Update README.md

README.md

@@ -21,6 +21,7 @@ The model can be used like this:
 
 ```python
 from sentence_transformers import CrossEncoder
+
 model = CrossEncoder('vectara/hallucination_evaluation_model')
 scores = model.predict([
     ["A man walks into a bar and buys a drink", "A bloke swigs alcohol at a pub"],
@@ -33,16 +34,18 @@ scores = model.predict([
 ])
 ```
 
-This returns a numpy array:
+This returns a numpy array representing a factual consistency score. A score < 0.5 indicates a likely hallucination):
 ```
 array([0.61051559, 0.00047493709, 0.99639291, 0.00021221573, 0.99599433, 0.0014127002, 0.002.8262993], dtype=float32)
 ```
 
 ## Usage with Transformers AutoModel
 You can use the model also directly with Transformers library (without SentenceTransformers library):
+
 ```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
+import numpy as np
 
 model = AutoModelForSequenceClassification.from_pretrained('vectara/hallucination_evaluation_model')
 tokenizer = AutoTokenizer.from_pretrained('vectara/hallucination_evaluation_model')
@@ -67,7 +70,7 @@ with torch.no_grad():
     scores = 1 / (1 + np.exp(-logits)).flatten()
 ```
 
-This returns a numpy array:
+This returns a numpy array representing a factual consistency score. A score < 0.5 indicates a likely hallucination):
 ```
 array([0.61051559, 0.00047493709, 0.99639291, 0.00021221573, 0.99599433, 0.0014127002, 0.002.8262993], dtype=float32)
 ```