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_train_metrics.json with huggingface_hub
Browse files
artifacts/stage4_train_metrics.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall_precision": 0.9539951573849879,
|
| 3 |
+
"overall_recall": 0.9708781362007168,
|
| 4 |
+
"overall_f1": 0.9623626068613301,
|
| 5 |
+
"overall_accuracy": 0.9948478767829058,
|
| 6 |
+
"person_precision": 0.9862857142857143,
|
| 7 |
+
"person_recall": 0.9953863898500577,
|
| 8 |
+
"person_f1_score": 0.9908151549942594,
|
| 9 |
+
"person_support": 867.0,
|
| 10 |
+
"organization_precision": 0.9662162162162162,
|
| 11 |
+
"organization_recall": 0.9711375212224108,
|
| 12 |
+
"organization_f1_score": 0.9686706181202371,
|
| 13 |
+
"organization_support": 589.0,
|
| 14 |
+
"location_precision": 0.9738562091503268,
|
| 15 |
+
"location_recall": 0.9834983498349835,
|
| 16 |
+
"location_f1_score": 0.9786535303776683,
|
| 17 |
+
"location_support": 606.0,
|
| 18 |
+
"timedate_precision": 0.978978978978979,
|
| 19 |
+
"timedate_recall": 0.9834087481146304,
|
| 20 |
+
"timedate_f1_score": 0.981188863807374,
|
| 21 |
+
"timedate_support": 663.0,
|
| 22 |
+
"product_precision": 0.9625984251968503,
|
| 23 |
+
"product_recall": 0.9607072691552063,
|
| 24 |
+
"product_f1_score": 0.9616519174041297,
|
| 25 |
+
"product_support": 509.0,
|
| 26 |
+
"workofart_precision": 0.9707207207207207,
|
| 27 |
+
"workofart_recall": 0.9729119638826185,
|
| 28 |
+
"workofart_f1_score": 0.971815107102593,
|
| 29 |
+
"workofart_support": 443.0,
|
| 30 |
+
"job_precision": 0.7661691542288557,
|
| 31 |
+
"job_recall": 0.875,
|
| 32 |
+
"job_f1_score": 0.8169761273209549,
|
| 33 |
+
"job_support": 352.0,
|
| 34 |
+
"amount_precision": 0.9527027027027027,
|
| 35 |
+
"amount_recall": 0.9724137931034482,
|
| 36 |
+
"amount_f1_score": 0.9624573378839592,
|
| 37 |
+
"amount_support": 435.0
|
| 38 |
+
}
|