Text Classification
Transformers
Safetensors
English
bert
sentiment-analysis
finance
english
text-embeddings-inference
Instructions to use marcev/financebert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marcev/financebert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="marcev/financebert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("marcev/financebert") model = AutoModelForSequenceClassification.from_pretrained("marcev/financebert") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -58,17 +58,19 @@ FinanceBERT was evaluated on a held-out test set and achieved the following perf
|
|
| 58 |
|
| 59 |
Classification Report:
|
| 60 |
|
| 61 |
-
|
| 62 |
- precision: 0.84
|
| 63 |
- recall: 0.90
|
| 64 |
- f1_score: 0.87
|
| 65 |
- support: 29
|
| 66 |
-
|
|
|
|
| 67 |
- precision: 0.94
|
| 68 |
- recall: 0.94
|
| 69 |
- f1_score: 0.94
|
| 70 |
- support: 199
|
| 71 |
-
|
|
|
|
| 72 |
- precision: 0.90
|
| 73 |
- recall: 0.88
|
| 74 |
- f1_score: 0.89
|
|
|
|
| 58 |
|
| 59 |
Classification Report:
|
| 60 |
|
| 61 |
+
class_index: 0
|
| 62 |
- precision: 0.84
|
| 63 |
- recall: 0.90
|
| 64 |
- f1_score: 0.87
|
| 65 |
- support: 29
|
| 66 |
+
|
| 67 |
+
class_index: 1
|
| 68 |
- precision: 0.94
|
| 69 |
- recall: 0.94
|
| 70 |
- f1_score: 0.94
|
| 71 |
- support: 199
|
| 72 |
+
|
| 73 |
+
class_index: 2
|
| 74 |
- precision: 0.90
|
| 75 |
- recall: 0.88
|
| 76 |
- f1_score: 0.89
|