Update README.md

README.md

@@ -40,25 +40,27 @@ should probably proofread and complete it, then remove this comment. -->
 # distilroberta-base-ner-wikiann
 
 This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the wikiann dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3156
-- Precision: 0.8332
-- Recall: 0.8424
-- F1: 0.8378
-- Accuracy: 0.9193
 
-## Model description
 
-More information needed
+eval F1-Score: **83,78** (CoNLL-03)   
+test F1-Score: **83,76** (CoNLL-03)  
+
+
+## Model Usage
 
-## Intended uses & limitations
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+from transformers import pipeline
 
-More information needed
+tokenizer = AutoTokenizer.from_pretrained("philschmid/distilroberta-base-ner-wikiann")
+model = AutoModelForTokenClassification.from_pretrained("philschmid/distilroberta-base-ner-wikiann")
 
-## Training and evaluation data
+nlp = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
+example = "My name is Philipp and live in Germany"
 
-More information needed
+nlp(example)
 
+```
 ## Training procedure
 
 ### Training hyperparameters
@@ -75,6 +77,19 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+It achieves the following results on the evaluation set:
+- Loss: 0.3156
+- Precision: 0.8332
+- Recall: 0.8424
+- F1: 0.8378
+- Accuracy: 0.9193
+
+It achieves the following results on the test set:
+- Loss: 0.3023
+- Precision: 0.8301
+- Recall: 0.8452
+- F1: 0.8376
+- Accuracy: 0.92
 
 
 ### Framework versions