Token Classification
GLiNER
ONNX
German
English
extractor
ner
zero-shot
pii-detection
privacy
multilingual
quantized
edge
Instructions to use patronus-studio/gliner2-multi-edge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use patronus-studio/gliner2-multi-edge with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("patronus-studio/gliner2-multi-edge") - Notebooks
- Google Colab
- Kaggle
Publish source-faithful fully quantized GLiNER2 edge bundle
Browse files- .gitattributes +5 -0
- added_tokens.json +13 -0
- classifier_fp32.onnx β classifier_int8.onnx +0 -0
- encoder_fp32.onnx β classifier_int8.ort +2 -2
- config.json +1 -2
- count_lstm_fp32.onnx β count_lstm_int8.onnx +0 -0
- count_lstm_int8.ort +3 -0
- count_pred_fp32.onnx β count_pred_int8.onnx +0 -0
- count_pred_int8.ort +3 -0
- edge_manifest.json +96 -0
- encoder_config/config.json +33 -0
- encoder_int8_int4.onnx +3 -0
- encoder_int8_int4.ort +3 -0
- gliner2_config.json +7 -7
- required_operators.config +18 -0
- span_rep_fp32.onnx β span_rep_int8.onnx +0 -0
- span_rep_int8.ort +3 -0
- special_tokens_map.json +123 -0
- spm.model +3 -0
- tokenizer.json +2 -2
- tokenizer_config.json +951 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
encoder_int8_int4.ort filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
span_rep_int8.ort filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
count_lstm_int8.ort filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
count_pred_int8.ort filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
classifier_int8.ort filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[C]": 250105,
|
| 3 |
+
"[DESCRIPTION]": 250111,
|
| 4 |
+
"[EXAMPLE]": 250109,
|
| 5 |
+
"[E]": 250106,
|
| 6 |
+
"[L]": 250108,
|
| 7 |
+
"[MASK]": 250101,
|
| 8 |
+
"[OUTPUT]": 250110,
|
| 9 |
+
"[P]": 250104,
|
| 10 |
+
"[R]": 250107,
|
| 11 |
+
"[SEP_STRUCT]": 250102,
|
| 12 |
+
"[SEP_TEXT]": 250103
|
| 13 |
+
}
|
classifier_fp32.onnx β classifier_int8.onnx
RENAMED
|
File without changes
|
encoder_fp32.onnx β classifier_int8.ort
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d73290acb7de470271c232dcbced84b7ff4071ceae88887c88216aa52b3825c1
|
| 3 |
+
size 1201328
|
config.json
CHANGED
|
@@ -1,10 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"_attn_implementation_autoset": true,
|
| 3 |
"counting_layer": "count_lstm",
|
| 4 |
-
"max_len": null,
|
| 5 |
"max_width": 8,
|
| 6 |
"model_name": "microsoft/mdeberta-v3-base",
|
| 7 |
"model_type": "extractor",
|
| 8 |
"token_pooling": "first",
|
| 9 |
-
"transformers_version": "
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_attn_implementation_autoset": true,
|
| 3 |
"counting_layer": "count_lstm",
|
|
|
|
| 4 |
"max_width": 8,
|
| 5 |
"model_name": "microsoft/mdeberta-v3-base",
|
| 6 |
"model_type": "extractor",
|
| 7 |
"token_pooling": "first",
|
| 8 |
+
"transformers_version": "4.51.0"
|
| 9 |
}
|
count_lstm_fp32.onnx β count_lstm_int8.onnx
RENAMED
|
File without changes
|
count_lstm_int8.ort
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b85e48edd9416282fece9dee3a07f462ce88e907a460ab5e874de6befd1c9f7
|
| 3 |
+
size 10729664
|
count_pred_fp32.onnx β count_pred_int8.onnx
RENAMED
|
File without changes
|
count_pred_int8.ort
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27739ae6faaf3048f8aacfad391939517be8e1a48198ccc1bd1413b71bc50ea6
|
| 3 |
+
size 1230392
|
edge_manifest.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"artifacts": {
|
| 3 |
+
"added_tokens.json": {
|
| 4 |
+
"sha256": "3ddf030c5aa61a4c2f6742d78b39329f8e2127bb9e212f758f968ff8787a6e03",
|
| 5 |
+
"size": 230
|
| 6 |
+
},
|
| 7 |
+
"classifier_int8.onnx": {
|
| 8 |
+
"sha256": "71e817694065379778d605677bd85d5cff5eb262263c697d5899095a518deffb",
|
| 9 |
+
"size": 1198146
|
| 10 |
+
},
|
| 11 |
+
"classifier_int8.ort": {
|
| 12 |
+
"sha256": "d73290acb7de470271c232dcbced84b7ff4071ceae88887c88216aa52b3825c1",
|
| 13 |
+
"size": 1201328
|
| 14 |
+
},
|
| 15 |
+
"config.json": {
|
| 16 |
+
"sha256": "7449d789b1be1423ce23549c02cc9bd87410d0fdf525a5468dcff4f0341f2986",
|
| 17 |
+
"size": 234
|
| 18 |
+
},
|
| 19 |
+
"count_lstm_int8.onnx": {
|
| 20 |
+
"sha256": "df6b9df86a4dabf8be60dd4387d98a0bdf506f03bc5e3a888d116471f0afafcc",
|
| 21 |
+
"size": 10716632
|
| 22 |
+
},
|
| 23 |
+
"count_lstm_int8.ort": {
|
| 24 |
+
"sha256": "8b85e48edd9416282fece9dee3a07f462ce88e907a460ab5e874de6befd1c9f7",
|
| 25 |
+
"size": 10729664
|
| 26 |
+
},
|
| 27 |
+
"count_pred_int8.onnx": {
|
| 28 |
+
"sha256": "758592271c097844b4f8ad1736c258d3b3ae36ed6ee482eb579a0fca9ae2b765",
|
| 29 |
+
"size": 1227508
|
| 30 |
+
},
|
| 31 |
+
"count_pred_int8.ort": {
|
| 32 |
+
"sha256": "27739ae6faaf3048f8aacfad391939517be8e1a48198ccc1bd1413b71bc50ea6",
|
| 33 |
+
"size": 1230392
|
| 34 |
+
},
|
| 35 |
+
"encoder_config/config.json": {
|
| 36 |
+
"sha256": "298b164a1c473a38bae4a20a5300b224765bf156d5de960078b42e75e172f7ad",
|
| 37 |
+
"size": 823
|
| 38 |
+
},
|
| 39 |
+
"encoder_int8_int4.onnx": {
|
| 40 |
+
"sha256": "72510eace9eb2763dfab84588c6f51dfc38f301d94421625c2084e322dfbba0a",
|
| 41 |
+
"size": 191446569
|
| 42 |
+
},
|
| 43 |
+
"encoder_int8_int4.ort": {
|
| 44 |
+
"sha256": "180d74159f27c2d583fca952a309d3b906afab5e3015968217a21572eaf068a1",
|
| 45 |
+
"size": 227806264
|
| 46 |
+
},
|
| 47 |
+
"gliner2_config.json": {
|
| 48 |
+
"sha256": "990ba8d73f19639d3cadafd11c7e1f1da1f3b97d8b50703355eacb6284a5d6c7",
|
| 49 |
+
"size": 349
|
| 50 |
+
},
|
| 51 |
+
"required_operators.config": {
|
| 52 |
+
"sha256": "a8fd7a76d357436ba81a144ae538b8746d06e7a854d225b69de5877fa5c0ab0f",
|
| 53 |
+
"size": 1059
|
| 54 |
+
},
|
| 55 |
+
"span_rep_int8.onnx": {
|
| 56 |
+
"sha256": "a509475d60f41ea4615451db5223c38aee793004d008785794bbadae878ac259",
|
| 57 |
+
"size": 16634452
|
| 58 |
+
},
|
| 59 |
+
"span_rep_int8.ort": {
|
| 60 |
+
"sha256": "d22b0031b2ff0d02b0d20010f8b23f625d900c11d855efc40ed696b6e4e9c715",
|
| 61 |
+
"size": 16646544
|
| 62 |
+
},
|
| 63 |
+
"special_tokens_map.json": {
|
| 64 |
+
"sha256": "84ea70143f533d7e99b393d87f20010887a9ac2cba955828ef313886e4e83f4f",
|
| 65 |
+
"size": 2414
|
| 66 |
+
},
|
| 67 |
+
"spm.model": {
|
| 68 |
+
"sha256": "13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3",
|
| 69 |
+
"size": 4305025
|
| 70 |
+
},
|
| 71 |
+
"tokenizer.json": {
|
| 72 |
+
"sha256": "a1c7ccb287623cccb7c03150953b6d2a09dd95122933393c9151c3a60095c97e",
|
| 73 |
+
"size": 16337353
|
| 74 |
+
},
|
| 75 |
+
"tokenizer_config.json": {
|
| 76 |
+
"sha256": "ccc4ee4b3054dc0fd736a0b3d4f9e867d55e7c2589020ec790a88892d574d8e2",
|
| 77 |
+
"size": 21626
|
| 78 |
+
}
|
| 79 |
+
},
|
| 80 |
+
"quantization": {
|
| 81 |
+
"activations": "float32",
|
| 82 |
+
"encoder_matmul_weights": "int8",
|
| 83 |
+
"other_fragment_matmul_weights": "int8",
|
| 84 |
+
"word_embeddings": "uint4"
|
| 85 |
+
},
|
| 86 |
+
"runtime": {
|
| 87 |
+
"format": "ORT Fixed",
|
| 88 |
+
"generator": "onnxruntime 1.27.0",
|
| 89 |
+
"prepacking_at_load": false,
|
| 90 |
+
"target_platform": "arm64"
|
| 91 |
+
},
|
| 92 |
+
"source": {
|
| 93 |
+
"repo": "fastino/gliner2-multi-v1",
|
| 94 |
+
"revision": "cc151f5b0ce4f7010c3ae8884527dd43dddf9d21"
|
| 95 |
+
}
|
| 96 |
+
}
|
encoder_config/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"attention_probs_dropout_prob": 0.1,
|
| 4 |
+
"hidden_act": "gelu",
|
| 5 |
+
"hidden_dropout_prob": 0.1,
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"intermediate_size": 3072,
|
| 9 |
+
"layer_norm_eps": 1e-07,
|
| 10 |
+
"legacy": true,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"max_relative_positions": -1,
|
| 13 |
+
"model_type": "deberta-v2",
|
| 14 |
+
"norm_rel_ebd": "layer_norm",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pooler_dropout": 0,
|
| 19 |
+
"pooler_hidden_act": "gelu",
|
| 20 |
+
"pooler_hidden_size": 768,
|
| 21 |
+
"pos_att_type": [
|
| 22 |
+
"p2c",
|
| 23 |
+
"c2p"
|
| 24 |
+
],
|
| 25 |
+
"position_biased_input": false,
|
| 26 |
+
"position_buckets": 256,
|
| 27 |
+
"relative_attention": true,
|
| 28 |
+
"share_att_key": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.51.0",
|
| 31 |
+
"type_vocab_size": 0,
|
| 32 |
+
"vocab_size": 250112
|
| 33 |
+
}
|
encoder_int8_int4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72510eace9eb2763dfab84588c6f51dfc38f301d94421625c2084e322dfbba0a
|
| 3 |
+
size 191446569
|
encoder_int8_int4.ort
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:180d74159f27c2d583fca952a309d3b906afab5e3015968217a21572eaf068a1
|
| 3 |
+
size 227806264
|
gliner2_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"max_width":
|
| 3 |
"special_tokens": {
|
| 4 |
"[P]": 250104,
|
| 5 |
"[E]": 250106,
|
|
@@ -7,11 +7,11 @@
|
|
| 7 |
"[SEP_TEXT]": 250103
|
| 8 |
},
|
| 9 |
"onnx_files": {
|
| 10 |
-
"
|
| 11 |
-
"encoder": "
|
| 12 |
-
"classifier": "
|
| 13 |
-
"span_rep": "
|
| 14 |
-
"count_embed": "
|
| 15 |
}
|
| 16 |
}
|
| 17 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"max_width": 8,
|
| 3 |
"special_tokens": {
|
| 4 |
"[P]": 250104,
|
| 5 |
"[E]": 250106,
|
|
|
|
| 7 |
"[SEP_TEXT]": 250103
|
| 8 |
},
|
| 9 |
"onnx_files": {
|
| 10 |
+
"quantized": {
|
| 11 |
+
"encoder": "encoder_int8_int4.onnx",
|
| 12 |
+
"classifier": "classifier_int8.onnx",
|
| 13 |
+
"span_rep": "span_rep_int8.onnx",
|
| 14 |
+
"count_embed": "count_lstm_int8.onnx"
|
| 15 |
}
|
| 16 |
}
|
| 17 |
+
}
|
required_operators.config
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Generated from model/s:
|
| 2 |
+
# - /Users/benediktveith/Documents/Uni/Semester 7/Playground/models/quant_rust/classifier_int8.ort
|
| 3 |
+
# - /Users/benediktveith/Documents/Uni/Semester 7/Playground/models/quant_rust/count_lstm_int8.ort
|
| 4 |
+
# - /Users/benediktveith/Documents/Uni/Semester 7/Playground/models/quant_rust/count_pred_int8.ort
|
| 5 |
+
# - /Users/benediktveith/Documents/Uni/Semester 7/Playground/models/quant_rust/encoder_int8_int4.ort
|
| 6 |
+
# - /Users/benediktveith/Documents/Uni/Semester 7/Playground/models/quant_rust/span_rep_int8.ort
|
| 7 |
+
ai.onnx;1;Not
|
| 8 |
+
ai.onnx;7;And
|
| 9 |
+
ai.onnx;9;Where
|
| 10 |
+
ai.onnx;11;DynamicQuantizeLinear,Range
|
| 11 |
+
ai.onnx;13;Abs,Ceil,Clip,Concat,Equal,Expand,Gather,GatherElements,Greater,Less,Log,MatMul,Neg,Shape,Sigmoid,Sign,Slice,Softmax,Sqrt,Squeeze,Tanh,Tile,Unsqueeze
|
| 12 |
+
ai.onnx;14;Add,Div,Mul,Relu,Reshape,Sub
|
| 13 |
+
ai.onnx;16;LessOrEqual,Where
|
| 14 |
+
ai.onnx;17;LayerNormalization
|
| 15 |
+
ai.onnx;19;Equal
|
| 16 |
+
ai.onnx;20;Gelu
|
| 17 |
+
ai.onnx;21;Cast,Identity,If,Reshape,Shape,Squeeze,Transpose,Unsqueeze
|
| 18 |
+
com.microsoft;1;DynamicQuantizeMatMul,FusedMatMul,GatherBlockQuantized,MatMulIntegerToFloat
|
span_rep_fp32.onnx β span_rep_int8.onnx
RENAMED
|
File without changes
|
span_rep_int8.ort
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d22b0031b2ff0d02b0d20010f8b23f625d900c11d855efc40ed696b6e4e9c715
|
| 3 |
+
size 16646544
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "[SEP_STRUCT]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "[SEP_TEXT]",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "[P]",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "[C]",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "[E]",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "[R]",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "[L]",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "[EXAMPLE]",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "[OUTPUT]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "[DESCRIPTION]",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
}
|
| 73 |
+
],
|
| 74 |
+
"bos_token": {
|
| 75 |
+
"content": "[CLS]",
|
| 76 |
+
"lstrip": false,
|
| 77 |
+
"normalized": false,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"single_word": false
|
| 80 |
+
},
|
| 81 |
+
"cls_token": {
|
| 82 |
+
"content": "[CLS]",
|
| 83 |
+
"lstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"rstrip": false,
|
| 86 |
+
"single_word": false
|
| 87 |
+
},
|
| 88 |
+
"eos_token": {
|
| 89 |
+
"content": "[SEP]",
|
| 90 |
+
"lstrip": false,
|
| 91 |
+
"normalized": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"single_word": false
|
| 94 |
+
},
|
| 95 |
+
"mask_token": {
|
| 96 |
+
"content": "[MASK]",
|
| 97 |
+
"lstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"rstrip": false,
|
| 100 |
+
"single_word": false
|
| 101 |
+
},
|
| 102 |
+
"pad_token": {
|
| 103 |
+
"content": "[PAD]",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false
|
| 108 |
+
},
|
| 109 |
+
"sep_token": {
|
| 110 |
+
"content": "[SEP]",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false
|
| 115 |
+
},
|
| 116 |
+
"unk_token": {
|
| 117 |
+
"content": "[UNK]",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false
|
| 122 |
+
}
|
| 123 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
| 3 |
+
size 4305025
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c7ccb287623cccb7c03150953b6d2a09dd95122933393c9151c3a60095c97e
|
| 3 |
+
size 16337353
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,951 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"250102": {
|
| 844 |
+
"content": "[SEP_STRUCT]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"250103": {
|
| 852 |
+
"content": "[SEP_TEXT]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"250104": {
|
| 860 |
+
"content": "[P]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"250105": {
|
| 868 |
+
"content": "[C]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"250106": {
|
| 876 |
+
"content": "[E]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"250107": {
|
| 884 |
+
"content": "[R]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"250108": {
|
| 892 |
+
"content": "[L]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"250109": {
|
| 900 |
+
"content": "[EXAMPLE]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"250110": {
|
| 908 |
+
"content": "[OUTPUT]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"250111": {
|
| 916 |
+
"content": "[DESCRIPTION]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
}
|
| 923 |
+
},
|
| 924 |
+
"additional_special_tokens": [
|
| 925 |
+
"[SEP_STRUCT]",
|
| 926 |
+
"[SEP_TEXT]",
|
| 927 |
+
"[P]",
|
| 928 |
+
"[C]",
|
| 929 |
+
"[E]",
|
| 930 |
+
"[R]",
|
| 931 |
+
"[L]",
|
| 932 |
+
"[EXAMPLE]",
|
| 933 |
+
"[OUTPUT]",
|
| 934 |
+
"[DESCRIPTION]"
|
| 935 |
+
],
|
| 936 |
+
"bos_token": "[CLS]",
|
| 937 |
+
"clean_up_tokenization_spaces": false,
|
| 938 |
+
"cls_token": "[CLS]",
|
| 939 |
+
"do_lower_case": false,
|
| 940 |
+
"eos_token": "[SEP]",
|
| 941 |
+
"extra_special_tokens": {},
|
| 942 |
+
"mask_token": "[MASK]",
|
| 943 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 944 |
+
"pad_token": "[PAD]",
|
| 945 |
+
"sep_token": "[SEP]",
|
| 946 |
+
"sp_model_kwargs": {},
|
| 947 |
+
"split_by_punct": false,
|
| 948 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 949 |
+
"unk_token": "[UNK]",
|
| 950 |
+
"vocab_type": "spm"
|
| 951 |
+
}
|