Text Classification
Transformers
PyTorch
English
roberta
text
stance
Eval Results (legacy)
text-embeddings-inference
Instructions to use eevvgg/Stance-Tw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eevvgg/Stance-Tw with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="eevvgg/Stance-Tw")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("eevvgg/Stance-Tw") model = AutoModelForSequenceClassification.from_pretrained("eevvgg/Stance-Tw", device_map="auto") - Notebooks
- Google Colab
- Kaggle
up readme corpus size
Browse files
README.md
CHANGED
|
@@ -57,7 +57,7 @@ labels # ['attack', 'neutral', 'support', 'attack']
|
|
| 57 |
|
| 58 |
## Intended uses & limitations
|
| 59 |
|
| 60 |
-
|
| 61 |
|
| 62 |
|
| 63 |
## Training procedure
|
|
@@ -85,4 +85,6 @@ It achieves the following results on the evaluation set:
|
|
| 85 |
positive 0.759 0.775 0.767 191
|
| 86 |
negative 0.769 0.714 0.741 84
|
| 87 |
|
| 88 |
-
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
## Intended uses & limitations
|
| 59 |
|
| 60 |
+
Model suited for classification of stance in short text. Fine-tuned on a manually-annotated corpus of size 3.2k.
|
| 61 |
|
| 62 |
|
| 63 |
## Training procedure
|
|
|
|
| 85 |
positive 0.759 0.775 0.767 191
|
| 86 |
negative 0.769 0.714 0.741 84
|
| 87 |
|
| 88 |
+
|
| 89 |
+
## Citation
|
| 90 |
+
**BibTeX**: tba
|