Hugging Face's logo

spacy
/
ru_core_news_sm

Token Classification
spaCy
Russian
Eval Results (legacy)
Model card Files
xet
Community
adrianeboyd commited on
Commit
5fcae88
·
1 Parent(s): aaa3c94

Update spaCy pipeline

Browse files
Files changed (13) hide show
  1. README.md +28 -28
  2. accuracy.json +167 -167
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +6 -5
  5. meta.json +171 -171
  6. morphologizer/model +1 -1
  7. ner/model +2 -2
  8. parser/model +1 -1
  9. ru_core_news_sm-any-py3-none-any.whl +2 -2
  10. senter/model +1 -1
  11. tok2vec/model +2 -2
  12. tokenizer +0 -0
  13. vocab/strings.json +2 -2
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.943812709
18
  - name: NER Recall
19
  type: recall
20
- value: 0.9500084161
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.9469004278
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9880060539
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9880060539
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.9711357536
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 2.15292e-05
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.9592758407
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.9473147719
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9986681887
73
  ---
74
  ### Details: https://spacy.io/models/ru#ru_core_news_sm
75
 
@@ -78,8 +78,8 @@ Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ru_core_news_sm` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -105,22 +105,22 @@ Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
105
 
106
  | Type | Score |
107
  | --- | --- |
108
- | `TOKEN_ACC` | 99.84 |
109
  | `TOKEN_P` | 97.28 |
110
- | `TOKEN_R` | 98.32 |
111
  | `TOKEN_F` | 97.79 |
112
- | `POS_ACC` | 98.80 |
113
- | `MORPH_ACC` | 97.11 |
114
- | `MORPH_MICRO_P` | 98.75 |
115
- | `MORPH_MICRO_R` | 98.06 |
116
- | `MORPH_MICRO_F` | 98.40 |
117
- | `SENTS_P` | 99.87 |
118
- | `SENTS_R` | 99.87 |
119
- | `SENTS_F` | 99.87 |
120
- | `DEP_UAS` | 95.93 |
121
- | `DEP_LAS` | 94.73 |
122
- | `TAG_ACC` | 98.80 |
123
  | `LEMMA_ACC` | 0.00 |
124
- | `ENTS_P` | 94.38 |
125
- | `ENTS_R` | 95.00 |
126
- | `ENTS_F` | 94.69 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.9487739335
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.9508500252
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.9498108449
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.987696514
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.987696514
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.9702812464
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 2.15295e-05
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.9586955101
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.946180635
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9988584475
73
  ---
74
  ### Details: https://spacy.io/models/ru#ru_core_news_sm
75
 
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ru_core_news_sm` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 
105
 
106
  | Type | Score |
107
  | --- | --- |
108
+ | `TOKEN_ACC` | 99.68 |
109
  | `TOKEN_P` | 97.28 |
110
+ | `TOKEN_R` | 98.31 |
111
  | `TOKEN_F` | 97.79 |
112
+ | `POS_ACC` | 98.77 |
113
+ | `MORPH_ACC` | 97.03 |
114
+ | `MORPH_MICRO_P` | 98.68 |
115
+ | `MORPH_MICRO_R` | 97.98 |
116
+ | `MORPH_MICRO_F` | 98.33 |
117
+ | `SENTS_P` | 99.89 |
118
+ | `SENTS_R` | 99.89 |
119
+ | `SENTS_F` | 99.89 |
120
+ | `DEP_UAS` | 95.87 |
121
+ | `DEP_LAS` | 94.62 |
122
+ | `TAG_ACC` | 98.77 |
123
  | `LEMMA_ACC` | 0.00 |
124
+ | `ENTS_P` | 94.88 |
125
+ | `ENTS_R` | 95.09 |
126
+ | `ENTS_F` | 94.98 |
accuracy.json CHANGED
@@ -1,68 +1,68 @@
1
  {
2
- "token_acc": 0.9984047451,
3
- "token_p": 0.9727635194,
4
- "token_r": 0.9831678569,
5
- "token_f": 0.9779380158,
6
- "pos_acc": 0.9880060539,
7
- "morph_acc": 0.9711357536,
8
- "morph_micro_p": 0.9875020482,
9
- "morph_micro_r": 0.9805651482,
10
- "morph_micro_f": 0.9840213729,
11
  "morph_per_feat": {
12
  "Animacy": {
13
- "p": 0.9879047647,
14
- "r": 0.9781698738,
15
- "f": 0.9830132184
16
  },
17
  "Case": {
18
- "p": 0.9752914486,
19
- "r": 0.9687632477,
20
- "f": 0.9720163872
21
  },
22
  "Gender": {
23
- "p": 0.9868704596,
24
- "r": 0.9804665946,
25
- "f": 0.9836581045
26
  },
27
  "Number": {
28
- "p": 0.9951099318,
29
- "r": 0.9888499642,
30
- "f": 0.991970072
31
  },
32
  "Degree": {
33
- "p": 0.983003993,
34
- "r": 0.9857289528,
35
- "f": 0.9843645871
36
  },
37
  "Aspect": {
38
- "p": 0.9826197158,
39
- "r": 0.9757303371,
40
- "f": 0.9791629082
41
  },
42
  "Mood": {
43
- "p": 0.9988819876,
44
- "r": 0.9969005703,
45
- "f": 0.9978902954
46
  },
47
  "Tense": {
48
- "p": 0.9901676671,
49
- "r": 0.982641742,
50
- "f": 0.9863903495
51
  },
52
  "VerbForm": {
53
- "p": 0.9945686612,
54
- "r": 0.9875955056,
55
- "f": 0.9910698178
56
  },
57
  "Voice": {
58
- "p": 0.9888657554,
59
- "r": 0.9819325843,
60
- "f": 0.9853869746
61
  },
62
  "StyleVariant": {
63
- "p": 0.986287953,
64
- "r": 0.9930966469,
65
- "f": 0.9896805897
66
  },
67
  "Polarity": {
68
  "p": 1.0,
@@ -70,14 +70,14 @@
70
  "f": 1.0
71
  },
72
  "Person": {
73
- "p": 0.9997725722,
74
- "r": 0.9916535078,
75
- "f": 0.9956964892
76
  },
77
  "Foreign": {
78
- "p": 0.970703125,
79
- "r": 0.8598615917,
80
- "f": 0.9119266055
81
  },
82
  "Hyph": {
83
  "p": 0.0,
@@ -85,111 +85,111 @@
85
  "f": 0.0
86
  }
87
  },
88
- "sents_p": 0.9986681887,
89
- "sents_r": 0.9986681887,
90
- "sents_f": 0.9986681887,
91
- "dep_uas": 0.9592758407,
92
- "dep_las": 0.9473147719,
93
  "dep_las_per_type": {
94
  "case": {
95
- "p": 0.9918071381,
96
- "r": 0.9895706098,
97
- "f": 0.9906876117
98
  },
99
  "parataxis": {
100
- "p": 0.893073302,
101
- "r": 0.8589909444,
102
- "f": 0.8757006264
103
  },
104
  "nmod": {
105
- "p": 0.922032006,
106
- "r": 0.920404941,
107
- "f": 0.9212177551
108
  },
109
  "advmod": {
110
- "p": 0.9584327087,
111
- "r": 0.9506590064,
112
- "f": 0.9545300305
113
  },
114
  "obl": {
115
- "p": 0.9369024857,
116
- "r": 0.9284070916,
117
- "f": 0.9326354429
118
  },
119
  "amod": {
120
- "p": 0.9856818826,
121
- "r": 0.9831730769,
122
- "f": 0.9844258814
123
  },
124
  "nsubj": {
125
- "p": 0.9683444128,
126
  "r": 0.9660508448,
127
- "f": 0.9671962691
128
  },
129
  "root": {
130
- "p": 0.9887640449,
131
- "r": 0.9878234399,
132
- "f": 0.9882935186
133
  },
134
  "xcomp": {
135
- "p": 0.9502262443,
136
- "r": 0.9574468085,
137
- "f": 0.9538228615
138
  },
139
  "conj": {
140
- "p": 0.8871515976,
141
- "r": 0.8956760467,
142
- "f": 0.8913934426
143
  },
144
  "cc": {
145
- "p": 0.9723912026,
146
- "r": 0.9719363891,
147
- "f": 0.9721637427
148
  },
149
  "fixed": {
150
- "p": 0.9898089172,
151
- "r": 0.9885496183,
152
- "f": 0.989178867
153
  },
154
  "mark": {
155
- "p": 0.9616384915,
156
- "r": 0.9654046997,
157
- "f": 0.9635179153
158
  },
159
  "ccomp": {
160
- "p": 0.978125,
161
- "r": 0.9822175732,
162
- "f": 0.9801670146
163
  },
164
  "nummod:gov": {
165
- "p": 0.9765957447,
166
- "r": 0.95625,
167
- "f": 0.9663157895
168
  },
169
  "nummod": {
170
- "p": 0.9629310345,
171
- "r": 0.9482173175,
172
- "f": 0.9555175364
173
  },
174
  "obj": {
175
- "p": 0.9696132597,
176
- "r": 0.9590163934,
177
- "f": 0.9642857143
178
  },
179
  "det": {
180
- "p": 0.9629898403,
181
- "r": 0.9588150289,
182
- "f": 0.9608979001
183
  },
184
  "appos": {
185
- "p": 0.8898865784,
186
- "r": 0.8088487973,
187
- "f": 0.8474347435
188
  },
189
  "aux": {
190
- "p": 0.9444444444,
191
- "r": 0.9714285714,
192
- "f": 0.9577464789
193
  },
194
  "flat": {
195
  "p": 0.9952718676,
@@ -197,79 +197,79 @@
197
  "f": 0.9767981439
198
  },
199
  "flat:name": {
200
- "p": 0.9770114943,
201
  "r": 0.9659090909,
202
- "f": 0.9714285714
203
  },
204
  "iobj": {
205
- "p": 0.9124293785,
206
- "r": 0.8115577889,
207
- "f": 0.8590425532
208
  },
209
  "acl": {
210
- "p": 0.9134993447,
211
- "r": 0.8701622971,
212
- "f": 0.8913043478
213
  },
214
  "obl:agent": {
215
- "p": 0.6790123457,
216
  "r": 0.7236842105,
217
- "f": 0.7006369427
218
  },
219
  "advcl": {
220
- "p": 0.8538812785,
221
- "r": 0.8538812785,
222
- "f": 0.8538812785
223
  },
224
  "cop": {
225
- "p": 0.9219858156,
226
- "r": 0.9027777778,
227
- "f": 0.9122807018
228
  },
229
  "flat:foreign": {
230
- "p": 0.9627659574,
231
- "r": 0.8227272727,
232
- "f": 0.887254902
233
  },
234
  "aux:pass": {
235
- "p": 0.9854651163,
236
- "r": 0.9713467049,
237
- "f": 0.9783549784
238
  },
239
  "nsubj:pass": {
240
- "p": 0.9460641399,
241
- "r": 0.9474452555,
242
- "f": 0.946754194
243
  },
244
  "acl:relcl": {
245
- "p": 0.7916666667,
246
- "r": 0.7802874743,
247
- "f": 0.7859358842
248
  },
249
  "orphan": {
250
- "p": 0.8285714286,
251
- "r": 0.8055555556,
252
- "f": 0.8169014085
253
  },
254
  "discourse": {
255
- "p": 0.9523809524,
256
  "r": 0.9230769231,
257
- "f": 0.9375
258
  },
259
  "csubj": {
260
- "p": 0.9503546099,
261
- "r": 0.9436619718,
262
- "f": 0.9469964664
263
  },
264
  "expl": {
265
- "p": 0.7894736842,
266
  "r": 0.7894736842,
267
- "f": 0.7894736842
268
  },
269
  "compound": {
270
- "p": 1.0,
271
  "r": 0.4,
272
- "f": 0.5714285714
273
  },
274
  "csubj:pass": {
275
  "p": 0.9,
@@ -287,27 +287,27 @@
287
  "f": 0.0
288
  }
289
  },
290
- "tag_acc": 0.9880060539,
291
- "lemma_acc": 2.15292e-05,
292
- "ents_p": 0.943812709,
293
- "ents_r": 0.9500084161,
294
- "ents_f": 0.9469004278,
295
  "ents_per_type": {
296
  "PER": {
297
- "p": 0.9628169014,
298
- "r": 0.9595732734,
299
- "f": 0.961192351
300
  },
301
  "LOC": {
302
- "p": 0.9730623819,
303
- "r": 0.9726027397,
304
- "f": 0.9728325065
305
  },
306
  "ORG": {
307
- "p": 0.8980373384,
308
- "r": 0.9182574645,
309
- "f": 0.90803485
310
  }
311
  },
312
- "speed": 3573.1911564665
313
  }
 
1
  {
2
+ "token_acc": 0.9968038482,
3
+ "token_p": 0.9727525387,
4
+ "token_r": 0.9831462495,
5
+ "token_f": 0.9779217779,
6
+ "pos_acc": 0.987696514,
7
+ "morph_acc": 0.9702812464,
8
+ "morph_micro_p": 0.9868284669,
9
+ "morph_micro_r": 0.9797638369,
10
+ "morph_micro_f": 0.9832834627,
11
  "morph_per_feat": {
12
  "Animacy": {
13
+ "p": 0.9862354357,
14
+ "r": 0.9768036742,
15
+ "f": 0.9814968967
16
  },
17
  "Case": {
18
+ "p": 0.9749084619,
19
+ "r": 0.9683393204,
20
+ "f": 0.9716127877
21
  },
22
  "Gender": {
23
+ "p": 0.986496091,
24
+ "r": 0.9803341647,
25
+ "f": 0.9834054754
26
  },
27
  "Number": {
28
+ "p": 0.9948064748,
29
+ "r": 0.9885109429,
30
+ "f": 0.9916487171
31
  },
32
  "Degree": {
33
+ "p": 0.9814985178,
34
+ "r": 0.9858316222,
35
+ "f": 0.9836602981
36
  },
37
  "Aspect": {
38
+ "p": 0.9809575626,
39
+ "r": 0.9724044944,
40
+ "f": 0.9766623031
41
  },
42
  "Mood": {
43
+ "p": 0.9982615174,
44
+ "r": 0.9966526159,
45
+ "f": 0.9974564179
46
  },
47
  "Tense": {
48
+ "p": 0.9893164609,
49
+ "r": 0.979663106,
50
+ "f": 0.9844661196
51
  },
52
  "VerbForm": {
53
+ "p": 0.994377947,
54
+ "r": 0.9857078652,
55
+ "f": 0.9900239245
56
  },
57
  "Voice": {
58
+ "p": 0.9889372506,
59
+ "r": 0.9803146067,
60
+ "f": 0.984607051
61
  },
62
  "StyleVariant": {
63
+ "p": 0.9852362205,
64
+ "r": 0.9871794872,
65
+ "f": 0.9862068966
66
  },
67
  "Polarity": {
68
  "p": 1.0,
 
70
  "f": 1.0
71
  },
72
  "Person": {
73
+ "p": 0.9988641527,
74
+ "r": 0.9918790887,
75
+ "f": 0.9953593662
76
  },
77
  "Foreign": {
78
+ "p": 0.9661181026,
79
+ "r": 0.8633217993,
80
+ "f": 0.9118318867
81
  },
82
  "Hyph": {
83
  "p": 0.0,
 
85
  "f": 0.0
86
  }
87
  },
88
+ "sents_p": 0.9988584475,
89
+ "sents_r": 0.9988584475,
90
+ "sents_f": 0.9988584475,
91
+ "dep_uas": 0.9586955101,
92
+ "dep_las": 0.946180635,
93
  "dep_las_per_type": {
94
  "case": {
95
+ "p": 0.9912313785,
96
+ "r": 0.9877853989,
97
+ "f": 0.9895053885
98
  },
99
  "parataxis": {
100
+ "p": 0.8735785953,
101
+ "r": 0.8447606727,
102
+ "f": 0.8589279842
103
  },
104
  "nmod": {
105
+ "p": 0.921448468,
106
+ "r": 0.9217052104,
107
+ "f": 0.9215768213
108
  },
109
  "advmod": {
110
+ "p": 0.9575633128,
111
+ "r": 0.9455897263,
112
+ "f": 0.9515388539
113
  },
114
  "obl": {
115
+ "p": 0.9364383562,
116
+ "r": 0.9251590202,
117
+ "f": 0.9307645177
118
  },
119
  "amod": {
120
+ "p": 0.9865248227,
121
+ "r": 0.9834558824,
122
+ "f": 0.984987962
123
  },
124
  "nsubj": {
125
+ "p": 0.9691113575,
126
  "r": 0.9660508448,
127
+ "f": 0.967578681
128
  },
129
  "root": {
130
+ "p": 0.9862935465,
131
+ "r": 0.9857305936,
132
+ "f": 0.9860119897
133
  },
134
  "xcomp": {
135
+ "p": 0.9516250945,
136
+ "r": 0.9566869301,
137
+ "f": 0.954149299
138
  },
139
  "conj": {
140
+ "p": 0.8895289732,
141
+ "r": 0.9008236102,
142
+ "f": 0.895140665
143
  },
144
  "cc": {
145
+ "p": 0.9705332086,
146
+ "r": 0.9705332086,
147
+ "f": 0.9705332086
148
  },
149
  "fixed": {
150
+ "p": 0.9835234474,
151
+ "r": 0.9872773537,
152
+ "f": 0.9853968254
153
  },
154
  "mark": {
155
+ "p": 0.9656513286,
156
+ "r": 0.9725848564,
157
+ "f": 0.9691056911
158
  },
159
  "ccomp": {
160
+ "p": 0.9800838574,
161
+ "r": 0.9780334728,
162
+ "f": 0.9790575916
163
  },
164
  "nummod:gov": {
165
+ "p": 0.9644351464,
166
+ "r": 0.9604166667,
167
+ "f": 0.9624217119
168
  },
169
  "nummod": {
170
+ "p": 0.9613402062,
171
+ "r": 0.9499151104,
172
+ "f": 0.9555935098
173
  },
174
  "obj": {
175
+ "p": 0.96216068,
176
+ "r": 0.9587431694,
177
+ "f": 0.9604488846
178
  },
179
  "det": {
180
+ "p": 0.9580318379,
181
+ "r": 0.9566473988,
182
+ "f": 0.9573391179
183
  },
184
  "appos": {
185
+ "p": 0.8868194842,
186
+ "r": 0.7976804124,
187
+ "f": 0.8398914518
188
  },
189
  "aux": {
190
+ "p": 0.9619047619,
191
+ "r": 0.9619047619,
192
+ "f": 0.9619047619
193
  },
194
  "flat": {
195
  "p": 0.9952718676,
 
197
  "f": 0.9767981439
198
  },
199
  "flat:name": {
200
+ "p": 0.9629248198,
201
  "r": 0.9659090909,
202
+ "f": 0.9644146467
203
  },
204
  "iobj": {
205
+ "p": 0.9083333333,
206
+ "r": 0.8216080402,
207
+ "f": 0.8627968338
208
  },
209
  "acl": {
210
+ "p": 0.9033942559,
211
+ "r": 0.8639200999,
212
+ "f": 0.8832163369
213
  },
214
  "obl:agent": {
215
+ "p": 0.7333333333,
216
  "r": 0.7236842105,
217
+ "f": 0.7284768212
218
  },
219
  "advcl": {
220
+ "p": 0.8668171558,
221
+ "r": 0.8767123288,
222
+ "f": 0.8717366629
223
  },
224
  "cop": {
225
+ "p": 0.8958333333,
226
+ "r": 0.8958333333,
227
+ "f": 0.8958333333
228
  },
229
  "flat:foreign": {
230
+ "p": 0.972972973,
231
+ "r": 0.8181818182,
232
+ "f": 0.8888888889
233
  },
234
  "aux:pass": {
235
+ "p": 0.9855491329,
236
+ "r": 0.9770773639,
237
+ "f": 0.981294964
238
  },
239
  "nsubj:pass": {
240
+ "p": 0.9529411765,
241
+ "r": 0.9459854015,
242
+ "f": 0.9494505495
243
  },
244
  "acl:relcl": {
245
+ "p": 0.7995780591,
246
+ "r": 0.7782340862,
247
+ "f": 0.7887617066
248
  },
249
  "orphan": {
250
+ "p": 0.78125,
251
+ "r": 0.6944444444,
252
+ "f": 0.7352941176
253
  },
254
  "discourse": {
255
+ "p": 0.9230769231,
256
  "r": 0.9230769231,
257
+ "f": 0.9230769231
258
  },
259
  "csubj": {
260
+ "p": 0.9352517986,
261
+ "r": 0.9154929577,
262
+ "f": 0.9252669039
263
  },
264
  "expl": {
265
+ "p": 0.8823529412,
266
  "r": 0.7894736842,
267
+ "f": 0.8333333333
268
  },
269
  "compound": {
270
+ "p": 0.6666666667,
271
  "r": 0.4,
272
+ "f": 0.5
273
  },
274
  "csubj:pass": {
275
  "p": 0.9,
 
287
  "f": 0.0
288
  }
289
  },
290
+ "tag_acc": 0.987696514,
291
+ "lemma_acc": 2.15295e-05,
292
+ "ents_p": 0.9487739335,
293
+ "ents_r": 0.9508500252,
294
+ "ents_f": 0.9498108449,
295
  "ents_per_type": {
296
  "PER": {
297
+ "p": 0.962506995,
298
+ "r": 0.9657495789,
299
+ "f": 0.9641255605
300
  },
301
  "LOC": {
302
+ "p": 0.9739706578,
303
+ "r": 0.9721303732,
304
+ "f": 0.9730496454
305
  },
306
  "ORG": {
307
+ "p": 0.9109055501,
308
+ "r": 0.9158100832,
309
+ "f": 0.9133512326
310
  }
311
  },
312
+ "speed": 2461.731348342
313
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -27,7 +27,7 @@ validate = false
27
 
28
  [components.lemmatizer]
29
  factory = "lemmatizer"
30
- mode = "pymorphy2"
31
  model = null
32
  overwrite = false
33
  scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
@@ -70,8 +70,8 @@ nO = null
70
  [components.ner.model.tok2vec.embed]
71
  @architectures = "spacy.MultiHashEmbed.v2"
72
  width = 96
73
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
74
- rows = [5000,1000,2500,2500,50]
75
  include_static_vectors = false
76
 
77
  [components.ner.model.tok2vec.encode]
@@ -139,8 +139,8 @@ factory = "tok2vec"
139
  [components.tok2vec.model.embed]
140
  @architectures = "spacy.MultiHashEmbed.v2"
141
  width = ${components.tok2vec.model.encode:width}
142
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
143
- rows = [5000,1000,2500,2500,50]
144
  include_static_vectors = false
145
 
146
  [components.tok2vec.model.encode]
@@ -182,6 +182,7 @@ eval_frequency = 1000
182
  frozen_components = []
183
  before_to_disk = null
184
  annotating_components = []
 
185
 
186
  [training.batcher]
187
  @batchers = "spacy.batch_by_words.v1"
 
27
 
28
  [components.lemmatizer]
29
  factory = "lemmatizer"
30
+ mode = "pymorphy3"
31
  model = null
32
  overwrite = false
33
  scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
 
70
  [components.ner.model.tok2vec.embed]
71
  @architectures = "spacy.MultiHashEmbed.v2"
72
  width = 96
73
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
74
+ rows = [5000,1000,2500,2500]
75
  include_static_vectors = false
76
 
77
  [components.ner.model.tok2vec.encode]
 
139
  [components.tok2vec.model.embed]
140
  @architectures = "spacy.MultiHashEmbed.v2"
141
  width = ${components.tok2vec.model.encode:width}
142
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
143
+ rows = [5000,1000,2500,2500,50,50]
144
  include_static_vectors = false
145
 
146
  [components.tok2vec.model.encode]
 
182
  frozen_components = []
183
  before_to_disk = null
184
  annotating_components = []
185
+ before_update = null
186
 
187
  [training.batcher]
188
  @batchers = "spacy.batch_by_words.v1"
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"ru",
3
  "name":"core_news_sm",
4
- "version":"3.4.0",
5
  "description":"Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
- "spacy_version":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -953,70 +953,70 @@
953
  "senter"
954
  ],
955
  "performance":{
956
- "token_acc":0.9984047451,
957
- "token_p":0.9727635194,
958
- "token_r":0.9831678569,
959
- "token_f":0.9779380158,
960
- "pos_acc":0.9880060539,
961
- "morph_acc":0.9711357536,
962
- "morph_micro_p":0.9875020482,
963
- "morph_micro_r":0.9805651482,
964
- "morph_micro_f":0.9840213729,
965
  "morph_per_feat":{
966
  "Animacy":{
967
- "p":0.9879047647,
968
- "r":0.9781698738,
969
- "f":0.9830132184
970
  },
971
  "Case":{
972
- "p":0.9752914486,
973
- "r":0.9687632477,
974
- "f":0.9720163872
975
  },
976
  "Gender":{
977
- "p":0.9868704596,
978
- "r":0.9804665946,
979
- "f":0.9836581045
980
  },
981
  "Number":{
982
- "p":0.9951099318,
983
- "r":0.9888499642,
984
- "f":0.991970072
985
  },
986
  "Degree":{
987
- "p":0.983003993,
988
- "r":0.9857289528,
989
- "f":0.9843645871
990
  },
991
  "Aspect":{
992
- "p":0.9826197158,
993
- "r":0.9757303371,
994
- "f":0.9791629082
995
  },
996
  "Mood":{
997
- "p":0.9988819876,
998
- "r":0.9969005703,
999
- "f":0.9978902954
1000
  },
1001
  "Tense":{
1002
- "p":0.9901676671,
1003
- "r":0.982641742,
1004
- "f":0.9863903495
1005
  },
1006
  "VerbForm":{
1007
- "p":0.9945686612,
1008
- "r":0.9875955056,
1009
- "f":0.9910698178
1010
  },
1011
  "Voice":{
1012
- "p":0.9888657554,
1013
- "r":0.9819325843,
1014
- "f":0.9853869746
1015
  },
1016
  "StyleVariant":{
1017
- "p":0.986287953,
1018
- "r":0.9930966469,
1019
- "f":0.9896805897
1020
  },
1021
  "Polarity":{
1022
  "p":1.0,
@@ -1024,14 +1024,14 @@
1024
  "f":1.0
1025
  },
1026
  "Person":{
1027
- "p":0.9997725722,
1028
- "r":0.9916535078,
1029
- "f":0.9956964892
1030
  },
1031
  "Foreign":{
1032
- "p":0.970703125,
1033
- "r":0.8598615917,
1034
- "f":0.9119266055
1035
  },
1036
  "Hyph":{
1037
  "p":0.0,
@@ -1039,111 +1039,111 @@
1039
  "f":0.0
1040
  }
1041
  },
1042
- "sents_p":0.9986681887,
1043
- "sents_r":0.9986681887,
1044
- "sents_f":0.9986681887,
1045
- "dep_uas":0.9592758407,
1046
- "dep_las":0.9473147719,
1047
  "dep_las_per_type":{
1048
  "case":{
1049
- "p":0.9918071381,
1050
- "r":0.9895706098,
1051
- "f":0.9906876117
1052
  },
1053
  "parataxis":{
1054
- "p":0.893073302,
1055
- "r":0.8589909444,
1056
- "f":0.8757006264
1057
  },
1058
  "nmod":{
1059
- "p":0.922032006,
1060
- "r":0.920404941,
1061
- "f":0.9212177551
1062
  },
1063
  "advmod":{
1064
- "p":0.9584327087,
1065
- "r":0.9506590064,
1066
- "f":0.9545300305
1067
  },
1068
  "obl":{
1069
- "p":0.9369024857,
1070
- "r":0.9284070916,
1071
- "f":0.9326354429
1072
  },
1073
  "amod":{
1074
- "p":0.9856818826,
1075
- "r":0.9831730769,
1076
- "f":0.9844258814
1077
  },
1078
  "nsubj":{
1079
- "p":0.9683444128,
1080
  "r":0.9660508448,
1081
- "f":0.9671962691
1082
  },
1083
  "root":{
1084
- "p":0.9887640449,
1085
- "r":0.9878234399,
1086
- "f":0.9882935186
1087
  },
1088
  "xcomp":{
1089
- "p":0.9502262443,
1090
- "r":0.9574468085,
1091
- "f":0.9538228615
1092
  },
1093
  "conj":{
1094
- "p":0.8871515976,
1095
- "r":0.8956760467,
1096
- "f":0.8913934426
1097
  },
1098
  "cc":{
1099
- "p":0.9723912026,
1100
- "r":0.9719363891,
1101
- "f":0.9721637427
1102
  },
1103
  "fixed":{
1104
- "p":0.9898089172,
1105
- "r":0.9885496183,
1106
- "f":0.989178867
1107
  },
1108
  "mark":{
1109
- "p":0.9616384915,
1110
- "r":0.9654046997,
1111
- "f":0.9635179153
1112
  },
1113
  "ccomp":{
1114
- "p":0.978125,
1115
- "r":0.9822175732,
1116
- "f":0.9801670146
1117
  },
1118
  "nummod:gov":{
1119
- "p":0.9765957447,
1120
- "r":0.95625,
1121
- "f":0.9663157895
1122
  },
1123
  "nummod":{
1124
- "p":0.9629310345,
1125
- "r":0.9482173175,
1126
- "f":0.9555175364
1127
  },
1128
  "obj":{
1129
- "p":0.9696132597,
1130
- "r":0.9590163934,
1131
- "f":0.9642857143
1132
  },
1133
  "det":{
1134
- "p":0.9629898403,
1135
- "r":0.9588150289,
1136
- "f":0.9608979001
1137
  },
1138
  "appos":{
1139
- "p":0.8898865784,
1140
- "r":0.8088487973,
1141
- "f":0.8474347435
1142
  },
1143
  "aux":{
1144
- "p":0.9444444444,
1145
- "r":0.9714285714,
1146
- "f":0.9577464789
1147
  },
1148
  "flat":{
1149
  "p":0.9952718676,
@@ -1151,79 +1151,79 @@
1151
  "f":0.9767981439
1152
  },
1153
  "flat:name":{
1154
- "p":0.9770114943,
1155
  "r":0.9659090909,
1156
- "f":0.9714285714
1157
  },
1158
  "iobj":{
1159
- "p":0.9124293785,
1160
- "r":0.8115577889,
1161
- "f":0.8590425532
1162
  },
1163
  "acl":{
1164
- "p":0.9134993447,
1165
- "r":0.8701622971,
1166
- "f":0.8913043478
1167
  },
1168
  "obl:agent":{
1169
- "p":0.6790123457,
1170
  "r":0.7236842105,
1171
- "f":0.7006369427
1172
  },
1173
  "advcl":{
1174
- "p":0.8538812785,
1175
- "r":0.8538812785,
1176
- "f":0.8538812785
1177
  },
1178
  "cop":{
1179
- "p":0.9219858156,
1180
- "r":0.9027777778,
1181
- "f":0.9122807018
1182
  },
1183
  "flat:foreign":{
1184
- "p":0.9627659574,
1185
- "r":0.8227272727,
1186
- "f":0.887254902
1187
  },
1188
  "aux:pass":{
1189
- "p":0.9854651163,
1190
- "r":0.9713467049,
1191
- "f":0.9783549784
1192
  },
1193
  "nsubj:pass":{
1194
- "p":0.9460641399,
1195
- "r":0.9474452555,
1196
- "f":0.946754194
1197
  },
1198
  "acl:relcl":{
1199
- "p":0.7916666667,
1200
- "r":0.7802874743,
1201
- "f":0.7859358842
1202
  },
1203
  "orphan":{
1204
- "p":0.8285714286,
1205
- "r":0.8055555556,
1206
- "f":0.8169014085
1207
  },
1208
  "discourse":{
1209
- "p":0.9523809524,
1210
  "r":0.9230769231,
1211
- "f":0.9375
1212
  },
1213
  "csubj":{
1214
- "p":0.9503546099,
1215
- "r":0.9436619718,
1216
- "f":0.9469964664
1217
  },
1218
  "expl":{
1219
- "p":0.7894736842,
1220
  "r":0.7894736842,
1221
- "f":0.7894736842
1222
  },
1223
  "compound":{
1224
- "p":1.0,
1225
  "r":0.4,
1226
- "f":0.5714285714
1227
  },
1228
  "csubj:pass":{
1229
  "p":0.9,
@@ -1241,29 +1241,29 @@
1241
  "f":0.0
1242
  }
1243
  },
1244
- "tag_acc":0.9880060539,
1245
- "lemma_acc":0.0000215292,
1246
- "ents_p":0.943812709,
1247
- "ents_r":0.9500084161,
1248
- "ents_f":0.9469004278,
1249
  "ents_per_type":{
1250
  "PER":{
1251
- "p":0.9628169014,
1252
- "r":0.9595732734,
1253
- "f":0.961192351
1254
  },
1255
  "LOC":{
1256
- "p":0.9730623819,
1257
- "r":0.9726027397,
1258
- "f":0.9728325065
1259
  },
1260
  "ORG":{
1261
- "p":0.8980373384,
1262
- "r":0.9182574645,
1263
- "f":0.90803485
1264
  }
1265
  },
1266
- "speed":3573.1911564665
1267
  },
1268
  "sources":[
1269
  {
@@ -1274,6 +1274,6 @@
1274
  }
1275
  ],
1276
  "requirements":[
1277
- "pymorphy2>=0.9"
1278
  ]
1279
  }
 
1
  {
2
  "lang":"ru",
3
  "name":"core_news_sm",
4
+ "version":"3.5.0",
5
  "description":"Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
+ "spacy_version":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
953
  "senter"
954
  ],
955
  "performance":{
956
+ "token_acc":0.9968038482,
957
+ "token_p":0.9727525387,
958
+ "token_r":0.9831462495,
959
+ "token_f":0.9779217779,
960
+ "pos_acc":0.987696514,
961
+ "morph_acc":0.9702812464,
962
+ "morph_micro_p":0.9868284669,
963
+ "morph_micro_r":0.9797638369,
964
+ "morph_micro_f":0.9832834627,
965
  "morph_per_feat":{
966
  "Animacy":{
967
+ "p":0.9862354357,
968
+ "r":0.9768036742,
969
+ "f":0.9814968967
970
  },
971
  "Case":{
972
+ "p":0.9749084619,
973
+ "r":0.9683393204,
974
+ "f":0.9716127877
975
  },
976
  "Gender":{
977
+ "p":0.986496091,
978
+ "r":0.9803341647,
979
+ "f":0.9834054754
980
  },
981
  "Number":{
982
+ "p":0.9948064748,
983
+ "r":0.9885109429,
984
+ "f":0.9916487171
985
  },
986
  "Degree":{
987
+ "p":0.9814985178,
988
+ "r":0.9858316222,
989
+ "f":0.9836602981
990
  },
991
  "Aspect":{
992
+ "p":0.9809575626,
993
+ "r":0.9724044944,
994
+ "f":0.9766623031
995
  },
996
  "Mood":{
997
+ "p":0.9982615174,
998
+ "r":0.9966526159,
999
+ "f":0.9974564179
1000
  },
1001
  "Tense":{
1002
+ "p":0.9893164609,
1003
+ "r":0.979663106,
1004
+ "f":0.9844661196
1005
  },
1006
  "VerbForm":{
1007
+ "p":0.994377947,
1008
+ "r":0.9857078652,
1009
+ "f":0.9900239245
1010
  },
1011
  "Voice":{
1012
+ "p":0.9889372506,
1013
+ "r":0.9803146067,
1014
+ "f":0.984607051
1015
  },
1016
  "StyleVariant":{
1017
+ "p":0.9852362205,
1018
+ "r":0.9871794872,
1019
+ "f":0.9862068966
1020
  },
1021
  "Polarity":{
1022
  "p":1.0,
 
1024
  "f":1.0
1025
  },
1026
  "Person":{
1027
+ "p":0.9988641527,
1028
+ "r":0.9918790887,
1029
+ "f":0.9953593662
1030
  },
1031
  "Foreign":{
1032
+ "p":0.9661181026,
1033
+ "r":0.8633217993,
1034
+ "f":0.9118318867
1035
  },
1036
  "Hyph":{
1037
  "p":0.0,
 
1039
  "f":0.0
1040
  }
1041
  },
1042
+ "sents_p":0.9988584475,
1043
+ "sents_r":0.9988584475,
1044
+ "sents_f":0.9988584475,
1045
+ "dep_uas":0.9586955101,
1046
+ "dep_las":0.946180635,
1047
  "dep_las_per_type":{
1048
  "case":{
1049
+ "p":0.9912313785,
1050
+ "r":0.9877853989,
1051
+ "f":0.9895053885
1052
  },
1053
  "parataxis":{
1054
+ "p":0.8735785953,
1055
+ "r":0.8447606727,
1056
+ "f":0.8589279842
1057
  },
1058
  "nmod":{
1059
+ "p":0.921448468,
1060
+ "r":0.9217052104,
1061
+ "f":0.9215768213
1062
  },
1063
  "advmod":{
1064
+ "p":0.9575633128,
1065
+ "r":0.9455897263,
1066
+ "f":0.9515388539
1067
  },
1068
  "obl":{
1069
+ "p":0.9364383562,
1070
+ "r":0.9251590202,
1071
+ "f":0.9307645177
1072
  },
1073
  "amod":{
1074
+ "p":0.9865248227,
1075
+ "r":0.9834558824,
1076
+ "f":0.984987962
1077
  },
1078
  "nsubj":{
1079
+ "p":0.9691113575,
1080
  "r":0.9660508448,
1081
+ "f":0.967578681
1082
  },
1083
  "root":{
1084
+ "p":0.9862935465,
1085
+ "r":0.9857305936,
1086
+ "f":0.9860119897
1087
  },
1088
  "xcomp":{
1089
+ "p":0.9516250945,
1090
+ "r":0.9566869301,
1091
+ "f":0.954149299
1092
  },
1093
  "conj":{
1094
+ "p":0.8895289732,
1095
+ "r":0.9008236102,
1096
+ "f":0.895140665
1097
  },
1098
  "cc":{
1099
+ "p":0.9705332086,
1100
+ "r":0.9705332086,
1101
+ "f":0.9705332086
1102
  },
1103
  "fixed":{
1104
+ "p":0.9835234474,
1105
+ "r":0.9872773537,
1106
+ "f":0.9853968254
1107
  },
1108
  "mark":{
1109
+ "p":0.9656513286,
1110
+ "r":0.9725848564,
1111
+ "f":0.9691056911
1112
  },
1113
  "ccomp":{
1114
+ "p":0.9800838574,
1115
+ "r":0.9780334728,
1116
+ "f":0.9790575916
1117
  },
1118
  "nummod:gov":{
1119
+ "p":0.9644351464,
1120
+ "r":0.9604166667,
1121
+ "f":0.9624217119
1122
  },
1123
  "nummod":{
1124
+ "p":0.9613402062,
1125
+ "r":0.9499151104,
1126
+ "f":0.9555935098
1127
  },
1128
  "obj":{
1129
+ "p":0.96216068,
1130
+ "r":0.9587431694,
1131
+ "f":0.9604488846
1132
  },
1133
  "det":{
1134
+ "p":0.9580318379,
1135
+ "r":0.9566473988,
1136
+ "f":0.9573391179
1137
  },
1138
  "appos":{
1139
+ "p":0.8868194842,
1140
+ "r":0.7976804124,
1141
+ "f":0.8398914518
1142
  },
1143
  "aux":{
1144
+ "p":0.9619047619,
1145
+ "r":0.9619047619,
1146
+ "f":0.9619047619
1147
  },
1148
  "flat":{
1149
  "p":0.9952718676,
 
1151
  "f":0.9767981439
1152
  },
1153
  "flat:name":{
1154
+ "p":0.9629248198,
1155
  "r":0.9659090909,
1156
+ "f":0.9644146467
1157
  },
1158
  "iobj":{
1159
+ "p":0.9083333333,
1160
+ "r":0.8216080402,
1161
+ "f":0.8627968338
1162
  },
1163
  "acl":{
1164
+ "p":0.9033942559,
1165
+ "r":0.8639200999,
1166
+ "f":0.8832163369
1167
  },
1168
  "obl:agent":{
1169
+ "p":0.7333333333,
1170
  "r":0.7236842105,
1171
+ "f":0.7284768212
1172
  },
1173
  "advcl":{
1174
+ "p":0.8668171558,
1175
+ "r":0.8767123288,
1176
+ "f":0.8717366629
1177
  },
1178
  "cop":{
1179
+ "p":0.8958333333,
1180
+ "r":0.8958333333,
1181
+ "f":0.8958333333
1182
  },
1183
  "flat:foreign":{
1184
+ "p":0.972972973,
1185
+ "r":0.8181818182,
1186
+ "f":0.8888888889
1187
  },
1188
  "aux:pass":{
1189
+ "p":0.9855491329,
1190
+ "r":0.9770773639,
1191
+ "f":0.981294964
1192
  },
1193
  "nsubj:pass":{
1194
+ "p":0.9529411765,
1195
+ "r":0.9459854015,
1196
+ "f":0.9494505495
1197
  },
1198
  "acl:relcl":{
1199
+ "p":0.7995780591,
1200
+ "r":0.7782340862,
1201
+ "f":0.7887617066
1202
  },
1203
  "orphan":{
1204
+ "p":0.78125,
1205
+ "r":0.6944444444,
1206
+ "f":0.7352941176
1207
  },
1208
  "discourse":{
1209
+ "p":0.9230769231,
1210
  "r":0.9230769231,
1211
+ "f":0.9230769231
1212
  },
1213
  "csubj":{
1214
+ "p":0.9352517986,
1215
+ "r":0.9154929577,
1216
+ "f":0.9252669039
1217
  },
1218
  "expl":{
1219
+ "p":0.8823529412,
1220
  "r":0.7894736842,
1221
+ "f":0.8333333333
1222
  },
1223
  "compound":{
1224
+ "p":0.6666666667,
1225
  "r":0.4,
1226
+ "f":0.5
1227
  },
1228
  "csubj:pass":{
1229
  "p":0.9,
 
1241
  "f":0.0
1242
  }
1243
  },
1244
+ "tag_acc":0.987696514,
1245
+ "lemma_acc":0.0000215295,
1246
+ "ents_p":0.9487739335,
1247
+ "ents_r":0.9508500252,
1248
+ "ents_f":0.9498108449,
1249
  "ents_per_type":{
1250
  "PER":{
1251
+ "p":0.962506995,
1252
+ "r":0.9657495789,
1253
+ "f":0.9641255605
1254
  },
1255
  "LOC":{
1256
+ "p":0.9739706578,
1257
+ "r":0.9721303732,
1258
+ "f":0.9730496454
1259
  },
1260
  "ORG":{
1261
+ "p":0.9109055501,
1262
+ "r":0.9158100832,
1263
+ "f":0.9133512326
1264
  }
1265
  },
1266
+ "speed":2461.731348342
1267
  },
1268
  "sources":[
1269
  {
 
1274
  }
1275
  ],
1276
  "requirements":[
1277
+ "pymorphy3>=1.0.0"
1278
  ]
1279
  }
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42298f06ffde77768b7400b6f121ecb0ea6b9b7d78b2ce583ac7faf38074445c
3
  size 332570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3654b06fd31e7df73294024a3f341147ea0e1694306ddb9ecf4acbdcae2cbf
3
  size 332570
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ead9c647faa2118d91e3f7f99eda8870915ef4be136771cc1820acc7e13951f6
3
- size 6269162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17efb4c07d9057784a78e8afebfc3ba4f0c50787048001d7fd89081ee3f4900
3
+ size 6139000
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c119231621c993c7da5becda0f63841be5e68e4813bdc5c228214b7ed02c5f55
3
  size 312369
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4aac120e3fe755c3b8c84420f54044d5192c098179bfa23f006e17976cc056
3
  size 312369
ru_core_news_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f6784f9c94001047345527af4ff706d0b577b530c67ef113dd1cf11e8d6f785
3
- size 15258741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bedf427ab4f522137822d52c50ebdf9edeef31fdb808ed4776ce1596aa789704
3
+ size 15257437
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fae98820fc248dd378f5a7daefb5605df6fb4f7f06e510c9377549092287708b
3
  size 197089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8a146d7d904107019b3c88943cf18959c565024dbd4085e5184cea7c2f926e
3
  size 197089
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da857348a5674b7daa357ccacf87328e8cb07c16c2abf163ad88f961ad03369d
3
- size 6139229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831172259ebcc925a122a1ae7b8c353c4028c23981f74585a6954a3df35592c0
3
+ size 6269370
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
 
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5044437de62a9b1477d83890ad75ed392678260bd6dc4664492ecf2e42540a30
3
- size 32859063
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f37f72669c66f20e12c22d3786400f4c80af235b31ac6a4e0ba4d6904deb159
3
+ size 32859126