Views
No views yet
correlationsbase_reference.csv (708 samples)| Metric | Value |
|---|---|
| Loss | 0.1960 |
| Subset Accuracy | 0.0000 |
| F1 Score | 0.0000 |
| F1 Micro | 0.0000 |
| F1 Macro | 0.0000 |
| Hamming Score | 0.9799 |
| Precision | 0.0000 |
| Recall | 0.0000 |
1from transformers import AutoTokenizer, AutoModelForSequenceClassification
2import torch
3
4tokenizer = AutoTokenizer.from_pretrained("Bencode92/tradepulse-finbert-correlations")
5model = AutoModelForSequenceClassification.from_pretrained("Bencode92/tradepulse-finbert-correlations")
6
7# Example prediction
8text = "Apple reported strong quarterly earnings beating expectations"
9inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
10outputs = model(**inputs)
11# Multi-label: apply sigmoid and threshold
12predictions = torch.sigmoid(outputs.logits).squeeze() > 0.5