Instructions to use THemidli/applied-ner-stage4-bert-tiny-improved with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use THemidli/applied-ner-stage4-bert-tiny-improved with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="THemidli/applied-ner-stage4-bert-tiny-improved")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("THemidli/applied-ner-stage4-bert-tiny-improved") model = AutoModelForTokenClassification.from_pretrained("THemidli/applied-ner-stage4-bert-tiny-improved", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload artifacts/stage4_test_metrics.json with huggingface_hub
Browse files
artifacts/stage4_test_metrics.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall_precision": 0.42610652663165793,
|
| 3 |
+
"overall_recall": 0.5264133456904542,
|
| 4 |
+
"overall_f1": 0.4709784411276949,
|
| 5 |
+
"overall_accuracy": 0.8332408742926883,
|
| 6 |
+
"person_precision": 0.48659003831417624,
|
| 7 |
+
"person_recall": 0.6512820512820513,
|
| 8 |
+
"person_f1_score": 0.5570175438596492,
|
| 9 |
+
"person_support": 195.0,
|
| 10 |
+
"organization_precision": 0.21637426900584794,
|
| 11 |
+
"organization_recall": 0.25170068027210885,
|
| 12 |
+
"organization_f1_score": 0.23270440251572325,
|
| 13 |
+
"organization_support": 147.0,
|
| 14 |
+
"location_precision": 0.43575418994413406,
|
| 15 |
+
"location_recall": 0.5454545454545454,
|
| 16 |
+
"location_f1_score": 0.48447204968944096,
|
| 17 |
+
"location_support": 143.0,
|
| 18 |
+
"timedate_precision": 0.7853107344632768,
|
| 19 |
+
"timedate_recall": 0.8323353293413174,
|
| 20 |
+
"timedate_f1_score": 0.8081395348837209,
|
| 21 |
+
"timedate_support": 167.0,
|
| 22 |
+
"product_precision": 0.1678832116788321,
|
| 23 |
+
"product_recall": 0.18110236220472442,
|
| 24 |
+
"product_f1_score": 0.17424242424242423,
|
| 25 |
+
"product_support": 127.0,
|
| 26 |
+
"workofart_precision": 0.13636363636363635,
|
| 27 |
+
"workofart_recall": 0.24742268041237114,
|
| 28 |
+
"workofart_f1_score": 0.1758241758241758,
|
| 29 |
+
"workofart_support": 97.0,
|
| 30 |
+
"job_precision": 0.6638655462184874,
|
| 31 |
+
"job_recall": 0.797979797979798,
|
| 32 |
+
"job_f1_score": 0.724770642201835,
|
| 33 |
+
"job_support": 99.0,
|
| 34 |
+
"amount_precision": 0.5398230088495575,
|
| 35 |
+
"amount_recall": 0.5865384615384616,
|
| 36 |
+
"amount_f1_score": 0.5622119815668203,
|
| 37 |
+
"amount_support": 104.0
|
| 38 |
+
}
|