Instructions to use teglad/DistilRoBERTaEmotionClassifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teglad/DistilRoBERTaEmotionClassifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="teglad/DistilRoBERTaEmotionClassifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("teglad/DistilRoBERTaEmotionClassifier") model = AutoModelForSequenceClassification.from_pretrained("teglad/DistilRoBERTaEmotionClassifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,3 +17,23 @@ This model was trained on the [Kaggle Emotions](https://www.kaggle.com/datasets/
|
|
| 17 |
+ Anger (3)
|
| 18 |
+ Fear (4)
|
| 19 |
+ Surprise (5)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
+ Anger (3)
|
| 18 |
+ Fear (4)
|
| 19 |
+ Surprise (5)
|
| 20 |
+
|
| 21 |
+
### Model Usage
|
| 22 |
+
|
| 23 |
+
```
|
| 24 |
+
import torch
|
| 25 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
| 26 |
+
|
| 27 |
+
# Load the model and tokenizer
|
| 28 |
+
model = AutoModelForSequenceClassification.from_pretrained("teglad/DistilRoBERTaEmotionClassifier")
|
| 29 |
+
tokenizer = AutoTokenizer.from_pretrained("teglad/DistilRoBERTaEmotionClassifier")
|
| 30 |
+
|
| 31 |
+
# Tokenize the input text, returning PyTorch tensors.
|
| 32 |
+
input_ids = tokenizer("Deep Learning models can be so difficult to understand, how do they even work?", return_tensors="pt")
|
| 33 |
+
|
| 34 |
+
# Pass the input_ids and attention_masks into the model
|
| 35 |
+
output = model(**input_ids)
|
| 36 |
+
|
| 37 |
+
# Get the position of the largest logit, this is the predicted class
|
| 38 |
+
prediction = torch.argmax(output.logits, dim=1).tolist()
|
| 39 |
+
```
|