Text Classification
Transformers
PyTorch
bert
CAP
politics
issues
agenda
multilingual
science
comparative agendas project
text-embeddings-inference
Instructions to use z-dickson/CAP_multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use z-dickson/CAP_multilingual with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="z-dickson/CAP_multilingual")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("z-dickson/CAP_multilingual") model = AutoModelForSequenceClassification.from_pretrained("z-dickson/CAP_multilingual", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,12 @@
|
|
| 1 |
---
|
| 2 |
license: afl-3.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
Multilingual Bert base (multilingual uncased) model trained to predict [CAP issue codes](https://www.comparativeagendas.net/pages/master-codebook).
|
|
@@ -19,14 +26,7 @@ Model training on 120,000 assorted political documents -- mostly from the [Compa
|
|
| 19 |
- UK
|
| 20 |
- Austria
|
| 21 |
- Ireland
|
| 22 |
-
|
| 23 |
-
- text: >-
|
| 24 |
-
To ask the Secretary of State for Energy and Climate Change what estimate he has made of the proportion of carbon dioxide emissions arising in the UK attributable to burning
|
| 25 |
-
example_title: 'English (UK House of Commons Question)'
|
| 26 |
-
- text: >-
|
| 27 |
-
To ask the Scottish Government what action it is taking to ensure that women who are prescribed sodium valproate are (a) adequately counselled\xa0regarding the risks of taking the drug while pregnant and (b) supported to plan their pregnancies in order to minimise the risk of foetal abnormalities.“
|
| 28 |
-
example_title: 'English (Scottish Parliamentary Question)'
|
| 29 |
-
---
|
| 30 |
|
| 31 |
# LABELS USED IN TRAINING
|
| 32 |
|
|
|
|
| 1 |
---
|
| 2 |
license: afl-3.0
|
| 3 |
+
widget:
|
| 4 |
+
- text: >-
|
| 5 |
+
To ask the Secretary of State for Energy and Climate Change what estimate he has made of the proportion of carbon dioxide emissions arising in the UK attributable to burning
|
| 6 |
+
example_title: 'English (UK House of Commons Question)'
|
| 7 |
+
- text: >-
|
| 8 |
+
To ask the Scottish Government what action it is taking to ensure that women who are prescribed sodium valproate are (a) adequately counselled\xa0regarding the risks of taking the drug while pregnant and (b) supported to plan their pregnancies in order to minimise the risk of foetal abnormalities.“
|
| 9 |
+
example_title: 'English (Scottish Parliamentary Question)'
|
| 10 |
---
|
| 11 |
|
| 12 |
Multilingual Bert base (multilingual uncased) model trained to predict [CAP issue codes](https://www.comparativeagendas.net/pages/master-codebook).
|
|
|
|
| 26 |
- UK
|
| 27 |
- Austria
|
| 28 |
- Ireland
|
| 29 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
# LABELS USED IN TRAINING
|
| 32 |
|