Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
This is a distilbert-base-multilingual-cased-Model fine-tuned with a NER objective to tag tokens based on whether they belong to a code block or natural language text.
|
| 6 |
+
The dataset of 78210 examples was generated by randomly combining code and text blocks from other permissively-licensed datasets, with some examples containing only code and some only regular text.
|
| 7 |
+
|
| 8 |
+
The model achieves the following stats on the validation set:
|
| 9 |
+
|
| 10 |
+
| Metric | Value |
|
| 11 |
+
|--------------|-----------|
|
| 12 |
+
| Loss | 0.0788 |
|
| 13 |
+
| F1 Score | 0.8619 |
|
| 14 |
+
| Precision | 0.8362 |
|
| 15 |
+
| Recall | 0.8893 |
|
| 16 |
+
| Accuracy | 0.9792 |
|