Model save
Browse files- README.md +168 -0
- final/added_tokens.json +3 -0
- final/config.json +42 -0
- final/model.safetensors +3 -0
- final/special_tokens_map.json +15 -0
- final/spm.model +3 -0
- final/tokenizer.json +3 -0
- final/tokenizer_config.json +859 -0
- final/training_args.bin +3 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/mdeberta-v3-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: gemma-fineweb-edu-scorer-mdeberta-binary-lr5e-05-20250411_140230
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# gemma-fineweb-edu-scorer-mdeberta-binary-lr5e-05-20250411_140230
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1614
|
| 24 |
+
- Precision: 1.0
|
| 25 |
+
- Recall: 1.0
|
| 26 |
+
- F1 Macro: 1.0
|
| 27 |
+
- Accuracy: 1.0
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 32
|
| 49 |
+
- seed: 0
|
| 50 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 20
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
|
| 57 |
+
|:-------------:|:-------:|:------:|:---------------:|:---------:|:------:|:--------:|:--------:|
|
| 58 |
+
| No log | 0 | 0 | 0.2170 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 59 |
+
| 0.1238 | 0.1954 | 1000 | 0.1458 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 60 |
+
| 0.1143 | 0.3908 | 2000 | 0.1076 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 61 |
+
| 0.1208 | 0.5862 | 3000 | 0.1133 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 62 |
+
| 0.1031 | 0.7816 | 4000 | 0.1069 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 63 |
+
| 0.1045 | 0.9769 | 5000 | 0.1047 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 64 |
+
| 0.0974 | 1.1723 | 6000 | 0.1087 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 65 |
+
| 0.1337 | 1.3677 | 7000 | 0.1209 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 66 |
+
| 0.0864 | 1.5631 | 8000 | 0.1151 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 67 |
+
| 0.1049 | 1.7585 | 9000 | 0.1203 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 68 |
+
| 0.0915 | 1.9539 | 10000 | 0.1255 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 69 |
+
| 0.079 | 2.1493 | 11000 | 0.1369 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 70 |
+
| 0.0709 | 2.3447 | 12000 | 0.1167 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 71 |
+
| 0.0823 | 2.5401 | 13000 | 0.1257 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 72 |
+
| 0.0725 | 2.7354 | 14000 | 0.1114 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 73 |
+
| 0.066 | 2.9308 | 15000 | 0.1232 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 74 |
+
| 0.0354 | 3.1262 | 16000 | 0.1321 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 75 |
+
| 0.0486 | 3.3216 | 17000 | 0.1245 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 76 |
+
| 0.0466 | 3.5170 | 18000 | 0.1329 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 77 |
+
| 0.0523 | 3.7124 | 19000 | 0.1350 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 78 |
+
| 0.0614 | 3.9078 | 20000 | 0.1373 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 79 |
+
| 0.0349 | 4.1032 | 21000 | 0.1461 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 80 |
+
| 0.0315 | 4.2986 | 22000 | 0.1406 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 81 |
+
| 0.0337 | 4.4939 | 23000 | 0.1355 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 82 |
+
| 0.0345 | 4.6893 | 24000 | 0.1300 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 83 |
+
| 0.0324 | 4.8847 | 25000 | 0.1324 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 84 |
+
| 0.0247 | 5.0801 | 26000 | 0.1347 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 85 |
+
| 0.0306 | 5.2755 | 27000 | 0.1474 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 86 |
+
| 0.0267 | 5.4709 | 28000 | 0.1394 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 87 |
+
| 0.0204 | 5.6663 | 29000 | 0.1487 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 88 |
+
| 0.0266 | 5.8617 | 30000 | 0.1454 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 89 |
+
| 0.0188 | 6.0571 | 31000 | 0.1434 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 90 |
+
| 0.0192 | 6.2524 | 32000 | 0.1458 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 91 |
+
| 0.0246 | 6.4478 | 33000 | 0.1455 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 92 |
+
| 0.0219 | 6.6432 | 34000 | 0.1440 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 93 |
+
| 0.0231 | 6.8386 | 35000 | 0.1561 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 94 |
+
| 0.0185 | 7.0340 | 36000 | 0.1504 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 95 |
+
| 0.0163 | 7.2294 | 37000 | 0.1516 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 96 |
+
| 0.0186 | 7.4248 | 38000 | 0.1451 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 97 |
+
| 0.025 | 7.6202 | 39000 | 0.1423 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 98 |
+
| 0.0217 | 7.8156 | 40000 | 0.1453 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 99 |
+
| 0.0226 | 8.0109 | 41000 | 0.1584 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 100 |
+
| 0.0136 | 8.2063 | 42000 | 0.1589 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 101 |
+
| 0.0186 | 8.4017 | 43000 | 0.1518 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 102 |
+
| 0.0215 | 8.5971 | 44000 | 0.1459 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 103 |
+
| 0.0182 | 8.7925 | 45000 | 0.1437 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 104 |
+
| 0.0236 | 8.9879 | 46000 | 0.1409 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 105 |
+
| 0.0204 | 9.1833 | 47000 | 0.1514 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 106 |
+
| 0.0198 | 9.3787 | 48000 | 0.1617 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 107 |
+
| 0.0158 | 9.5741 | 49000 | 0.1366 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 108 |
+
| 0.0256 | 9.7694 | 50000 | 0.1450 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 109 |
+
| 0.0186 | 9.9648 | 51000 | 0.1525 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 110 |
+
| 0.0238 | 10.1602 | 52000 | 0.1658 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 111 |
+
| 0.0189 | 10.3556 | 53000 | 0.1442 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 112 |
+
| 0.0184 | 10.5510 | 54000 | 0.1495 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 113 |
+
| 0.0196 | 10.7464 | 55000 | 0.1428 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 114 |
+
| 0.0224 | 10.9418 | 56000 | 0.1606 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 115 |
+
| 0.018 | 11.1372 | 57000 | 0.1436 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 116 |
+
| 0.1813 | 11.3326 | 58000 | 0.1829 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 117 |
+
| 0.1888 | 11.5279 | 59000 | 0.1832 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 118 |
+
| 0.1826 | 11.7233 | 60000 | 0.1828 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 119 |
+
| 0.0227 | 11.9187 | 61000 | 0.1447 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 120 |
+
| 0.0162 | 12.1141 | 62000 | 0.1491 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 121 |
+
| 0.0212 | 12.3095 | 63000 | 0.1386 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 122 |
+
| 0.0124 | 12.5049 | 64000 | 0.1507 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 123 |
+
| 0.0162 | 12.7003 | 65000 | 0.1425 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 124 |
+
| 0.0122 | 12.8957 | 66000 | 0.1417 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 125 |
+
| 0.0105 | 13.0911 | 67000 | 0.1414 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 126 |
+
| 0.0114 | 13.2864 | 68000 | 0.1537 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 127 |
+
| 0.0083 | 13.4818 | 69000 | 0.1548 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 128 |
+
| 0.0084 | 13.6772 | 70000 | 0.1439 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 129 |
+
| 0.0113 | 13.8726 | 71000 | 0.1504 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 130 |
+
| 0.013 | 14.0680 | 72000 | 0.1480 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 131 |
+
| 0.0066 | 14.2634 | 73000 | 0.1544 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 132 |
+
| 0.0119 | 14.4588 | 74000 | 0.1509 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 133 |
+
| 0.0078 | 14.6542 | 75000 | 0.1546 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 134 |
+
| 0.0162 | 14.8496 | 76000 | 0.1513 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 135 |
+
| 0.0094 | 15.0449 | 77000 | 0.1571 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 136 |
+
| 0.0097 | 15.2403 | 78000 | 0.1646 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 137 |
+
| 0.0132 | 15.4357 | 79000 | 0.1505 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 138 |
+
| 0.0127 | 15.6311 | 80000 | 0.1539 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 139 |
+
| 0.0086 | 15.8265 | 81000 | 0.1572 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 140 |
+
| 0.0067 | 16.0219 | 82000 | 0.1583 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 141 |
+
| 0.007 | 16.2173 | 83000 | 0.1531 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 142 |
+
| 0.0117 | 16.4127 | 84000 | 0.1485 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 143 |
+
| 0.0156 | 16.6081 | 85000 | 0.1495 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 144 |
+
| 0.0089 | 16.8034 | 86000 | 0.1570 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 145 |
+
| 0.0075 | 16.9988 | 87000 | 0.1540 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 146 |
+
| 0.0068 | 17.1942 | 88000 | 0.1612 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 147 |
+
| 0.0074 | 17.3896 | 89000 | 0.1596 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 148 |
+
| 0.0117 | 17.5850 | 90000 | 0.1617 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 149 |
+
| 0.0116 | 17.7804 | 91000 | 0.1689 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 150 |
+
| 0.0064 | 17.9758 | 92000 | 0.1602 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 151 |
+
| 0.0079 | 18.1712 | 93000 | 0.1647 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 152 |
+
| 0.0051 | 18.3665 | 94000 | 0.1534 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 153 |
+
| 0.0069 | 18.5619 | 95000 | 0.1570 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 154 |
+
| 0.0062 | 18.7573 | 96000 | 0.1533 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 155 |
+
| 0.0048 | 18.9527 | 97000 | 0.1566 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 156 |
+
| 0.0142 | 19.1481 | 98000 | 0.1532 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 157 |
+
| 0.0147 | 19.3435 | 99000 | 0.1501 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 158 |
+
| 0.0085 | 19.5389 | 100000 | 0.1535 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 159 |
+
| 0.005 | 19.7343 | 101000 | 0.1599 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 160 |
+
| 0.0066 | 19.9297 | 102000 | 0.1614 | 1.0 | 1.0 | 1.0 | 1.0 |
|
| 161 |
+
|
| 162 |
+
|
| 163 |
+
### Framework versions
|
| 164 |
+
|
| 165 |
+
- Transformers 4.49.0
|
| 166 |
+
- Pytorch 2.6.0+cu124
|
| 167 |
+
- Datasets 3.3.2
|
| 168 |
+
- Tokenizers 0.21.1
|
final/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 250101
|
| 3 |
+
}
|
final/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.0,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0"
|
| 12 |
+
},
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"label2id": {
|
| 16 |
+
"LABEL_0": 0
|
| 17 |
+
},
|
| 18 |
+
"layer_norm_eps": 1e-07,
|
| 19 |
+
"legacy": true,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"max_relative_positions": -1,
|
| 22 |
+
"model_type": "deberta-v2",
|
| 23 |
+
"norm_rel_ebd": "layer_norm",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"pooler_dropout": 0,
|
| 28 |
+
"pooler_hidden_act": "gelu",
|
| 29 |
+
"pooler_hidden_size": 768,
|
| 30 |
+
"pos_att_type": [
|
| 31 |
+
"p2c",
|
| 32 |
+
"c2p"
|
| 33 |
+
],
|
| 34 |
+
"position_biased_input": false,
|
| 35 |
+
"position_buckets": 256,
|
| 36 |
+
"relative_attention": true,
|
| 37 |
+
"share_att_key": true,
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.49.0",
|
| 40 |
+
"type_vocab_size": 0,
|
| 41 |
+
"vocab_size": 251000
|
| 42 |
+
}
|
final/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e4b54339be91cb82d150601635c8c8fbac49c2572e2ef3ed8e083156df1016
|
| 3 |
+
size 1115265124
|
final/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
final/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
| 3 |
+
size 4305025
|
final/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ddbe35b768b22d6cd0d61a0a88ea3a188b7c00bbb7b825f9f247cf0b79c2365
|
| 3 |
+
size 16350764
|
final/tokenizer_config.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 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": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "β<extra_id_99>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"250002": {
|
| 44 |
+
"content": "β<extra_id_98>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"250003": {
|
| 52 |
+
"content": "β<extra_id_97>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"250004": {
|
| 60 |
+
"content": "β<extra_id_96>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"250005": {
|
| 68 |
+
"content": "β<extra_id_95>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"250006": {
|
| 76 |
+
"content": "β<extra_id_94>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"250007": {
|
| 84 |
+
"content": "β<extra_id_93>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"250008": {
|
| 92 |
+
"content": "β<extra_id_92>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"250009": {
|
| 100 |
+
"content": "β<extra_id_91>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"250010": {
|
| 108 |
+
"content": "β<extra_id_90>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"250011": {
|
| 116 |
+
"content": "β<extra_id_89>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"250012": {
|
| 124 |
+
"content": "β<extra_id_88>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"250013": {
|
| 132 |
+
"content": "β<extra_id_87>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"250014": {
|
| 140 |
+
"content": "β<extra_id_86>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"250015": {
|
| 148 |
+
"content": "β<extra_id_85>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"250016": {
|
| 156 |
+
"content": "β<extra_id_84>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"250017": {
|
| 164 |
+
"content": "β<extra_id_83>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"250018": {
|
| 172 |
+
"content": "β<extra_id_82>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"250019": {
|
| 180 |
+
"content": "β<extra_id_81>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"250020": {
|
| 188 |
+
"content": "β<extra_id_80>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"250021": {
|
| 196 |
+
"content": "β<extra_id_79>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"250022": {
|
| 204 |
+
"content": "β<extra_id_78>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"250023": {
|
| 212 |
+
"content": "β<extra_id_77>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"250024": {
|
| 220 |
+
"content": "β<extra_id_76>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"250025": {
|
| 228 |
+
"content": "β<extra_id_75>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"250026": {
|
| 236 |
+
"content": "β<extra_id_74>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"250027": {
|
| 244 |
+
"content": "β<extra_id_73>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": false
|
| 250 |
+
},
|
| 251 |
+
"250028": {
|
| 252 |
+
"content": "β<extra_id_72>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": false
|
| 258 |
+
},
|
| 259 |
+
"250029": {
|
| 260 |
+
"content": "β<extra_id_71>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": false
|
| 266 |
+
},
|
| 267 |
+
"250030": {
|
| 268 |
+
"content": "β<extra_id_70>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"250031": {
|
| 276 |
+
"content": "β<extra_id_69>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"250032": {
|
| 284 |
+
"content": "β<extra_id_68>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"250033": {
|
| 292 |
+
"content": "β<extra_id_67>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"250034": {
|
| 300 |
+
"content": "β<extra_id_66>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"250035": {
|
| 308 |
+
"content": "β<extra_id_65>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"250036": {
|
| 316 |
+
"content": "β<extra_id_64>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"250037": {
|
| 324 |
+
"content": "β<extra_id_63>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"250038": {
|
| 332 |
+
"content": "β<extra_id_62>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"250039": {
|
| 340 |
+
"content": "β<extra_id_61>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"250040": {
|
| 348 |
+
"content": "β<extra_id_60>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"250041": {
|
| 356 |
+
"content": "β<extra_id_59>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"250042": {
|
| 364 |
+
"content": "β<extra_id_58>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"250043": {
|
| 372 |
+
"content": "β<extra_id_57>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"250044": {
|
| 380 |
+
"content": "β<extra_id_56>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"250045": {
|
| 388 |
+
"content": "β<extra_id_55>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"250046": {
|
| 396 |
+
"content": "β<extra_id_54>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"250047": {
|
| 404 |
+
"content": "β<extra_id_53>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"250048": {
|
| 412 |
+
"content": "β<extra_id_52>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"250049": {
|
| 420 |
+
"content": "β<extra_id_51>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"250050": {
|
| 428 |
+
"content": "β<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"250051": {
|
| 436 |
+
"content": "β<extra_id_49>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"250052": {
|
| 444 |
+
"content": "β<extra_id_48>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"250053": {
|
| 452 |
+
"content": "β<extra_id_47>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"250054": {
|
| 460 |
+
"content": "β<extra_id_46>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"250055": {
|
| 468 |
+
"content": "β<extra_id_45>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"250056": {
|
| 476 |
+
"content": "β<extra_id_44>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"250057": {
|
| 484 |
+
"content": "β<extra_id_43>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"250058": {
|
| 492 |
+
"content": "β<extra_id_42>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"250059": {
|
| 500 |
+
"content": "β<extra_id_41>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"250060": {
|
| 508 |
+
"content": "β<extra_id_40>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"250061": {
|
| 516 |
+
"content": "β<extra_id_39>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"250062": {
|
| 524 |
+
"content": "β<extra_id_38>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"250063": {
|
| 532 |
+
"content": "β<extra_id_37>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"250064": {
|
| 540 |
+
"content": "β<extra_id_36>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"250065": {
|
| 548 |
+
"content": "β<extra_id_35>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"250066": {
|
| 556 |
+
"content": "β<extra_id_34>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"250067": {
|
| 564 |
+
"content": "β<extra_id_33>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"250068": {
|
| 572 |
+
"content": "β<extra_id_32>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"250069": {
|
| 580 |
+
"content": "β<extra_id_31>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"250070": {
|
| 588 |
+
"content": "β<extra_id_30>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"250071": {
|
| 596 |
+
"content": "β<extra_id_29>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"250072": {
|
| 604 |
+
"content": "β<extra_id_28>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"250073": {
|
| 612 |
+
"content": "β<extra_id_27>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"250074": {
|
| 620 |
+
"content": "β<extra_id_26>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"250075": {
|
| 628 |
+
"content": "β<extra_id_25>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"250076": {
|
| 636 |
+
"content": "β<extra_id_24>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"250077": {
|
| 644 |
+
"content": "β<extra_id_23>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"250078": {
|
| 652 |
+
"content": "β<extra_id_22>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"250079": {
|
| 660 |
+
"content": "β<extra_id_21>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"250080": {
|
| 668 |
+
"content": "β<extra_id_20>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"250081": {
|
| 676 |
+
"content": "β<extra_id_19>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"250082": {
|
| 684 |
+
"content": "β<extra_id_18>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"250083": {
|
| 692 |
+
"content": "β<extra_id_17>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"250084": {
|
| 700 |
+
"content": "β<extra_id_16>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"250085": {
|
| 708 |
+
"content": "β<extra_id_15>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"250086": {
|
| 716 |
+
"content": "β<extra_id_14>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"250087": {
|
| 724 |
+
"content": "β<extra_id_13>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"250088": {
|
| 732 |
+
"content": "β<extra_id_12>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"250089": {
|
| 740 |
+
"content": "β<extra_id_11>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"250090": {
|
| 748 |
+
"content": "β<extra_id_10>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"250091": {
|
| 756 |
+
"content": "β<extra_id_9>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"250092": {
|
| 764 |
+
"content": "β<extra_id_8>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"250093": {
|
| 772 |
+
"content": "β<extra_id_7>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"250094": {
|
| 780 |
+
"content": "β<extra_id_6>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"250095": {
|
| 788 |
+
"content": "β<extra_id_5>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"250096": {
|
| 796 |
+
"content": "β<extra_id_4>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"250097": {
|
| 804 |
+
"content": "β<extra_id_3>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"250098": {
|
| 812 |
+
"content": "β<extra_id_2>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"250099": {
|
| 820 |
+
"content": "β<extra_id_1>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"250100": {
|
| 828 |
+
"content": "β<extra_id_0>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"250101": {
|
| 836 |
+
"content": "[MASK]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
}
|
| 843 |
+
},
|
| 844 |
+
"bos_token": "[CLS]",
|
| 845 |
+
"clean_up_tokenization_spaces": false,
|
| 846 |
+
"cls_token": "[CLS]",
|
| 847 |
+
"do_lower_case": false,
|
| 848 |
+
"eos_token": "[SEP]",
|
| 849 |
+
"extra_special_tokens": {},
|
| 850 |
+
"mask_token": "[MASK]",
|
| 851 |
+
"model_max_length": 512,
|
| 852 |
+
"pad_token": "[PAD]",
|
| 853 |
+
"sep_token": "[SEP]",
|
| 854 |
+
"sp_model_kwargs": {},
|
| 855 |
+
"split_by_punct": false,
|
| 856 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 857 |
+
"unk_token": "[UNK]",
|
| 858 |
+
"vocab_type": "spm"
|
| 859 |
+
}
|
final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:056aaadc4cf2a14aae145e5dc8e1c7c35e9f5ef785f20eb72c83ed669016191f
|
| 3 |
+
size 5560
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1115265124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e4b54339be91cb82d150601635c8c8fbac49c2572e2ef3ed8e083156df1016
|
| 3 |
size 1115265124
|