Text Classification
Transformers
Safetensors
Korean
electra
korean
multi-label-classification
kcelectra
fine-tuned
Eval Results (legacy)
Instructions to use Kaaeun/Labeling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kaaeun/Labeling with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Kaaeun/Labeling")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Kaaeun/Labeling") model = AutoModelForSequenceClassification.from_pretrained("Kaaeun/Labeling", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -63,17 +63,17 @@ model-index:
|
|
| 63 |
|
| 64 |
| Metric | Value |
|
| 65 |
|--------|--------|
|
| 66 |
-
| Micro-F1 | 0.
|
| 67 |
-
| Macro-F1 | 0.
|
| 68 |
| Subset Accuracy | 0.516 |
|
| 69 |
|
| 70 |
F1-score:
|
| 71 |
| Emotion | F1-score |
|
| 72 |
|----------|-----------|
|
| 73 |
-
| Dislike | 0.
|
| 74 |
-
| Sympathy | 0.
|
| 75 |
-
| Sadness | 0.
|
| 76 |
-
| Surprised | 0.
|
| 77 |
-
| Angry | 0.
|
| 78 |
|
| 79 |
---
|
|
|
|
| 63 |
|
| 64 |
| Metric | Value |
|
| 65 |
|--------|--------|
|
| 66 |
+
| Micro-F1 | 0.896 |
|
| 67 |
+
| Macro-F1 | 0.892 |
|
| 68 |
| Subset Accuracy | 0.516 |
|
| 69 |
|
| 70 |
F1-score:
|
| 71 |
| Emotion | F1-score |
|
| 72 |
|----------|-----------|
|
| 73 |
+
| Dislike | 0.88 |
|
| 74 |
+
| Sympathy | 0.90 |
|
| 75 |
+
| Sadness | 0.684|
|
| 76 |
+
| Surprised | 0.92 |
|
| 77 |
+
| Angry | 0.93 |
|
| 78 |
|
| 79 |
---
|