Downloads · 30 days
4
2% of all-time downloads
sr_SRPCNNEL
Tanor/sr_SRPCNNEL
sr_SRPCNNEL is a token classification model from Tanor. Use it when you need labels on individual words, such as names. It is set up for spacy.
Named Entity Linking model for Serbian language
All-time downloads
167
Public
Repo size
193 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other100 MB · 50%
At a glance
- Task
- Token Classification
- Library
- spacy
- Access
- Public
- Created
- Aug 16, 2024
- Updated
- Dec 23, 2024
- SHA
- 75e05389
Model card
From the Hugging Face model README
Named Entity Linking model for Serbian language
| Feature | Description |
|---|---|
| Name | sr_SRPCNNEL |
| Version | 1.0.0 |
| spaCy | >=3.5.2,<3.6.0 |
| Default Pipeline | tok2vec, tagger, ner, sentencizer, entity_linker |
| Components | tok2vec, tagger, ner, sentencizer, entity_linker |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | Milica Ikonić Nešić, Saša Petalinkar, Ranka Stanković, Miloš Utvić, Olivera Kitanović |
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 |
Accuracy
| Type | Score |
|---|---|
TAG_ACC | 96.49 |
ENTS_F | 93.38 |
ENTS_P | 93.35 |
ENTS_R | 93.40 |
TOK2VEC_LOSS | 205472.21 |
TAGGER_LOSS | 502844.65 |
NER_LOSS | 148170.50 |
- Task
- Token Classification
- Library
- spacy
- Languages
- sr
- Created
- Aug 16, 2024
- Updated
- Dec 23, 2024