Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ tags:
|
|
13 |
- Deberta-v2
|
14 |
---
|
15 |
|
16 |
-
# Deberta for Financial Sentiment
|
17 |
|
18 |
I use a Deberta model trained on over 1 million reviews from Amazon's multi-reviews dataset and finetune it on 4 finance datasets that are categorized with Sentiment labels.
|
19 |
The datasets I use are
|
@@ -41,7 +41,7 @@ def get_sentiment(sentences):
|
|
41 |
bert_dict['pos'] = round(prob[2].item(), 3)
|
42 |
print (bert_dict)
|
43 |
|
44 |
-
MODEL_NAME = 'RashidNLP/
|
45 |
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
46 |
|
47 |
bert_model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, num_labels = 3).to(device)
|
|
|
13 |
- Deberta-v2
|
14 |
---
|
15 |
|
16 |
+
# Deberta for Financial Sentiment Classification
|
17 |
|
18 |
I use a Deberta model trained on over 1 million reviews from Amazon's multi-reviews dataset and finetune it on 4 finance datasets that are categorized with Sentiment labels.
|
19 |
The datasets I use are
|
|
|
41 |
bert_dict['pos'] = round(prob[2].item(), 3)
|
42 |
print (bert_dict)
|
43 |
|
44 |
+
MODEL_NAME = 'RashidNLP/Finance-Sentiment-Classification'
|
45 |
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
46 |
|
47 |
bert_model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, num_labels = 3).to(device)
|