Update README.md
Browse files
README.md
CHANGED
|
@@ -44,19 +44,10 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 44 |
3. The Training data can be downloaded from [here](https://docs.google.com/spreadsheets/d/1BVDardwVs04ZWmc5_Eg62Lyr_w_OuXysQwhne8ErkoA/edit?usp=sharing)
|
| 45 |
|
| 46 |
## Usage and Inference
|
| 47 |
-
|
| 48 |
-
To use this model for inference, first install the SetFit library:
|
| 49 |
-
|
| 50 |
-
```bash
|
| 51 |
-
pip install -U dataset
|
| 52 |
-
python -m pip install setfit==0.5.0
|
| 53 |
-
pip install -U sentence_transformers
|
| 54 |
-
```
|
| 55 |
-
|
| 56 |
For a global overview of the pipeline used for inference please refer to this [colab notebook](https://colab.research.google.com/drive/1GgEGrhQZfA1pbcB9Zl0VtV7L5wXdh6vj?usp=sharing)
|
| 57 |
|
| 58 |
## Model Performance
|
| 59 |
-
The
|
| 60 |
* Accuracy: 0.68
|
| 61 |
* Balanced_Accuracy: 0.45
|
| 62 |
* MCC: 0.37
|
|
|
|
| 44 |
3. The Training data can be downloaded from [here](https://docs.google.com/spreadsheets/d/1BVDardwVs04ZWmc5_Eg62Lyr_w_OuXysQwhne8ErkoA/edit?usp=sharing)
|
| 45 |
|
| 46 |
## Usage and Inference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
For a global overview of the pipeline used for inference please refer to this [colab notebook](https://colab.research.google.com/drive/1GgEGrhQZfA1pbcB9Zl0VtV7L5wXdh6vj?usp=sharing)
|
| 48 |
|
| 49 |
## Model Performance
|
| 50 |
+
The performances of the model on our internal test set are:
|
| 51 |
* Accuracy: 0.68
|
| 52 |
* Balanced_Accuracy: 0.45
|
| 53 |
* MCC: 0.37
|