Instructions to use pvaluedotone/bigbird-flight with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pvaluedotone/bigbird-flight with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="pvaluedotone/bigbird-flight")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("pvaluedotone/bigbird-flight") model = AutoModelForSequenceClassification.from_pretrained("pvaluedotone/bigbird-flight", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -23,24 +23,15 @@ Big Bird Flight captures nuanced emotional gradients in text, offering richer se
|
|
| 23 |
- Sentiment class: 1 (extremely negative) to 10 (extremely positive)
|
| 24 |
|
| 25 |
## Validation metrics
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
f1_macro: 0.
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
precision_weighted: 0.277737992326741
|
| 39 |
-
|
| 40 |
-
recall_macro: 0.2594956658786446
|
| 41 |
-
|
| 42 |
-
recall_micro: 0.26653696498054474
|
| 43 |
-
|
| 44 |
-
recall_weighted: 0.26653696498054474
|
| 45 |
-
|
| 46 |
-
accuracy: 0.26653696498054474
|
|
|
|
| 23 |
- Sentiment class: 1 (extremely negative) to 10 (extremely positive)
|
| 24 |
|
| 25 |
## Validation metrics
|
| 26 |
+
The validation metrics reflects the inherent complexity in the fine granularity of the 10-point scale.
|
| 27 |
+
- loss: 1.7985
|
| 28 |
+
- f1_macro: 0.2275
|
| 29 |
+
- f1_micro: 0.2665
|
| 30 |
+
- f1_weighted: 0.2347
|
| 31 |
+
- precision_macro: 0.2676
|
| 32 |
+
- precision_micro: 0.2665
|
| 33 |
+
- precision_weighted: 0.2777
|
| 34 |
+
- recall_macro: 0.2595
|
| 35 |
+
- recall_micro: 0.2665
|
| 36 |
+
- recall_weighted: 0.2665
|
| 37 |
+
- accuracy: 0.2665
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|