Instructions to use puzzz21/sci-sentiment-classify with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use puzzz21/sci-sentiment-classify with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="puzzz21/sci-sentiment-classify")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("puzzz21/sci-sentiment-classify") model = AutoModelForSequenceClassification.from_pretrained("puzzz21/sci-sentiment-classify") - Notebooks
- Google Colab
- Kaggle
Update Readme
Browse files
README.md
CHANGED
|
@@ -23,4 +23,8 @@ This model outputs following classnames according to the sentiment:
|
|
| 23 |
</ul>
|
| 24 |
</br>
|
| 25 |
</br>
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
</ul>
|
| 24 |
</br>
|
| 25 |
</br>
|
| 26 |
+
The model achieved F1 score of 0.72 and an accuracy score of 0.73, with the manually annoted dataset: [Link to the dataset](https://huggingface.co/datasets/puzzz21/sci-sentiment-annotated-dataset).
|
| 27 |
+
</br>
|
| 28 |
+
</br>
|
| 29 |
+
For finetuning, the publicly available dataset on context identification from Angrosh et al. https://dl.acm.org/doi/10.1145/1816123.1816168 is used.
|
| 30 |
+
|