Simon van Dyk commited on
Commit
a3c51ba
Β·
1 Parent(s): 91ab207

Move images into plots/

Browse files
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