Instructions to use hjianganthony/en_nerry_rel_tok2vec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use hjianganthony/en_nerry_rel_tok2vec with spaCy:
!pip install https://huggingface.co/hjianganthony/en_nerry_rel_tok2vec/resolve/main/en_nerry_rel_tok2vec-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("en_nerry_rel_tok2vec") # Importing as module. import en_nerry_rel_tok2vec nlp = en_nerry_rel_tok2vec.load() - Notebooks
- Google Colab
- Kaggle
RE with tok2vec
| Feature | Description |
|---|---|
| Name | en_nerry_rel_tok2vec |
| Version | 2.0.0 |
| spaCy | >=3.6.1,<3.7.0 |
| Default Pipeline | tok2vec, ner, relation_extractor |
| Components | tok2vec, ner, relation_extractor |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | HjAnthony |
Label Scheme
View label scheme (4 labels for 2 components)
| Component | Labels |
|---|---|
ner |
CRIME, PERSON, PROCECUTION |
relation_extractor |
INVOVLED_IN |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
70.42 |
ENTS_P |
54.35 |
ENTS_R |
100.00 |
REL_MICRO_P |
55.56 |
REL_MICRO_R |
100.00 |
REL_MICRO_F |
71.43 |
TOK2VEC_LOSS |
0.00 |
RELATION_EXTRACTOR_LOSS |
105.57 |
- Downloads last month
- 2
Evaluation results
- NER Precisionself-reported0.543
- NER Recallself-reported1.000
- NER F Scoreself-reported0.704