Text Classification
Transformers
PyTorch
Safetensors
English
perceiver
financial-sentiment-analysis
sentiment-analysis
language-perceiver
Eval Results (legacy)
Instructions to use warwickai/fin-perceiver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use warwickai/fin-perceiver with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="warwickai/fin-perceiver")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("warwickai/fin-perceiver") model = AutoModelForSequenceClassification.from_pretrained("warwickai/fin-perceiver") - Notebooks
- Google Colab
- Kaggle
Tomás Fernandes commited on
Commit ·
1da4ac8
1
Parent(s): 42ecfee
Update the model card to include metrics
Browse files
README.md
CHANGED
|
@@ -13,3 +13,16 @@ widget:
|
|
| 13 |
|
| 14 |
# FINPerceiver
|
| 15 |
FINPerceiver is a fine-tuned Perceiver IO language model for financial sentiment analysis.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# FINPerceiver
|
| 15 |
FINPerceiver is a fine-tuned Perceiver IO language model for financial sentiment analysis.
|
| 16 |
+
The model achieves the following results on a 30% evaluation subset of the original dataset.
|
| 17 |
+
```
|
| 18 |
+
eval/accuracy 0.8453
|
| 19 |
+
eval/f1 0.7597
|
| 20 |
+
eval/loss 0.4785
|
| 21 |
+
eval/precision 0.7443
|
| 22 |
+
eval/recall 0.8024
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
More details on the training process of this model are available on the [GitHub repository](https://github.com/warwickai/fin-perceiver).
|
| 26 |
+
|
| 27 |
+
## Datasets
|
| 28 |
+
This model was trained on the Financial PhraseBank (>= 50% agreement)
|