Update spaCy pipeline

.gitattributes

@@ -33,3 +33,5 @@ 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_pner_tesla_j355-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- sr
+license: cc-by-sa-3.0
+model-index:
+- name: sr_pner_tesla_j355
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.9516940624
+    - name: NER Recall
+      type: recall
+      value: 0.9596130429
+    - name: NER F Score
+      type: f_score
+      value: 0.9556371476
+  - task:
+      name: TAG
+      type: token-classification
+    metrics:
+    - name: TAG (XPOS) Accuracy
+      type: accuracy
+      value: 0.9841723761
+---
+sr_pner_tesla_j355 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 Jerteh-355, 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_pner_tesla_j355` |
+| **Version** | `1.0.0` |
+| **spaCy** | `>=3.7.2,<3.8.0` |
+| **Default Pipeline** | `transformer`, `tagger`, `ner` |
+| **Components** | `transformer`, `tagger`, `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` | 98.42 |
+| `ENTS_F` | 95.56 |
+| `ENTS_P` | 95.17 |
+| `ENTS_R` | 95.96 |
+| `TRANSFORMER_LOSS` | 151439.86 |
+| `TAGGER_LOSS` | 141230.81 |
+| `NER_LOSS` | 84043.38 |

config.cfg

@@ -0,0 +1,167 @@
+[paths]
+train = "./train.spacy"
+dev = "./dev.spacy"
+vectors = null
+bert = "E:\\scratch2lm\\bert modeli\\jerteh-355"
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "sr"
+pipeline = ["transformer","tagger","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.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 = ${paths.bert}
+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"]
+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 = 0.5
+ents_f = 0.5
+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 +1,112 @@
+{
+  "lang":"sr",
+  "name":"pner_tesla_j355",
+  "version":"1.0.0",
+  "description":"sr_pner_tesla_j355 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 Jerteh-355, 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",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "tagger",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "tag_acc":0.9841723761,
+    "ents_f":0.9556371476,
+    "ents_p":0.9516940624,
+    "ents_r":0.9596130429,
+    "ents_per_type":{
+      "ROLE":{
+        "p":0.8498759305,
+        "r":0.8995403808,
+        "f":0.8740031898
+      },
+      "PERS":{
+        "p":0.9859102244,
+        "r":0.9889931207,
+        "f":0.9874492663
+      },
+      "LOC":{
+        "p":0.9557385486,
+        "r":0.9789140749,
+        "f":0.9671875
+      },
+      "DEMO":{
+        "p":0.9150227618,
+        "r":0.9496062992,
+        "f":0.9319938176
+      },
+      "ORG":{
+        "p":0.835443038,
+        "r":0.7213114754,
+        "f":0.7741935484
+      },
+      "WORK":{
+        "p":0.6461538462,
+        "r":0.5915492958,
+        "f":0.6176470588
+      },
+      "EVENT":{
+        "p":0.6774193548,
+        "r":0.65625,
+        "f":0.6666666667
+      }
+    },
+    "transformer_loss":1514.3986259683,
+    "tagger_loss":1412.3081215593,
+    "ner_loss":840.4338100267
+  },
+  "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_pner_tesla_j355-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396741d112805677bcd33da5746601a25c979f1352826aca98a052479903e4c6
+size 1309084368

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
+}

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:e33ff19e8a8543d01c7158b35ac9a6bb518f562ff087d88f51cc6160fcfbfa31
+size 1420537659

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"
+}