Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags: []
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
This model was developed by finetuning the [DistilBERT Nepali Model](https://huggingface.co/Sakonii/distilbert-base-nepali).
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
## Model Details
|
| 14 |
+
|
| 15 |
+
### Model Description
|
| 16 |
+
|
| 17 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 18 |
+
|
| 19 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 20 |
+
|
| 21 |
+
- **Developed by:** Jeevan
|
| 22 |
+
- **Model type:** DistilBERT Nepali
|
| 23 |
+
- **Language(s) (NLP):** Nepali
|
| 24 |
+
- **Finetuned from model [optional]:** [DistilBERT Nepali Model](https://huggingface.co/Sakonii/distilbert-base-nepali)
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
## Training Details
|
| 29 |
+
|
| 30 |
+
### Training Data
|
| 31 |
+
|
| 32 |
+
The dataset used for finetuning this model can be found at [NepCOV19Tweets](https://www.kaggle.com/datasets/mathew11111/nepcov19tweets) which contains Nepali tweets related to COVID-19.
|
| 33 |
+
|
| 34 |
+
### Training HyperParameters
|
| 35 |
+
|
| 36 |
+
* Batch size: 16
|
| 37 |
+
* Learning Rate: 0.0001
|
| 38 |
+
* Optimizer: AdamW
|
| 39 |
+
* Epochs: 10
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
## Evaluation
|
| 44 |
+
|
| 45 |
+
* Training loss: 0.2414
|
| 46 |
+
* Precision: 0.73
|
| 47 |
+
* Recall: 0.73
|
| 48 |
+
* F1 Score (Weighted): 0.73
|
| 49 |
+
|
| 50 |
+
## Labels
|
| 51 |
+
|
| 52 |
+
* Neutral: 0
|
| 53 |
+
* Positive: 1
|
| 54 |
+
* Negative: 2
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
## USAGE
|
| 58 |
+
|
| 59 |
+
```python
|
| 60 |
+
from transformers import pipeline
|
| 61 |
+
|
| 62 |
+
pipe = pipeline("text-classification", model="xap/Sentiment_Analysis_NepaliCovidTweets")
|
| 63 |
+
pipe("अमेरिकामा कोभिड बाट एकै दिन चार हजारभन्दा बढीको मृत्यु")
|
| 64 |
+
```
|