Commit ·
fc9b3e3
1
Parent(s): c835591
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,12 +12,9 @@ datasets:
|
|
| 12 |
metrics:
|
| 13 |
- Accuracy
|
| 14 |
---
|
| 15 |
-
#
|
| 16 |
|
| 17 |
## Model description:
|
| 18 |
-
[Distilbert](https://arxiv.org/abs/1910.01108) is created with knowledge distillation during the pre-training phase which reduces the size of a BERT model by 40% while retaining 97% of its language understanding. It's smaller, faster than Bert and any other Bert-based model.
|
| 19 |
-
|
| 20 |
-
[Distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) finetuned on the emotion dataset using HuggingFace Trainer with below Hyperparameters
|
| 21 |
|
| 22 |
## Training Parameters:
|
| 23 |
```
|
|
|
|
| 12 |
metrics:
|
| 13 |
- Accuracy
|
| 14 |
---
|
| 15 |
+
# Bert-Base-Uncased-Go-Emotion
|
| 16 |
|
| 17 |
## Model description:
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Training Parameters:
|
| 20 |
```
|