Updated to include sts conventional training

app.py

@@ -6,9 +6,11 @@ import plotly.express as px
 import pandas as pd
 
 tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
+tokenizer1 = AutoTokenizer.from_pretrained("albert-base-v2")
+tokenizer2 = AutoTokenizer.from_pretrained("microsoft/deberta-v3-xsmall")
 loraModel = AutoPeftModelForSequenceClassification.from_pretrained("Intradiction/text_classification_WithLORA")
+#loraModel1 = AutoPeftModelForSequenceClassification.from_pretrained("rajevan123/STS-Lora-Fine-Tuning-Capstone-Deberta-small")
 
-tokenizer1 = AutoTokenizer.from_pretrained("albert-base-v2")
 
 # Handle calls to DistilBERT------------------------------------------
 distilBERTUntrained_pipe = pipeline("sentiment-analysis", model="bert-base-uncased")
@@ -44,14 +46,15 @@ def AlbertUntrained_fn(text1, text2):
 
 # Handle calls to Deberta--------------------------------------------
 DebertaUntrained_pipe = pipeline("text-classification", model="microsoft/deberta-v3-xsmall")
-#DebertanoLORA_pipe = pipeline()
-#DebertawithLORA_pipe = pipeline()
+DebertanoLORA_pipe = pipeline(model="rajevan123/STS-Conventional-Fine-Tuning")
+#DebertawithLORA_pipe = pipeline("text-classification", model=loraModel1, tokenizer=tokenizer2)
 
 #STS models
 def DebertanoLORA_fn(text1, text2):
-    return ("working3")
+    return DebertanoLORA_pipe({'text': text1, 'text_pair': text2})
 
 def DebertawithLORA_fn(text1, text2):
+    #return DebertawithLORA_pipe({'text': text1, 'text_pair': text2})
     return ("working2")
 
 def DebertaUntrained_fn(text1, text2):