Instructions to use GateNLP/stance-bertweet-target-oblivious with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GateNLP/stance-bertweet-target-oblivious with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GateNLP/stance-bertweet-target-oblivious")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("GateNLP/stance-bertweet-target-oblivious") model = AutoModelForSequenceClassification.from_pretrained("GateNLP/stance-bertweet-target-oblivious", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: transformers
datasets:
- strombergnlp/rumoureval_2019
language:
- en
base_model:
- vinai/bertweet-base
Model Card for Model ID
One of a pair of models intended to classify the stance of a "reply" post with respect to the post to which it is replying. This is a target oblivious model, i.e. it considers only the reply itself, not the original target post. GateNLP/stance-bertweet-target-aware is the complementary "target-aware" model, the two models are used in combination in the GATE Cloud English Stance Classifier.
For background, see this paper.