Update README.md

README.md

@@ -5,7 +5,7 @@ pipeline_tag: text-classification
 ---
 # PaloBERT for Sentiment Analysis
 
-A greek [RoBERTa](https://arxiv.org/abs/1907.11692) based model ([PaloBERT](https://huggingface.co/pchatz/greeksocialbert-base-greek-social-media)) fine-tuned for sentiment analysis.
+A greek [RoBERTa](https://arxiv.org/abs/1907.11692) based model ([PaloBERT](https://huggingface.co/pchatz/palobert-base-greek-social-media)) fine-tuned for sentiment analysis.
 
 ## Training data
 
@@ -13,7 +13,6 @@ The model is pre-trained on a corpus of 458,293 documents collected from greek s
 
 The corpus as well as the annotated dataset have been provided by [Palo LTD](http://www.paloservices.com/).
 
-
 ## Requirements
 
 ```
@@ -41,6 +40,35 @@ def preprocess(text, default_replace=""):
   return text
 ```
 
+## Load Model
+
+```python
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained("pchatz/palobert-base-greek-social-media") #load PaloBERT pre-trained model
+language_model = AutoModel.from_pretrained("pchatz/palobert-base-greek-social-media")
+```
+Refer to [GitHub](https://github.com/Paulinechatz/sentiment-analysis-greek-social-media/blob/main/code/train_classifier_roberta_arch.py#L100) code for details on ModelClass architecture
+```python
+model = TheModelClass(*args, **kwargs) #load fine-tuned model as SentimentClassifier_v2
+model.load_state_dict(torch.load(PATH))
+model.eval()
+```
+You can use this sentiment analysis model directly on raw text:
+```python
+#Example
+class_names={0: 'neutral', 1:'positive', 2:'negative'}
+text='οι εξετασεις ηταν πολυ καλες' 
+encoding=tokenizer(text,return_tensors='pt')
+
+input_ids = encoding['input_ids']
+attention_mask = encoding['attention_mask']
+
+output = model(input_ids, attention_mask)
+_,prediction = torch.max(output, dim=1)
+
+print(f'sentiment  : {class_names[prediction.item()]}') #positive
+```
 
 ## Evaluation