Token Classification
Transformers
Safetensors
English
roberta
sequence-labeling
political-science
social-groups
parliamentary-debates
Instructions to use maxwlnd/roberta_group_mention_detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maxwlnd/roberta_group_mention_detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="maxwlnd/roberta_group_mention_detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("maxwlnd/roberta_group_mention_detector") model = AutoModelForTokenClassification.from_pretrained("maxwlnd/roberta_group_mention_detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
MaximilianWeiland commited on
Commit ·
a99d025
1
Parent(s): 9554ad4
update model card
Browse files
README.md
CHANGED
|
@@ -14,25 +14,6 @@ pipeline_tag: token-classification
|
|
| 14 |
library_name: transformers
|
| 15 |
metrics:
|
| 16 |
- seqeval
|
| 17 |
-
model-index:
|
| 18 |
-
- name: roberta_group_mention_detector
|
| 19 |
-
results:
|
| 20 |
-
- task:
|
| 21 |
-
type: token-classification
|
| 22 |
-
name: Sequence Labeling
|
| 23 |
-
dataset:
|
| 24 |
-
name: UK House of Commons Parliamentary Debates (2010–2019)
|
| 25 |
-
type: custom
|
| 26 |
-
metrics:
|
| 27 |
-
- type: seqeval f1
|
| 28 |
-
name: F1
|
| 29 |
-
value: 0.82
|
| 30 |
-
- type: seqeval precision
|
| 31 |
-
name: Precision
|
| 32 |
-
value: 0.80
|
| 33 |
-
- type: seqeval recall
|
| 34 |
-
name: Recall
|
| 35 |
-
value: 0.84
|
| 36 |
---
|
| 37 |
|
| 38 |
# RoBERTa Group Mention Detector
|
|
|
|
| 14 |
library_name: transformers
|
| 15 |
metrics:
|
| 16 |
- seqeval
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# RoBERTa Group Mention Detector
|