Update spaCy pipeline

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sr_pln_tesla_dbmu-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+trainable_lemmatizer/model filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- sr
+license: cc-by-sa-3.0
+model-index:
+- name: sr_pln_tesla_dbmu
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.9465813405
+    - name: NER Recall
+      type: recall
+      value: 0.9506156136
+    - name: NER F Score
+      type: f_score
+      value: 0.9485941877
+  - task:
+      name: TAG
+      type: token-classification
+    metrics:
+    - name: TAG (XPOS) Accuracy
+      type: accuracy
+      value: 0.9815057009
+  - task:
+      name: LEMMA
+      type: token-classification
+    metrics:
+    - name: Lemma Accuracy
+      type: accuracy
+      value: 0.9797101778
+---
+sr_pln_tesla_dbmu is a spaCy model meticulously fine-tuned for Part-of-Speech Tagging, Lemmatization, and Named Entity Recognition in Serbian language texts. This advanced model incorporates a transformer layer based on distilbert/distilbert-base-multilingual-cased, enhancing its analytical capabilities. It is proficient in identifying 7 distinct categories of entities: PERS (persons), ROLE (professions), DEMO (demonyms), ORG (organizations), LOC (locations), WORK (artworks), and EVENT (events). Detailed information about these categories is available in the accompanying table. The development of this model has been made possible through the support of the Science Fund of the Republic of Serbia, under grant #7276, for the project 'Text Embeddings - Serbian Language Applications - TESLA'.
+
+| Feature | Description |
+| --- | --- |
+| **Name** | `sr_pln_tesla_dbmu` |
+| **Version** | `1.0.0` |
+| **spaCy** | `>=3.7.2,<3.8.0` |
+| **Default Pipeline** | `transformer`, `tagger`, `trainable_lemmatizer`, `ner` |
+| **Components** | `transformer`, `tagger`, `trainable_lemmatizer`, `ner` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | `CC BY-SA 3.0` |
+| **Author** | [Milica Ikonić Nešić, Saša Petalinkar, Mihailo Škorić, Ranka Stanković](https://tesla.rgf.bg.ac.rs/) |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (23 labels for 2 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`tagger`** | `ADJ`, `ADP`, `ADV`, `AUX`, `CCONJ`, `DET`, `INTJ`, `NOUN`, `NUM`, `PART`, `PRON`, `PROPN`, `PUNCT`, `SCONJ`, `VERB`, `X` |
+| **`ner`** | `DEMO`, `EVENT`, `LOC`, `ORG`, `PERS`, `ROLE`, `WORK` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `TAG_ACC` | 98.15 |
+| `LEMMA_ACC` | 97.97 |
+| `ENTS_F` | 94.86 |
+| `ENTS_P` | 94.66 |
+| `ENTS_R` | 95.06 |
+| `TRANSFORMER_LOSS` | 604959.76 |
+| `TAGGER_LOSS` | 359950.85 |
+| `TRAINABLE_LEMMATIZER_LOSS` | 466065.88 |
+| `NER_LOSS` | 175653.69 |

config.cfg

@@ -0,0 +1,186 @@
+[paths]
+train = "./train.spacy"
+dev = "./dev.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "sr"
+pipeline = ["transformer","tagger","trainable_lemmatizer","ner"]
+batch_size = 128
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = false
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.tagger]
+factory = "tagger"
+label_smoothing = 0.0
+neg_prefix = "!"
+overwrite = false
+scorer = {"@scorers":"spacy.tagger_scorer.v1"}
+
+[components.tagger.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.tagger.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.trainable_lemmatizer]
+factory = "trainable_lemmatizer"
+backoff = "orth"
+min_tree_freq = 3
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+
+[components.trainable_lemmatizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.trainable_lemmatizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "distilbert-base-multilingual-cased"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+annotating_components = ["tagger","trainable_lemmatizer"]
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 2000
+buffer = 256
+get_length = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+tag_acc = 0.33
+lemma_acc = 0.33
+ents_f = 0.33
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,116 @@
+{
+  "lang":"sr",
+  "name":"pln_tesla_dbmu",
+  "version":"1.0.0",
+  "description":"sr_pln_tesla_dbmu is a spaCy model meticulously fine-tuned for Part-of-Speech Tagging, Lemmatization, and Named Entity Recognition in Serbian language texts. This advanced model incorporates a transformer layer based on distilbert/distilbert-base-multilingual-cased, enhancing its analytical capabilities. It is proficient in identifying 7 distinct categories of entities: PERS (persons), ROLE (professions), DEMO (demonyms), ORG (organizations), LOC (locations), WORK (artworks), and EVENT (events). Detailed information about these categories is available in the accompanying table. The development of this model has been made possible through the support of the Science Fund of the Republic of Serbia, under grant #7276, for the project 'Text Embeddings - Serbian Language Applications - TESLA'.",
+  "author":"Milica Ikoni\u0107 Ne\u0161i\u0107, Sa\u0161a Petalinkar, Mihailo \u0160kori\u0107, Ranka Stankovi\u0107",
+  "email":"",
+  "url":"https://tesla.rgf.bg.ac.rs/",
+  "license":"CC BY-SA 3.0",
+  "spacy_version":">=3.7.2,<3.8.0",
+  "spacy_git_version":"a89eae928",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "tagger":[
+      "ADJ",
+      "ADP",
+      "ADV",
+      "AUX",
+      "CCONJ",
+      "DET",
+      "INTJ",
+      "NOUN",
+      "NUM",
+      "PART",
+      "PRON",
+      "PROPN",
+      "PUNCT",
+      "SCONJ",
+      "VERB",
+      "X"
+    ],
+    "ner":[
+      "DEMO",
+      "EVENT",
+      "LOC",
+      "ORG",
+      "PERS",
+      "ROLE",
+      "WORK"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "tagger",
+    "trainable_lemmatizer",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "tagger",
+    "trainable_lemmatizer",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "tag_acc":0.9815057009,
+    "lemma_acc":0.9797101778,
+    "ents_f":0.9485941877,
+    "ents_p":0.9465813405,
+    "ents_r":0.9506156136,
+    "ents_per_type":{
+      "ROLE":{
+        "p":0.8503487635,
+        "r":0.8804990151,
+        "f":0.8651612903
+      },
+      "PERS":{
+        "p":0.9804580533,
+        "r":0.9852407755,
+        "f":0.982843596
+      },
+      "LOC":{
+        "p":0.9490266393,
+        "r":0.9765419083,
+        "f":0.9625876851
+      },
+      "DEMO":{
+        "p":0.9109375,
+        "r":0.9181102362,
+        "f":0.9145098039
+      },
+      "ORG":{
+        "p":0.8142164782,
+        "r":0.6885245902,
+        "f":0.7461139896
+      },
+      "WORK":{
+        "p":0.5918367347,
+        "r":0.4084507042,
+        "f":0.4833333333
+      },
+      "EVENT":{
+        "p":0.5909090909,
+        "r":0.40625,
+        "f":0.4814814815
+      }
+    },
+    "transformer_loss":6049.5975609321,
+    "tagger_loss":3599.5084625129,
+    "trainable_lemmatizer_loss":4660.6587796062,
+    "ner_loss":1756.5368891107
+  },
+  "requirements":[
+    "spacy-transformers>=1.3.4,<1.4.0"
+  ]
+}

ner/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

ner/moves

@@ -0,0 +1 @@
+��moves�
�{"0":{},"1":{"PERS":66081,"LOC":35152,"ROLE":14259,"ORG":10504,"DEMO":5087,"WORK":973,"EVENT":546},"2":{"PERS":66081,"LOC":35152,"ROLE":14259,"ORG":10504,"DEMO":5087,"WORK":973,"EVENT":546},"3":{"PERS":66081,"LOC":35152,"ROLE":14259,"ORG":10504,"DEMO":5087,"WORK":973,"EVENT":546},"4":{"PERS":66081,"LOC":35152,"ROLE":14259,"ORG":10504,"DEMO":5087,"WORK":973,"EVENT":546,"":1},"5":{"":1}}�cfg��neg_key�

sr_pln_tesla_dbmu-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1bd02539a5b4defa075d093bc3f71a8464fbc42d8e16450a668334cbe348fe
+size 507812233

tagger/cfg

@@ -0,0 +1,23 @@
+{
+  "label_smoothing":0.0,
+  "labels":[
+    "ADJ",
+    "ADP",
+    "ADV",
+    "AUX",
+    "CCONJ",
+    "DET",
+    "INTJ",
+    "NOUN",
+    "NUM",
+    "PART",
+    "PRON",
+    "PROPN",
+    "PUNCT",
+    "SCONJ",
+    "VERB",
+    "X"
+  ],
+  "neg_prefix":"!",
+  "overwrite":false
+}

trainable_lemmatizer/cfg

@@ -0,0 +1,1978 @@
+{
+  "labels":[
+    2,
+    4,
+    7,
+    8,
+    10,
+    12,
+    15,
+    17,
+    20,
+    22,
+    24,
+    26,
+    28,
+    31,
+    34,
+    36,
+    39,
+    41,
+    44,
+    46,
+    49,
+    51,
+    53,
+    54,
+    56,
+    58,
+    60,
+    62,
+    63,
+    66,
+    68,
+    69,
+    71,
+    73,
+    74,
+    76,
+    78,
+    79,
+    81,
+    83,
+    85,
+    87,
+    88,
+    89,
+    91,
+    93,
+    95,
+    97,
+    99,
+    100,
+    102,
+    103,
+    105,
+    107,
+    109,
+    111,
+    113,
+    115,
+    117,
+    119,
+    121,
+    124,
+    126,
+    128,
+    132,
+    134,
+    136,
+    137,
+    139,
+    141,
+    143,
+    147,
+    149,
+    150,
+    153,
+    156,
+    157,
+    159,
+    161,
+    164,
+    166,
+    167,
+    169,
+    172,
+    173,
+    174,
+    175,
+    177,
+    178,
+    179,
+    180,
+    182,
+    184,
+    185,
+    186,
+    187,
+    189,
+    191,
+    193,
+    195,
+    197,
+    199,
+    201,
+    203,
+    205,
+    208,
+    209,
+    210,
+    213,
+    215,
+    217,
+    219,
+    221,
+    222,
+    223,
+    225,
+    227,
+    229,
+    231,
+    233,
+    235,
+    238,
+    240,
+    242,
+    244,
+    246,
+    248,
+    250,
+    252,
+    253,
+    254,
+    255,
+    257,
+    259,
+    260,
+    262,
+    264,
+    266,
+    268,
+    270,
+    271,
+    272,
+    273,
+    274,
+    275,
+    277,
+    279,
+    282,
+    284,
+    285,
+    287,
+    288,
+    290,
+    292,
+    294,
+    295,
+    297,
+    299,
+    300,
+    302,
+    304,
+    306,
+    308,
+    311,
+    313,
+    314,
+    316,
+    317,
+    319,
+    321,
+    322,
+    325,
+    327,
+    328,
+    330,
+    332,
+    333,
+    335,
+    337,
+    339,
+    341,
+    343,
+    345,
+    347,
+    349,
+    351,
+    353,
+    356,
+    358,
+    360,
+    363,
+    365,
+    366,
+    368,
+    370,
+    373,
+    374,
+    376,
+    377,
+    378,
+    380,
+    382,
+    384,
+    386,
+    388,
+    389,
+    390,
+    392,
+    395,
+    398,
+    399,
+    401,
+    402,
+    404,
+    406,
+    408,
+    411,
+    413,
+    416,
+    418,
+    420,
+    421,
+    422,
+    424,
+    426,
+    428,
+    429,
+    432,
+    433,
+    435,
+    438,
+    440,
+    442,
+    444,
+    446,
+    448,
+    450,
+    453,
+    454,
+    455,
+    457,
+    459,
+    461,
+    462,
+    464,
+    465,
+    468,
+    469,
+    471,
+    473,
+    474,
+    476,
+    478,
+    480,
+    482,
+    484,
+    486,
+    487,
+    491,
+    492,
+    493,
+    494,
+    496,
+    498,
+    500,
+    501,
+    503,
+    505,
+    507,
+    508,
+    510,
+    512,
+    515,
+    516,
+    517,
+    518,
+    519,
+    521,
+    523,
+    525,
+    526,
+    528,
+    530,
+    192,
+    532,
+    534,
+    535,
+    537,
+    539,
+    540,
+    541,
+    542,
+    543,
+    545,
+    547,
+    549,
+    550,
+    552,
+    554,
+    556,
+    557,
+    558,
+    559,
+    562,
+    183,
+    565,
+    566,
+    568,
+    570,
+    572,
+    574,
+    576,
+    577,
+    578,
+    580,
+    582,
+    583,
+    587,
+    589,
+    592,
+    593,
+    596,
+    599,
+    601,
+    603,
+    604,
+    606,
+    608,
+    610,
+    612,
+    613,
+    616,
+    618,
+    620,
+    621,
+    623,
+    625,
+    626,
+    627,
+    629,
+    630,
+    631,
+    632,
+    634,
+    635,
+    636,
+    637,
+    638,
+    641,
+    643,
+    645,
+    646,
+    647,
+    650,
+    652,
+    655,
+    657,
+    659,
+    661,
+    663,
+    665,
+    668,
+    669,
+    671,
+    672,
+    674,
+    676,
+    261,
+    680,
+    681,
+    683,
+    685,
+    687,
+    688,
+    689,
+    690,
+    693,
+    694,
+    696,
+    698,
+    700,
+    702,
+    705,
+    706,
+    708,
+    709,
+    710,
+    713,
+    715,
+    717,
+    718,
+    720,
+    721,
+    723,
+    724,
+    727,
+    728,
+    731,
+    732,
+    734,
+    736,
+    738,
+    741,
+    744,
+    745,
+    746,
+    747,
+    748,
+    750,
+    752,
+    755,
+    757,
+    759,
+    760,
+    762,
+    763,
+    765,
+    766,
+    769,
+    771,
+    772,
+    774,
+    775,
+    777,
+    779,
+    781,
+    782,
+    783,
+    785,
+    787,
+    789,
+    791,
+    792,
+    794,
+    796,
+    797,
+    798,
+    800,
+    802,
+    803,
+    804,
+    806,
+    809,
+    811,
+    813,
+    815,
+    818,
+    819,
+    821,
+    822,
+    825,
+    827,
+    829,
+    830,
+    833,
+    834,
+    836,
+    837,
+    840,
+    841,
+    843,
+    844,
+    846,
+    847,
+    848,
+    850,
+    851,
+    853,
+    854,
+    855,
+    856,
+    858,
+    860,
+    862,
+    863,
+    864,
+    865,
+    867,
+    869,
+    870,
+    871,
+    872,
+    876,
+    879,
+    882,
+    884,
+    887,
+    889,
+    891,
+    892,
+    893,
+    895,
+    898,
+    900,
+    902,
+    904,
+    906,
+    909,
+    911,
+    913,
+    915,
+    916,
+    917,
+    918,
+    920,
+    922,
+    923,
+    924,
+    925,
+    928,
+    930,
+    931,
+    932,
+    934,
+    937,
+    940,
+    943,
+    945,
+    946,
+    950,
+    951,
+    954,
+    956,
+    957,
+    958,
+    959,
+    960,
+    962,
+    964,
+    968,
+    970,
+    972,
+    974,
+    975,
+    977,
+    979,
+    980,
+    982,
+    983,
+    985,
+    987,
+    988,
+    991,
+    993,
+    995,
+    997,
+    998,
+    999,
+    1000,
+    1002,
+    1004,
+    1006,
+    1008,
+    1010,
+    1012,
+    1014,
+    1016,
+    1018,
+    1019,
+    1020,
+    1021,
+    1022,
+    1024,
+    1027,
+    1029,
+    1030,
+    1032,
+    1034,
+    1037,
+    1039,
+    1041,
+    1044,
+    1046,
+    1047,
+    1049,
+    1050,
+    1051,
+    1053,
+    1055,
+    1057,
+    1059,
+    1060,
+    1062,
+    1063,
+    1066,
+    1068,
+    1071,
+    1074,
+    1076,
+    1079,
+    1081,
+    1083,
+    1084,
+    1086,
+    1087,
+    1088,
+    1089,
+    1091,
+    1093,
+    1095,
+    1096,
+    1097,
+    1099,
+    1101,
+    1103,
+    1104,
+    1105,
+    1106,
+    1107,
+    1109,
+    1111,
+    1113,
+    1115,
+    1116,
+    1117,
+    1118,
+    1120,
+    1122,
+    1124,
+    1126,
+    1128,
+    1129,
+    1132,
+    1135,
+    1138,
+    1140,
+    1141,
+    1142,
+    1143,
+    1145,
+    1146,
+    1147,
+    1148,
+    1149,
+    1151,
+    1153,
+    1154,
+    1155,
+    1156,
+    1158,
+    1160,
+    1161,
+    1162,
+    1164,
+    1165,
+    1166,
+    1167,
+    1168,
+    1169,
+    1170,
+    1171,
+    1172,
+    1173,
+    1174,
+    1175,
+    1177,
+    1178,
+    1180,
+    1181,
+    1183,
+    1185,
+    1186,
+    1187,
+    1189,
+    1192,
+    1193,
+    1195,
+    1196,
+    1197,
+    1199,
+    1201,
+    1202,
+    1204,
+    1206,
+    1207,
+    1208,
+    1210,
+    1211,
+    1214,
+    1216,
+    1217,
+    1219,
+    1221,
+    1222,
+    1224,
+    1226,
+    1227,
+    1228,
+    1229,
+    1232,
+    1234,
+    1237,
+    1239,
+    1241,
+    1242,
+    1243,
+    1245,
+    1246,
+    1249,
+    1251,
+    1253,
+    1255,
+    1256,
+    1257,
+    1258,
+    1260,
+    1262,
+    1264,
+    1266,
+    1267,
+    1269,
+    1270,
+    1271,
+    1272,
+    1274,
+    1275,
+    1277,
+    1278,
+    1280,
+    1282,
+    1284,
+    1286,
+    1288,
+    1290,
+    1291,
+    1292,
+    1293,
+    1296,
+    1298,
+    1301,
+    1303,
+    1305,
+    1307,
+    1308,
+    1309,
+    1311,
+    1312,
+    1313,
+    1314,
+    1316,
+    1317,
+    1318,
+    1319,
+    1321,
+    1323,
+    1324,
+    1325,
+    1326,
+    1328,
+    1330,
+    1332,
+    1001,
+    1334,
+    1335,
+    1336,
+    1339,
+    1340,
+    1342,
+    1344,
+    1346,
+    1347,
+    1349,
+    1352,
+    1354,
+    1356,
+    1357,
+    1359,
+    1362,
+    1363,
+    1364,
+    1365,
+    1366,
+    1368,
+    1369,
+    1370,
+    1371,
+    1373,
+    1376,
+    1377,
+    1378,
+    1380,
+    1381,
+    1382,
+    1384,
+    1386,
+    1388,
+    1389,
+    1390,
+    1391,
+    1393,
+    1396,
+    1398,
+    1399,
+    1401,
+    1404,
+    1406,
+    1408,
+    1409,
+    1410,
+    1412,
+    1414,
+    1415,
+    1417,
+    1419,
+    1420,
+    1421,
+    1423,
+    1424,
+    1428,
+    1429,
+    1430,
+    1432,
+    1435,
+    1436,
+    1437,
+    1439,
+    1441,
+    1442,
+    1444,
+    1446,
+    1447,
+    1448,
+    1449,
+    1451,
+    1452,
+    1453,
+    1454,
+    1457,
+    1459,
+    1461,
+    1462,
+    1464,
+    1465,
+    1466,
+    1467,
+    1468,
+    1471,
+    1473,
+    1474,
+    1475,
+    1477,
+    1480,
+    1481,
+    1483,
+    1485,
+    1486,
+    1488,
+    1489,
+    1490,
+    1491,
+    1494,
+    1495,
+    1496,
+    1497,
+    1499,
+    1500,
+    1501,
+    1502,
+    1503,
+    1505,
+    1507,
+    1508,
+    1509,
+    1511,
+    1512,
+    1513,
+    1515,
+    1517,
+    1518,
+    1519,
+    1521,
+    1523,
+    1524,
+    1525,
+    1527,
+    1529,
+    1531,
+    1532,
+    1533,
+    1535,
+    1536,
+    1537,
+    1538,
+    218,
+    1540,
+    1542,
+    1543,
+    1544,
+    1546,
+    1547,
+    1548,
+    1549,
+    1550,
+    1552,
+    1553,
+    1554,
+    1555,
+    1556,
+    1557,
+    1560,
+    1562,
+    1564,
+    1566,
+    1568,
+    1569,
+    1570,
+    1571,
+    1572,
+    1574,
+    1576,
+    1578,
+    1579,
+    1582,
+    1584,
+    1586,
+    1588,
+    1590,
+    1592,
+    1593,
+    1594,
+    1595,
+    1596,
+    1599,
+    1600,
+    1601,
+    1602,
+    1603,
+    1604,
+    1605,
+    1606,
+    1608,
+    1610,
+    1611,
+    1613,
+    1614,
+    1616,
+    1618,
+    1619,
+    1620,
+    1621,
+    1623,
+    1624,
+    1625,
+    1627,
+    1628,
+    1629,
+    1630,
+    1631,
+    1632,
+    1633,
+    1635,
+    1638,
+    1640,
+    1641,
+    1643,
+    1644,
+    1645,
+    1646,
+    1648,
+    1650,
+    1652,
+    1653,
+    1656,
+    1658,
+    1659,
+    1661,
+    1663,
+    1665,
+    1666,
+    1667,
+    1669,
+    1670,
+    1671,
+    1673,
+    1675,
+    1677,
+    1678,
+    1679,
+    1680,
+    1682,
+    1684,
+    1686,
+    1688,
+    1690,
+    1692,
+    1693,
+    1694,
+    1696,
+    1697,
+    1698,
+    1700,
+    1701,
+    1702,
+    1703,
+    1704,
+    1705,
+    1707,
+    1709,
+    1711,
+    1713,
+    1715,
+    1716,
+    1717,
+    1720,
+    1722,
+    1723,
+    1724,
+    1726,
+    1728,
+    1730,
+    1733,
+    1735,
+    1736,
+    1737,
+    1739,
+    1740,
+    1742,
+    1745,
+    1747,
+    1749,
+    1751,
+    1752,
+    1754,
+    1756,
+    1757,
+    1759,
+    1760,
+    1761,
+    1762,
+    1764,
+    1765,
+    1766,
+    1768,
+    1769,
+    1770,
+    1772,
+    1773,
+    1775,
+    1776,
+    1777,
+    1779,
+    1781,
+    1783,
+    1785,
+    1787,
+    1789,
+    1791,
+    1792,
+    1794,
+    1795,
+    1798,
+    1800,
+    1802,
+    1803,
+    1804,
+    1805,
+    1807,
+    1809,
+    1811,
+    1813,
+    1814,
+    1815,
+    1817,
+    1819,
+    1820,
+    1821,
+    1822,
+    1824,
+    1826,
+    1828,
+    1831,
+    1832,
+    1834,
+    1836,
+    1837,
+    1838,
+    1839,
+    1840,
+    1841,
+    1842,
+    1843,
+    1846,
+    1848,
+    1849,
+    1851,
+    1854,
+    1857,
+    1859,
+    77,
+    1860,
+    1861,
+    1863,
+    1864,
+    1865,
+    1866,
+    1867,
+    1869,
+    1871,
+    1873,
+    1874,
+    1876,
+    1878,
+    1879,
+    1880,
+    1882,
+    1883,
+    1886,
+    1887,
+    1888,
+    1889,
+    1890,
+    1891,
+    1893,
+    1895,
+    1896,
+    1897,
+    1898,
+    1899,
+    1900,
+    1903,
+    1905,
+    1906,
+    1907,
+    1908,
+    1909,
+    1910,
+    1913,
+    1914,
+    1915,
+    1916,
+    1917,
+    1919,
+    1920,
+    1921,
+    1922,
+    1924,
+    1925,
+    1926,
+    1928,
+    1929,
+    1930,
+    1932,
+    1934,
+    1936,
+    1938,
+    1939,
+    1941,
+    1942,
+    1943,
+    1944,
+    1946,
+    1947,
+    1949,
+    1950,
+    1952,
+    1954,
+    1955,
+    1956,
+    1957,
+    1958,
+    1959,
+    1960,
+    1962,
+    1963,
+    1964,
+    1965,
+    1966,
+    1968,
+    1969,
+    1970,
+    1972,
+    1974,
+    1975,
+    1978,
+    1979,
+    1980,
+    1982,
+    1983,
+    1985,
+    1987,
+    1988,
+    1990,
+    1991,
+    1992,
+    1994,
+    1995,
+    1996,
+    1998,
+    1999,
+    2000,
+    2001,
+    2002,
+    2004,
+    2006,
+    2007,
+    2009,
+    2011,
+    2013,
+    2014,
+    2017,
+    2019,
+    2023,
+    2024,
+    2025,
+    2026,
+    2027,
+    2030,
+    2031,
+    2033,
+    2034,
+    2035,
+    2036,
+    2037,
+    2039,
+    2040,
+    2042,
+    2043,
+    2044,
+    2046,
+    2047,
+    2048,
+    2049,
+    2050,
+    2051,
+    2053,
+    94,
+    2055,
+    2057,
+    2059,
+    2061,
+    2062,
+    2063,
+    2064,
+    2065,
+    2066,
+    2067,
+    2068,
+    2070,
+    2073,
+    2076,
+    2077,
+    2079,
+    2080,
+    2081,
+    2082,
+    2083,
+    2084,
+    2085,
+    2086,
+    2089,
+    2090,
+    2091,
+    2092,
+    2093,
+    2094,
+    2095,
+    2096,
+    2097,
+    2098,
+    2099,
+    2100,
+    2102,
+    2104,
+    2105,
+    2106,
+    2108,
+    2109,
+    2111,
+    2113,
+    2114,
+    2115,
+    2117,
+    2119,
+    2120,
+    2121,
+    2122,
+    2124,
+    2125,
+    2126,
+    2127,
+    2128,
+    2130,
+    2131,
+    2132,
+    2133,
+    2135,
+    2136,
+    2137,
+    2138,
+    2139,
+    2140,
+    2142,
+    2144,
+    2145,
+    2146,
+    2148,
+    2151,
+    2152,
+    2153,
+    2154,
+    2155,
+    2156,
+    2158,
+    2159,
+    2161,
+    2162,
+    2163,
+    2164,
+    2165,
+    2167,
+    2168,
+    2169,
+    2170,
+    2171,
+    2172,
+    2173,
+    2174,
+    2176,
+    2177,
+    2178,
+    2179,
+    2180,
+    2183,
+    2184,
+    2185,
+    2186,
+    2188,
+    2189,
+    2192,
+    2194,
+    2196,
+    2197,
+    2198,
+    2200,
+    2201,
+    2203,
+    2204,
+    2205,
+    2206,
+    2207,
+    2210,
+    2211,
+    2212,
+    2214,
+    2217,
+    2218,
+    2220,
+    2222,
+    2224,
+    2225,
+    2226,
+    2228,
+    1427,
+    2229,
+    2230,
+    2231,
+    2232,
+    2233,
+    2234,
+    2235,
+    2237,
+    2238,
+    2241,
+    2242,
+    2243,
+    2246,
+    2247,
+    2249,
+    2250,
+    2252,
+    2253,
+    2254,
+    2257,
+    2258,
+    2259,
+    2261,
+    2262,
+    2263,
+    2264,
+    2267,
+    2270,
+    2272,
+    2273,
+    2275,
+    2276,
+    2277,
+    2279,
+    2281,
+    2282,
+    2283,
+    2284,
+    2286,
+    2287,
+    2288,
+    2290,
+    2292,
+    2294,
+    2295,
+    2296,
+    2298,
+    2300,
+    2301,
+    2302,
+    2303,
+    2305,
+    2307,
+    2308,
+    2310,
+    2311,
+    2312,
+    2313,
+    2314,
+    2315,
+    2316,
+    2317,
+    2318,
+    2320,
+    2321,
+    2322,
+    2323,
+    2324,
+    2325,
+    2326,
+    2328,
+    2330,
+    2331,
+    2333,
+    2334,
+    2336,
+    2337,
+    2339,
+    2341,
+    2342,
+    2344,
+    2345,
+    2346,
+    2347,
+    2349,
+    2351,
+    2353,
+    2355,
+    2356,
+    2357,
+    2358,
+    2360,
+    2362,
+    2364,
+    2365,
+    2366,
+    2367,
+    2368,
+    2369,
+    2372,
+    2374,
+    2376,
+    2377,
+    2378,
+    2380,
+    2381,
+    2382,
+    2383,
+    2385,
+    2386,
+    2387,
+    2389,
+    2390,
+    2391,
+    2392,
+    2393,
+    2395,
+    2396,
+    2398,
+    2401,
+    2403,
+    2404,
+    2405,
+    2406,
+    2407,
+    2409,
+    2410,
+    2411,
+    2412,
+    2415,
+    2417,
+    2418,
+    2419,
+    2421,
+    2422,
+    2423,
+    2425,
+    1986,
+    2427,
+    2428,
+    2429,
+    2430,
+    2432,
+    2434,
+    2436,
+    2437,
+    2439,
+    2441,
+    2442,
+    2443,
+    2446,
+    2447,
+    2449,
+    2450,
+    2451,
+    2452,
+    2453,
+    2454,
+    2455,
+    2457,
+    2458,
+    2460,
+    2461,
+    2463,
+    2465,
+    2466,
+    2467,
+    2468,
+    2470,
+    2472,
+    2474,
+    2475,
+    2477,
+    2479,
+    2480,
+    2482,
+    2483,
+    2485,
+    2486,
+    2487,
+    2490,
+    2491,
+    2493,
+    2494,
+    2495,
+    2497,
+    2498,
+    2499,
+    2500,
+    2501,
+    2502,
+    2503,
+    2504,
+    2506,
+    2507,
+    2508,
+    2509,
+    2510,
+    2512,
+    2514,
+    2517,
+    2518,
+    2519,
+    2521,
+    2522,
+    2524,
+    2525,
+    2527,
+    2528,
+    2530,
+    2532,
+    2533,
+    2535,
+    2536,
+    2537,
+    2538,
+    2539,
+    2541,
+    2544,
+    2545,
+    2546,
+    2547,
+    2549,
+    2551,
+    2554,
+    2555,
+    2556,
+    2557,
+    2559,
+    2560,
+    2561,
+    2562,
+    2563,
+    2564,
+    2565,
+    2567,
+    2569,
+    2570,
+    2571,
+    2573,
+    2574,
+    2575,
+    2576,
+    2577,
+    2578,
+    2580,
+    2582,
+    2585,
+    2587,
+    2589,
+    2591,
+    2592,
+    2594,
+    2595,
+    2597,
+    2599,
+    2600,
+    2602,
+    2604,
+    2605,
+    2607,
+    2608,
+    2610,
+    2612,
+    2615,
+    2616,
+    2618,
+    2620,
+    2621,
+    2622,
+    2623,
+    2624,
+    2627,
+    2629,
+    2630,
+    2631,
+    2634,
+    2635,
+    2638,
+    2640,
+    2641,
+    2642,
+    2643,
+    2645,
+    2647,
+    2648,
+    2650,
+    2653,
+    2654,
+    2656,
+    2659,
+    2661,
+    2663,
+    2664,
+    2666,
+    2667,
+    2668,
+    2669,
+    2671,
+    2672,
+    2673,
+    2676,
+    2677,
+    2680,
+    2681,
+    2682,
+    2685,
+    2686,
+    2687,
+    2688,
+    2689,
+    2691,
+    2692,
+    2693,
+    2694,
+    2695,
+    2696,
+    2698,
+    2699,
+    2700,
+    2701,
+    2702,
+    2703,
+    2704,
+    2706,
+    2707,
+    2708,
+    2709,
+    2710,
+    2713,
+    2715,
+    2717,
+    2718,
+    2720,
+    2721,
+    2722,
+    2723,
+    2725,
+    2727,
+    2730,
+    2732,
+    2733,
+    2734,
+    2736,
+    2737,
+    2738,
+    2739,
+    2742,
+    2743,
+    2746,
+    2747,
+    2748,
+    2749,
+    2750,
+    2751,
+    2752,
+    2753,
+    2754,
+    2756,
+    2757,
+    2759,
+    2760,
+    2761,
+    2762,
+    2763,
+    2764,
+    2765,
+    2767,
+    2769,
+    2771,
+    2772,
+    2773,
+    2774,
+    2775,
+    2776,
+    2778,
+    2781,
+    2783,
+    2786,
+    2787,
+    2788,
+    2790,
+    2793,
+    2794,
+    2795,
+    2796,
+    2797,
+    2798,
+    2800,
+    2801,
+    2802,
+    2803,
+    2805,
+    2806,
+    2807,
+    2809,
+    2810,
+    2811,
+    2812,
+    2814,
+    2816,
+    2817,
+    2820,
+    2821,
+    2822,
+    2823,
+    2824,
+    2825,
+    2827,
+    2828,
+    2830,
+    2831,
+    2834,
+    2835,
+    2836,
+    2837,
+    2839,
+    2840,
+    2841,
+    2842,
+    2843,
+    2845,
+    2846,
+    2847,
+    2849,
+    2850,
+    2852,
+    2853,
+    2854,
+    2855,
+    2856,
+    2857,
+    2859,
+    2861,
+    2863,
+    2865,
+    2866,
+    2868,
+    2870,
+    2872,
+    2873,
+    2875,
+    2876,
+    2878,
+    2879,
+    2880,
+    2882,
+    2884,
+    2885,
+    2886,
+    2888,
+    2889,
+    2891,
+    2892,
+    2894,
+    2895,
+    2896,
+    2898,
+    2899,
+    2900,
+    2901,
+    2902,
+    2903,
+    2904,
+    2905,
+    2907,
+    2908,
+    2909,
+    2910,
+    2911,
+    2912,
+    2914,
+    2915,
+    2916,
+    2918,
+    2919,
+    1056,
+    2920,
+    2922,
+    2923,
+    2925,
+    2926,
+    2927,
+    2929,
+    2930,
+    2931,
+    2933,
+    2934,
+    2936,
+    2938,
+    2939,
+    2940,
+    2943,
+    2945,
+    2946,
+    2948,
+    2949,
+    2951,
+    2952,
+    2954,
+    2955,
+    2956,
+    2957,
+    2958,
+    2959,
+    2961,
+    2962,
+    2964,
+    2965,
+    2966,
+    2968,
+    2970,
+    2971,
+    2972,
+    2973,
+    2974,
+    2976,
+    2977,
+    2978,
+    2979,
+    2980,
+    2982,
+    2984,
+    2986,
+    2987,
+    2988,
+    2989,
+    2991,
+    2993,
+    2994,
+    2996,
+    2999,
+    3000,
+    3001,
+    3002,
+    3003,
+    3004,
+    3005,
+    3006,
+    3008,
+    3010,
+    3011,
+    3012,
+    3014,
+    3016,
+    3019,
+    3022,
+    3023,
+    3024,
+    3025,
+    3026,
+    3028,
+    3031,
+    3032,
+    3033,
+    3035,
+    3036,
+    3038,
+    3040,
+    3041,
+    3042,
+    3043,
+    3045,
+    3048,
+    3049,
+    3050,
+    3051,
+    3052,
+    3053,
+    3054,
+    3055,
+    3056,
+    3057,
+    3058,
+    3059,
+    3060,
+    3062,
+    3065,
+    3068,
+    3069,
+    3070,
+    3071,
+    3072,
+    3073,
+    3074,
+    3075,
+    3076,
+    3077,
+    3079,
+    3080,
+    3081,
+    3082,
+    3083,
+    3084,
+    3085,
+    3086,
+    3087,
+    3089,
+    3090,
+    3091,
+    3092,
+    3093,
+    3094,
+    3096,
+    3097,
+    3098,
+    3099,
+    3100,
+    3101,
+    3102,
+    3103,
+    3104,
+    3105,
+    3106,
+    3108,
+    3109,
+    3110,
+    3111,
+    3114,
+    3116,
+    3117
+  ]
+}

trainable_lemmatizer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c2940e7dcf34e2768bb5ebc75a5396d7666d00cac26c622ec645edfe0839ff
+size 6072677

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d74046bee285f0163b572717408914d0d20398c7dad415d5e9245cfa3a89354
+size 542890597

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}