Upload folder using huggingface_hub

PKG-INFO

@@ -0,0 +1,21 @@
+Metadata-Version: 2.1
+Name: dummy-ner
+Version: 0.1.0
+Summary: 
+Author: Perceval Wajsburt
+Author-email: perceval.wajsburt@aphp.fr
+Requires-Python: >=3.7.1,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: edsnlp[ml] (>=0.11.2)
+Requires-Dist: sentencepiece (>=0.1.96,<0.2.0)
+Description-Content-Type: text/markdown
+
+# Dummy EDS-NLP NER model
+
+This model was trained on the DEFT 2020 Track 3 dataset, but it's main purpose is to
+test the integration of EDS-NLP with the Hugging Face Hub.

README.md

@@ -1,3 +1,4 @@
----
-license: bsd-3-clause
----
+# Dummy EDS-NLP NER model
+
+This model was trained on the DEFT 2020 Track 3 dataset, but it's main purpose is to
+test the integration of EDS-NLP with the Hugging Face Hub.

dummy_ner/__init__.py

@@ -0,0 +1,17 @@
+
+# -----------------------------------------
+# This section was autogenerated by edsnlp
+# -----------------------------------------
+
+import edsnlp
+from pathlib import Path
+from typing import Optional, Dict, Any
+
+__version__ = None
+
+def load(
+    overrides: Optional[Dict[str, Any]] = None,
+) -> edsnlp.Pipeline:
+    artifacts_path = Path(__file__).parent / "artifacts"
+    model = edsnlp.load(artifacts_path, overrides=overrides)
+    return model

dummy_ner/artifacts/config.cfg

@@ -0,0 +1,33 @@
+[nlp]
+lang = "eds"
+pipeline = ["ner"]
+
+[nlp.tokenizer]
+@tokenizers = "eds.tokenizer"
+
+[components]
+
+[components.ner]
+@factory = "eds.ner_crf"
+target_span_getter = "gold_spans"
+labels = ["anatomie", "date", "dose", "duree", "examen", "frequence", "mode", "moment", "pathologie", "sosy", "substance", "traitement", "valeur"]
+infer_span_setter = true
+mode = "joint"
+window = 40
+stride = 20
+
+[components.ner.embedding]
+@factory = "eds.text_cnn"
+kernel_sizes = [3]
+
+[components.ner.embedding.embedding]
+@factory = "eds.transformer"
+model = "./ner/embedding/embedding"
+window = 128
+stride = 96
+
+[components.ner.span_setter]
+ents = true
+* = true
+gold_spans = ["anatomie", "date", "dose", "duree", "examen", "frequence", "mode", "moment", "pathologie", "sosy", "substance", "traitement", "valeur"]
+

dummy_ner/artifacts/meta.json

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

dummy_ner/artifacts/ner/embedding/embedding/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./ner/embedding/embedding",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

dummy_ner/artifacts/ner/embedding/embedding/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead96338fa7a78a05b3f0cb78763d825f9144b6ae6ff346092261e8d3c3ef046
+size 17547912

dummy_ner/artifacts/ner/embedding/embedding/parameters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ad71db7a9edf51b3a873b80cab6a1af6f1ba026021af76bbee919c451ca5a4
+size 8992

dummy_ner/artifacts/ner/embedding/embedding/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

dummy_ner/artifacts/ner/embedding/embedding/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

dummy_ner/artifacts/ner/embedding/parameters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4653e3d2bda5ef27335411413e121eefdd4ceb7aed323f3964e9ad43cbab4d8d
+size 263528

dummy_ner/artifacts/ner/parameters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5a517b89e44c372a89938808359ff8113651c41e383d10d88a6fd01d80aea7
+size 34363

dummy_ner/artifacts/tokenizer

@@ -0,0 +1 @@
+��prefix_search��suffix_search��infix_finditer��token_match��url_match��exceptions��faster_heuristics�

pyproject.toml

@@ -0,0 +1,76 @@
+[build-system]
+requires = [ "poetry-core>=1.0.0", "pypandoc<1.8.0",]
+build-backend = "poetry.core.masonry.api"
+
+[tool.edsnlp]
+model_name = "dummy-ner"
+
+[tool.poetry]
+name = "dummy-ner"
+version = "0.1.0"
+description = ""
+authors = [ "Perceval Wajsburt <perceval.wajsburt@aphp.fr>",]
+readme = "README.md"
+include = [ "dummy_ner/artifacts/**",]
+[[tool.poetry.packages]]
+include = "dummy_ner"
+
+[tool.interrogate]
+ignore-init-method = true
+ignore-init-module = true
+ignore-magic = false
+ignore-semiprivate = false
+ignore-private = false
+ignore-property-decorators = false
+ignore-module = true
+ignore-nested-functions = false
+ignore-nested-classes = true
+ignore-setters = false
+fail-under = 10
+exclude = [ "docs", "build", "tests",]
+verbose = 0
+quiet = false
+whitelist-regex = []
+color = true
+omit-covered-files = false
+
+[tool.mypy]
+plugins = "pydantic.mypy"
+
+[tool.ruff]
+fix = true
+extend-exclude = [ ".git", "__pycache__", "__init__.py", ".mypy_cache", ".pytest_cache", ".venv", "build",]
+line-length = 88
+select = [ "E", "F", "W", "I001",]
+
+[tool.poetry.dependencies]
+python = ">=3.7.1,<4.0"
+sentencepiece = "^0.1.96"
+
+[tool.pytest.ini_options]
+testpaths = [ "tests",]
+
+[tool.ruff.flake8-tidy-imports]
+ban-relative-imports = "parents"
+
+[tool.ruff.extend-per-file-ignores]
+"__init__.py" = [ "F401",]
+
+[tool.ruff.isort]
+known-first-party = [ "edsnlp",]
+known-third-party = [ "build",]
+order-by-type = true
+
+[tool.coverage.report]
+include = [ "quaero_ner/*", "scripts/*",]
+omit = [ "tests/*",]
+exclude_lines = [ "def __repr__", "if __name__ == .__main__.:", "@overload", "pragma: no cover", "raise .*Error", "raise .*Exception", "warn\\(", "if __name__ == .__main__.:", "if TYPE_CHECKING:", "class .*\\bProtocol\\):", "@(abc\\.)?abstractmethod", "Span.set_extension.*", "Doc.set_extension.*", "Token.set_extension.*",]
+
+[tool.poetry.dependencies.edsnlp]
+version = ">=0.11.2"
+extras = [ "ml",]
+
+[tool.poetry.group.docs]
+optional = true
+
+[tool.poetry.group.docs.dependencies]