Update Readme

Add inference example

README.md

@@ -13,7 +13,9 @@ metrics:
 - precision
 - recall
 - f1
-widget: []
+widget: 
+- text: "His name was Radu-Sebastian Amarie, and was building IJW trying to figure out how to properly extract entities from raw data. He's from Romania and he's eager to watch Dune 2."
+- example_title: "Random few NERD examples."
 pipeline_tag: token-classification
 license: cc-by-sa-4.0
 language:
@@ -80,7 +82,7 @@ The following are some manually-selected checkpoints that correspond to the abov
 
 ### Model Description
 - **Model Type:** SpanMarker
-**Encoder:** [muppet-roberta-large](https://huggingface.co/facebook/muppet-roberta-large)
+- **Encoder:** [muppet-roberta-large](https://huggingface.co/facebook/muppet-roberta-large)
 - **Maximum Sequence Length:** 256 tokens
 - **Maximum Entity Length:** 6 words
 - **Training Dataset:** [DFKI-SLT/few-nerd](https://huggingface.co/datasets/DFKI-SLT/few-nerd)