Instructions to use rasoultilburg/uce_scibert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rasoultilburg/uce_scibert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="rasoultilburg/uce_scibert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("rasoultilburg/uce_scibert") model = AutoModelForSequenceClassification.from_pretrained("rasoultilburg/uce_scibert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
language: en
license: gpl-3.0
widget:
- text: >-
In the beginning, Sonca seemed to have intensified rapidly since its
formation , however, soon the storm weakened back to a minimal tropical
storm because of dry air entering the LLCC that caused it to elongate and
weaken.
example_title: Causal Example 1
- text: >-
Our findings thus far show that the sanction reduced the number of chips
that participants allocated to themselves and that it only increased the
number of chips allocated to the yellow pool when there were two options.
example_title: Causal Example 2
- text: >-
In addition, several vent gas scrubbers had been out of service as well as
the steam boiler, intended to clean the pipes.
example_title: Non-causal Example 1
- text: >-
First, we can assess the correlation between beliefs and contributions,
which we expect to differ between types of players and which helps us to
check on the player type as elicited in the P-experiment.
example_title: Non-causal Example 2
Binary causal sentence classification:
- LABEL_0 = Non-causal
- LABEL_1 = Causal
See the project repository here: