Instructions to use owen198/esgbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use owen198/esgbert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="owen198/esgbert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("owen198/esgbert") model = AutoModelForSequenceClassification.from_pretrained("owen198/esgbert") - Notebooks
- Google Colab
- Kaggle
This is an example of machine reading articles with BERT. The main function is to determine whether the input sentence is related to Carbon Emissions (LABLE_1), Community Relations (LABEL_0), or Random Sentences (LABEL_2). The following are example sentence patterns for the two classes:
Community Relations (LABEL_0)
- We strive to source products in a responsible manner while working with suppliers to improve their social and environmental practices.
- Ethical sourcing has been a key area of focus for the Wesfarmers Group for almost a decade.
- Our businesses directly source products from nearly 28,000 suppliers in more than 40 countries. Some of the major locations we source from include Australia, Bangladesh, China, India and Indonesia.
Carbon Emissions (LABLE_1)
- The reduction of CO2 emissions was 19.3 percent in Japan from the level of the fiscal year ended March 31, 2015.
- The emissions were 6.6 percent increased overseas.
- As a result, the emissions were 1.2% increased globally.
Random Sentences (LABEL_2)
- I do wish there were new interviews with Anthony Hopkins and Ann Margret though.
- Alas, the answer is telegraphed too soon so whatever suspense director Richard Attenborough is trying to muster is drained away.
- The dummy is seemingly real at all times, especially when it is killing some hapless victim.
- Downloads last month
- 7