Upload folder using huggingface_hub

.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
+textcat_multilabel/model filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

config.cfg

@@ -0,0 +1,154 @@
+[paths]
+train = "/content/spacy_textcat_train.spacy"
+dev = "/content/spacy_textcat_test.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "nl"
+pipeline = ["transformer","textcat_multilabel"]
+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.textcat_multilabel]
+factory = "textcat_multilabel"
+scorer = {"@scorers":"spacy.textcat_multilabel_scorer.v2"}
+threshold = 0.5
+
+[components.textcat_multilabel.model]
+@architectures = "spacy.TextCatEnsemble.v2"
+nO = null
+
+[components.textcat_multilabel.model.linear_model]
+@architectures = "spacy.TextCatBOW.v3"
+exclusive_classes = false
+length = 262144
+ngram_size = 1
+no_output_layer = false
+nO = null
+
+[components.textcat_multilabel.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 = "svercoutere/robbert-2023-dutch-base-abb"
+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"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_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]
+cats_score = 1.0
+cats_score_desc = null
+cats_micro_p = null
+cats_micro_r = null
+cats_micro_f = null
+cats_macro_p = null
+cats_macro_r = null
+cats_macro_f = null
+cats_macro_auc = null
+cats_f_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 +1,106 @@
+{
+  "lang":"nl",
+  "name":"pipeline",
+  "version":"0.0.0",
+  "spacy_version":">=3.7.5,<3.8.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"a6d0fc360",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null,
+    "mode":"default"
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "textcat_multilabel":[
+      "burgerzaken",
+      "stadsbestuur",
+      "cultuur, sport en vrije tijd",
+      "mobiliteit en openbare werken",
+      "groen en milieu",
+      "onderwijs en kinderopvang",
+      "samenleven, welzijn en gezondheid",
+      "werken en ondernemen",
+      "wonen en (ver)bouwen"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "textcat_multilabel"
+  ],
+  "components":[
+    "transformer",
+    "textcat_multilabel"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "cats_score":0.9719654552,
+    "cats_score_desc":"macro AUC",
+    "cats_micro_p":0.8677536232,
+    "cats_micro_r":0.8607367475,
+    "cats_micro_f":0.8642309427,
+    "cats_macro_p":0.7953757735,
+    "cats_macro_r":0.8020388718,
+    "cats_macro_f":0.7967031577,
+    "cats_macro_auc":0.9719654552,
+    "cats_f_per_type":{
+      "burgerzaken":{
+        "p":0.8823529412,
+        "r":0.8823529412,
+        "f":0.8823529412
+      },
+      "stadsbestuur":{
+        "p":0.936,
+        "r":0.8780487805,
+        "f":0.9060987415
+      },
+      "cultuur, sport en vrije tijd":{
+        "p":0.7671232877,
+        "r":0.8549618321,
+        "f":0.8086642599
+      },
+      "mobiliteit en openbare werken":{
+        "p":0.8923076923,
+        "r":0.8529411765,
+        "f":0.8721804511
+      },
+      "groen en milieu":{
+        "p":0.6481481481,
+        "r":0.7954545455,
+        "f":0.7142857143
+      },
+      "onderwijs en kinderopvang":{
+        "p":0.8947368421,
+        "r":0.8717948718,
+        "f":0.8831168831
+      },
+      "samenleven, welzijn en gezondheid":{
+        "p":0.6511627907,
+        "r":0.6666666667,
+        "f":0.6588235294
+      },
+      "werken en ondernemen":{
+        "p":0.6153846154,
+        "r":0.5,
+        "f":0.5517241379
+      },
+      "wonen en (ver)bouwen":{
+        "p":0.8711656442,
+        "r":0.9161290323,
+        "f":0.893081761
+      }
+    },
+    "transformer_loss":10.075634643,
+    "textcat_multilabel_loss":1.4619364219
+  }
+}

textcat_multilabel/cfg

@@ -0,0 +1,14 @@
+{
+  "labels":[
+    "burgerzaken",
+    "stadsbestuur",
+    "cultuur, sport en vrije tijd",
+    "mobiliteit en openbare werken",
+    "groen en milieu",
+    "onderwijs en kinderopvang",
+    "samenleven, welzijn en gezondheid",
+    "werken en ondernemen",
+    "wonen en (ver)bouwen"
+  ],
+  "threshold":0.5
+}

textcat_multilabel/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c150416d1a00c98f54bb4cb661e4dbc9aae4102d5d058d81b7678f2a24e8c001
+size 16564411

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 sha256:5ed2d953e347826f578226f456e8697e263d84f0fa889425ce3dfe19a6cbd5f5
+size 501386812

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"
+}