Simon van Dyk
commited on
Commit
Β·
a3c51ba
1
Parent(s):
91ab207
Move images into plots/
Browse files- README.md +5 -5
- accuracy--nosible-dataset.png β plots/accuracy--nosible-dataset.png +0 -0
- accuracy--phrase-bank-dataset.png β plots/accuracy--phrase-bank-dataset.png +0 -0
- accuracy-vs-cost--nosible-dataset.png β plots/accuracy-vs-cost--nosible-dataset.png +0 -0
- accuracy-vs-cost--phrase-bank-dataset.png β plots/accuracy-vs-cost--phrase-bank-dataset.png +0 -0
README.md
CHANGED
|
@@ -49,11 +49,11 @@ Most existing financial sentiment models rely on fine-tuned variants of older BE
|
|
| 49 |
We computed the validation set accuracy based on a sample of 1,000 points from our validation set.
|
| 50 |
|
| 51 |
<p align="center">
|
| 52 |
-
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/accuracy--nosible-dataset.png"/>
|
| 53 |
<p>
|
| 54 |
|
| 55 |
<p align="center">
|
| 56 |
-
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/accuracy-vs-cost--nosible-dataset.png"/>
|
| 57 |
<p>
|
| 58 |
|
| 59 |
#### Financial PhraseBank Dataset
|
|
@@ -61,11 +61,11 @@ We computed the validation set accuracy based on a sample of 1,000 points from o
|
|
| 61 |
We computed the Financial PhraseBank accuracies on the entire dataset. The 86% for FinBERT was their reported number in their paper.
|
| 62 |
|
| 63 |
<p align="center">
|
| 64 |
-
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/accuracy--phrase-bank-dataset.png"/>
|
| 65 |
<p>
|
| 66 |
|
| 67 |
<p align="center">
|
| 68 |
-
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/accuracy-vs-cost--phrase-bank-dataset.png"/>
|
| 69 |
<p>
|
| 70 |
|
| 71 |
|
|
@@ -295,4 +295,4 @@ If you use this model, please cite it as follows:
|
|
| 295 |
journal = {Hugging Face Repository},
|
| 296 |
howpublished = {https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base}
|
| 297 |
}
|
| 298 |
-
```
|
|
|
|
| 49 |
We computed the validation set accuracy based on a sample of 1,000 points from our validation set.
|
| 50 |
|
| 51 |
<p align="center">
|
| 52 |
+
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/plots/accuracy--nosible-dataset.png"/>
|
| 53 |
<p>
|
| 54 |
|
| 55 |
<p align="center">
|
| 56 |
+
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/plots/accuracy-vs-cost--nosible-dataset.png"/>
|
| 57 |
<p>
|
| 58 |
|
| 59 |
#### Financial PhraseBank Dataset
|
|
|
|
| 61 |
We computed the Financial PhraseBank accuracies on the entire dataset. The 86% for FinBERT was their reported number in their paper.
|
| 62 |
|
| 63 |
<p align="center">
|
| 64 |
+
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/plots/accuracy--phrase-bank-dataset.png"/>
|
| 65 |
<p>
|
| 66 |
|
| 67 |
<p align="center">
|
| 68 |
+
<img src="https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base/resolve/main/plots/accuracy-vs-cost--phrase-bank-dataset.png"/>
|
| 69 |
<p>
|
| 70 |
|
| 71 |
|
|
|
|
| 295 |
journal = {Hugging Face Repository},
|
| 296 |
howpublished = {https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base}
|
| 297 |
}
|
| 298 |
+
```
|
accuracy--nosible-dataset.png β plots/accuracy--nosible-dataset.png
RENAMED
|
File without changes
|
accuracy--phrase-bank-dataset.png β plots/accuracy--phrase-bank-dataset.png
RENAMED
|
File without changes
|
accuracy-vs-cost--nosible-dataset.png β plots/accuracy-vs-cost--nosible-dataset.png
RENAMED
|
File without changes
|
accuracy-vs-cost--phrase-bank-dataset.png β plots/accuracy-vs-cost--phrase-bank-dataset.png
RENAMED
|
File without changes
|