Update SA LORA pipe with newly trained model

Now uses bert-base-uncased trained on 3k samples, better scores than previous

app.py

@@ -1,16 +1,16 @@
 import gradio as gr
-from transformers import pipeline, AutoTokenizer, AutoModel
+from transformers import pipeline, AutoTokenizer, AutoModel, BertForSequenceClassification
 from peft.auto import AutoPeftModelForSequenceClassification
 from tensorboard.backend.event_processing import event_accumulator
 from peft import PeftModel
 import plotly.express as px
 import pandas as pd
 
-tokenizer1 = AutoTokenizer.from_pretrained("albert-base-v2")
 
-loraModel = AutoPeftModelForSequenceClassification.from_pretrained("Intradiction/text_classification_WithLORA")
-tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
 
+loraModel = AutoPeftModelForSequenceClassification.from_pretrained("Intradiction/text_classification_WithLORA")
+#tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
+tokenizer1 = AutoTokenizer.from_pretrained("albert-base-v2")
 tokenizer2 = AutoTokenizer.from_pretrained("microsoft/deberta-v3-xsmall")
 # base_model = AutoModel.from_pretrained("microsoft/deberta-v3-xsmall")
 # peft_model_id = "rajevan123/STS-Lora-Fine-Tuning-Capstone-Deberta-small"
@@ -19,16 +19,22 @@ tokenizer2 = AutoTokenizer.from_pretrained("microsoft/deberta-v3-xsmall")
 
 
 # Handle calls to DistilBERT------------------------------------------
+base_model = BertForSequenceClassification.from_pretrained("bert-base-uncased")
+peft_model_id = "Intradiction/BERT-SA-LORA"
+model = PeftModel.from_pretrained(model=base_model, model_id=peft_model_id)
+sa_merged_model = model.merge_and_unload()
+bbu_tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
+
 distilBERTUntrained_pipe = pipeline("sentiment-analysis", model="bert-base-uncased")
 distilBERTnoLORA_pipe = pipeline(model="Intradiction/text_classification_NoLORA")
-distilBERTwithLORA_pipe = pipeline("sentiment-analysis", model=loraModel, tokenizer=tokenizer)
+SentimentAnalysis_LORA_pipe = pipeline("sentiment-analysis", model=sa_merged_model, tokenizer=bbu_tokenizer)
 
 #text class models 
 def distilBERTnoLORA_fn(text):
     return distilBERTnoLORA_pipe(text)
 
 def distilBERTwithLORA_fn(text):
-    return distilBERTwithLORA_pipe(text)
+    return SentimentAnalysis_LORA_pipe(text)
 
 def distilBERTUntrained_fn(text):
     return distilBERTUntrained_pipe(text)
@@ -425,7 +431,7 @@ with gr.Blocks(
          btnSTSStats.click(fn=displayMetricStatsTextSTSNoLora, outputs=STSNoLoraStats)
          btnSTSStats.click(fn=displayMetricStatsTextSTSLora, outputs=STSLoraStats)
 
-    with gr.Tab("More informatioen"):
+    with gr.Tab("More information"):
         gr.Markdown("stuff to add")