
126
+ "epoch": 4.0,
127
+ "eval_loss": 5.879088878631592,
128
+ "eval_runtime": 3.2638,
129
+ "eval_samples_per_second": 306.393,
130
+ "eval_steps_per_second": 0.613,
131
+ "step": 7808
132
+ },
133
+ {
134
+ "epoch": 4.1,
135
+ "learning_rate": 0.009180327868852459,
136
+ "loss": 5.883,
137
+ "step": 8000
138
+ },
139
+ {
140
+ "epoch": 4.35,
141
+ "learning_rate": 0.009129098360655738,
142
+ "loss": 5.879,
143
+ "step": 8500
144
+ },
145
+ {
146
+ "epoch": 4.61,
147
+ "learning_rate": 0.009077868852459018,
148
+ "loss": 5.8752,
149
+ "step": 9000
150
+ },
151
+ {
152
+ "epoch": 4.87,
153
+ "learning_rate": 0.009026639344262295,
154
+ "loss": 5.8742,
155
+ "step": 9500
156
+ },
157
+ {
158
+ "epoch": 5.0,
159
+ "eval_loss": 5.866305828094482,
160
+ "eval_runtime": 3.2,
161
+ "eval_samples_per_second": 312.496,
162
+ "eval_steps_per_second": 0.625,
163
+ "step": 9760
164
+ },
165
+ {
166
+ "epoch": 5.12,
167
+ "learning_rate": 0.008975409836065575,
168
+ "loss": 5.8721,
169
+ "step": 10000
170
+ },
171
+ {
172
+ "epoch": 5.38,
173
+ "learning_rate": 0.008924180327868852,
174
+ "loss": 5.8674,
175
+ "step": 10500
176
+ },
177
+ {
178
+ "epoch": 5.64,
179
+ "learning_rate": 0.008872950819672131,
180
+ "loss": 5.8722,
181
+ "step": 11000
182
+ },
183
+ {
184
+ "epoch": 5.89,
185
+ "learning_rate": 0.00882172131147541,
186
+ "loss": 5.8702,
187
+ "step": 11500
188
+ },
189
+ {
190
+ "epoch": 6.0,
191
+ "eval_loss": 5.863623142242432,
192
+ "eval_runtime": 3.1064,
193
+ "eval_samples_per_second": 321.914,
194
+ "eval_steps_per_second": 0.644,
195
+ "step": 11712
196
+ },
197
+ {
198
+ "epoch": 6.15,
199
+ "learning_rate": 0.008770491803278688,
200
+ "loss": 5.8684,
201
+ "step": 12000
202
+ },
203
+ {
204
+ "epoch": 6.4,
205
+ "learning_rate": 0.008719262295081968,
206
+ "loss": 5.8664,
207
+ "step": 12500
208
+ },
209
+ {
210
+ "epoch": 6.66,
211
+ "learning_rate": 0.008668032786885245,
212
+ "loss": 5.8657,
213
+ "step": 13000
214
+ },
215
+ {
216
+ "epoch": 6.92,
217
+ "learning_rate": 0.008616803278688525,
218
+ "loss": 5.8616,
219
+ "step": 13500
220
+ },
221
+ {
222
+ "epoch": 7.0,
223
+ "eval_loss": 5.859433174133301,
224
+ "eval_runtime": 3.1303,
225
+ "eval_samples_per_second": 319.454,
226
+ "eval_steps_per_second": 0.639,
227
+ "step": 13664
228
+ },
229
+ {
230
+ "epoch": 7.17,
231
+ "learning_rate": 0.008565573770491804,
232
+ "loss": 5.8638,
233
+ "step": 14000
234
+ },
235
+ {
236
+ "epoch": 7.43,
237
+ "learning_rate": 0.008514344262295082,
238
+ "loss": 5.8628,
239
+ "step": 14500
240
+ },
241
+ {
242
+ "epoch": 7.68,
243
+ "learning_rate": 0.008463114754098361,
244
+ "loss": 5.8659,
245
+ "step": 15000
246
+ },
247
+ {
248
+ "epoch": 7.94,
249
+ "learning_rate": 0.008411885245901638,
250
+ "loss": 5.8659,
251
+ "step": 15500
252
+ },
253
+ {
254
+ "epoch": 8.0,
255
+ "eval_loss": 5.862513065338135,
256
+ "eval_runtime": 3.0899,
257
+ "eval_samples_per_second": 323.637,
258
+ "eval_steps_per_second": 0.647,
259
+ "step": 15616
260
+ },
261
+ {
262
+ "epoch": 8.2,
263
+ "learning_rate": 0.008360655737704918,
264
+ "loss": 5.8653,
265
+ "step": 16000
266
+ },
267
+ {
268
+ "epoch": 8.45,
269
+ "learning_rate": 0.008309426229508197,
270
+ "loss": 5.8625,
271
+ "step": 16500
272
+ },
273
+ {
274
+ "epoch": 8.71,
275
+ "learning_rate": 0.008258196721311475,
276
+ "loss": 5.8673,
277
+ "step": 17000
278
+ },
279
+ {
280
+ "epoch": 8.97,
281
+ "learning_rate": 0.008206967213114754,
282
+ "loss": 5.8662,
283
+ "step": 17500
284
+ },
285
+ {
286
+ "epoch": 9.0,
287
+ "eval_loss": 5.861349105834961,
288
+ "eval_runtime": 3.0909,
289
+ "eval_samples_per_second": 323.532,
290
+ "eval_steps_per_second": 0.647,
291
+ "step": 17568
292
+ },
293
+ {
294
+ "epoch": 9.22,
295
+ "learning_rate": 0.008155737704918033,
296
+ "loss": 5.8644,
297
+ "step": 18000
298
+ },
299
+ {
300
+ "epoch": 9.48,
301
+ "learning_rate": 0.008104508196721313,
302
+ "loss": 5.8615,
303
+ "step": 18500
304
+ },
305
+ {
306
+ "epoch": 9.73,
307
+ "learning_rate": 0.00805327868852459,
308
+ "loss": 5.8613,
309
+ "step": 19000
310
+ },
311
+ {
312
+ "epoch": 9.99,
313
+ "learning_rate": 0.00800204918032787,
314
+ "loss": 5.8591,
315
+ "step": 19500
316
+ },
317
+ {
318
+ "epoch": 10.0,
319
+ "eval_loss": 5.853126525878906,
320
+ "eval_runtime": 3.1333,
321
+ "eval_samples_per_second": 319.15,
322
+ "eval_steps_per_second": 0.638,
323
+ "step": 19520
324
+ },
325
+ {
326
+ "epoch": 10.25,
327
+ "learning_rate": 0.007950819672131147,
328
+ "loss": 5.8565,
329
+ "step": 20000
330
+ },
331
+ {
332
+ "epoch": 10.5,
333
+ "learning_rate": 0.007899590163934427,
334
+ "loss": 5.8547,
335
+ "step": 20500
336
+ },
337
+ {
338
+ "epoch": 10.76,
339
+ "learning_rate": 0.007848360655737706,
340
+ "loss": 5.8554,
341
+ "step": 21000
342
+ },
343
+ {
344
+ "epoch": 11.0,
345
+ "eval_loss": 5.850937843322754,
346
+ "eval_runtime": 3.092,
347
+ "eval_samples_per_second": 323.419,
348
+ "eval_steps_per_second": 0.647,
349
+ "step": 21472
350
+ },
351
+ {
352
+ "epoch": 11.01,
353
+ "learning_rate": 0.0077971311475409835,
354
+ "loss": 5.8557,
355
+ "step": 21500
356
+ },
357
+ {
358
+ "epoch": 11.27,
359
+ "learning_rate": 0.007745901639344263,
360
+ "loss": 5.8544,
361
+ "step": 22000
362
+ },
363
+ {
364
+ "epoch": 11.53,
365
+ "learning_rate": 0.007694672131147541,
366
+ "loss": 5.8536,
367
+ "step": 22500
368
+ },
369
+ {
370
+ "epoch": 11.78,
371
+ "learning_rate": 0.0076434426229508206,
372
+ "loss": 5.8531,
373
+ "step": 23000
374
+ },
375
+ {
376
+ "epoch": 12.0,
377
+ "eval_loss": 5.84649133682251,
378
+ "eval_runtime": 3.1942,
379
+ "eval_samples_per_second": 313.065,
380
+ "eval_steps_per_second": 0.626,
381
+ "step": 23424
382
+ }
383
+ ],
384
+ "logging_steps": 500,
385
+ "max_steps": 97600,
386
+ "num_input_tokens_seen": 0,
387
+ "num_train_epochs": 50,
388
+ "save_steps": 500,
389
+ "total_flos": 5.51042373648384e+17,
390
+ "train_batch_size": 512,
391
+ "trial_name": null,
392
+ "trial_params": null
393
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f101afae5679ed1d12288811ec492221e83faad0b24f7186c4d410ed510c20
3
+ size 4664