Downloads · 30 days
12
60% of all-time downloads
ru_custom_new_model
Dessan/ru_custom_new_model
ru_custom_new_model is a token classification model from Dessan. Use it when you need labels on individual words, such as names. It is set up for spacy.
Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attributeruler, lemmatizer.
All-time downloads
20
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other621 MB · 52%
At a glance
- Task
- Token Classification
- Library
- spacy
- Access
- Public
- Created
- Apr 3, 2024
- Updated
- Apr 3, 2024
- SHA
- 04c0e480
Try a prompt
Model card
From the Hugging Face model README
Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.
| Feature | Description |
|---|---|
| Name | ru_custom_new_model |
| Version | 0.0.1 |
| spaCy | >=3.7.0,<3.8.0 |
| Default Pipeline | tok2vec, morphologizer, parser, attribute_ruler, lemmatizer, ner |
| Components | tok2vec, morphologizer, parser, senter, attribute_ruler, lemmatizer, ner |
| Vectors | 500002 keys, 500002 unique vectors (300 dimensions) |
| Sources | n/a |
| License | MIT |
| Author | Dessan |
Label Scheme
<details> <summary>View label scheme (905 labels for 3 components)</summary>| Component | Labels |
|---|---|
morphologizer | Case=Nom|Degree=Pos|Number=Plur|POS=ADJ, Animacy=Anim|Case=Nom|Gender=Masc|Number=Plur|POS=NOUN, `Aspect=Perf|Mood=Ind|Number=Plur|POS=VERB|Tense=Pa> |
Accuracy
| Type | Score |
|---|---|
TOKEN_ACC | 99.68 |
TOKEN_P | 97.28 |
TOKEN_R | 98.31 |
TOKEN_F | 97.79 |
POS_ACC | 98.93 |
MORPH_ACC | 97.49 |
MORPH_MICRO_P | 98.97 |
MORPH_MICRO_R | 98.30 |
MORPH_MICRO_F | 98.64 |
SENTS_P | 99.87 |
SENTS_R | 99.85 |
SENTS_F | 99.86 |
DEP_UAS | 96.22 |
DEP_LAS | 95.12 |
TAG_ACC | 98.93 |
LEMMA_ACC | 0.00 |
ENTS_P | 95.24 |
ENTS_R | 95.35 |
ENTS_F | 95.30 |
- Task
- Token Classification
- Library
- spacy
- Languages
- ru
- Created
- Apr 3, 2024
- Updated
- Apr 3, 2024