Upload 12 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+tok2vec/model filter=lfs diff=lfs merge=lfs -text

config.cfg

@@ -0,0 +1,159 @@
+[paths]
+train = "../VM/data/spacy-spancat-paragraphs/train/train.spacy"
+dev = "../VM/data/spacy-spancat-paragraphs/dev/train.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "fr"
+pipeline = ["tok2vec","spancat"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[components.spancat]
+factory = "spancat"
+max_positive = null
+scorer = {"@scorers":"spacy.spancat_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.spancat.model]
+@architectures = "spacy.SpanCategorizer.v1"
+
+[components.spancat.model.reducer]
+@layers = "spacy.mean_max_reducer.v1"
+hidden_size = 128
+
+[components.spancat.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = null
+nI = null
+
+[components.spancat.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.spancat.suggester]
+@misc = "spacy.ngram_range_suggester.v1"
+min_size = 1
+max_size = 44
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
+[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]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 10
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[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
+learn_rate = 0.001
+
+[training.score_weights]
+spans_sc_f = 1.0
+spans_sc_p = 0.0
+spans_sc_r = 0.0
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.components.spancat]
+
+[initialize.components.spancat.labels]
+@readers = "spacy.read_labels.v1"
+path = "../VM/data/spacy-spancat-paragraphs/train/labels/spancat.json"
+require = false
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,56 @@
+{
+  "lang":"fr",
+  "name":"pipeline",
+  "version":"0.0.0",
+  "spacy_version":">=3.7.2,<3.8.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"a89eae928",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null,
+    "mode":"default"
+  },
+  "labels":{
+    "tok2vec":[
+
+    ],
+    "spancat":[
+      "Head",
+      "Domain-mark",
+      "NC-Spatial",
+      "ENE-Spatial",
+      "NP-Spatial",
+      "Relation",
+      "Latlong",
+      "NC-Person",
+      "NP-Person",
+      "ENE-Person",
+      "NP-Misc",
+      "ENE-Misc"
+    ]
+  },
+  "pipeline":[
+    "tok2vec",
+    "spancat"
+  ],
+  "components":[
+    "tok2vec",
+    "spancat"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "spans_sc_f":0.8158965765,
+    "spans_sc_p":0.875192604,
+    "spans_sc_r":0.7641255605,
+    "tok2vec_loss":23.5552025161,
+    "spancat_loss":4975.8467903137
+  }
+}

spancat/cfg

@@ -0,0 +1,21 @@
+{
+  "labels":[
+    "Head",
+    "Domain-mark",
+    "NC-Spatial",
+    "ENE-Spatial",
+    "NP-Spatial",
+    "Relation",
+    "Latlong",
+    "NC-Person",
+    "NP-Person",
+    "ENE-Person",
+    "NP-Misc",
+    "ENE-Misc"
+  ],
+  "spans_key":"sc",
+  "threshold":0.5,
+  "max_positive":null,
+  "negative_weight":null,
+  "allow_overlap":true
+}

tok2vec/cfg

@@ -0,0 +1,3 @@
+{
+
+}

tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b88e08479cd5d2c07ff6ec44fdf4b7c29e586ed57bfef4ea618f68d372bc115
+size 6009091

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"
+}