Update README.md

README.md

@@ -1,47 +1,3 @@
-Hugging Face's logo
-Hugging Face
-Search models, datasets, users...
-Models
-Datasets
-Spaces
-Docs
-Solutions
-Pricing
-
-
-Hugging Face is way more fun with friends and colleagues! 🤗 Join an organization
-
-mcsabai
-/
-huBert-fine-tuned-hungarian-squadv1 Copied
-like
-1
-Question Answering
-PyTorch
-TensorFlow
-Transformers
-hu
-bert
-AutoTrain Compatible
-Model card
-Files and versions
-Community
-Settings
-huBert-fine-tuned-hungarian-squadv1
-/
-README.md
-mcsabai's picture
-mcsabai
-Update README.md
-4d72ef9
-about 2 months ago
-raw
-history
-blame
-edit
-delete
-Safe
-2.03 kB
 ---
 language: hu
 thumbnail: 
@@ -57,8 +13,26 @@ widget:
 
 ## MODEL DESCRIPTION
 
-huBERT base model (cased) fine-tuned on SQUADv2!! NEW
+huBERT base model (cased) fine-tuned on SQuAD v2 (NEW!!)
 - huBert model + Tokenizer: https://huggingface.co/SZTAKI-HLT/hubert-base-cc
-- This is a demo model. Date of publication: 2022.07.06.
+- Hungarian SQUAD v2 dataset: Machine Translated SQuAD dataset (Google Translate API)
+
+## Model in action
 
+- Fast usage with pipelines:
 
+```python
+from transformers import pipeline
+qa_pipeline = pipeline(
+    "question-answering",
+    model="mcsabai/huBert-fine-tuned-hungarian-squadv2",
+    tokenizer="mcsabai/huBert-fine-tuned-hungarian-squadv2"
+)
+predictions = qa_pipeline({
+    'context': "Anita vagyok és Budapesten élek már több mint 4 éve.",
+    'question': "Hol lakik Anita?"
+})
+print(predictions)
+# output:
+# {'score': 0.9892364144325256, 'start': 16, 'end': 26, 'answer': 'Budapesten'}
+```