Update app.py

app.py

@@ -53,42 +53,20 @@ if __name__ == "__main__":
     chatbot.run()
 """
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import pipeline
 
-# Load the base model
-base_model_name = "Preetham04/sentiment-analysis"
-tokenizer = AutoTokenizer.from_pretrained(base_model_name)
-model = AutoModelForSequenceClassification.from_pretrained(base_model_name)
-
-# Load the adapter configuration and model files
-adapter_path = "model.safetensors"  # Typically, this is a single path
-
-# Load the adapter into the model
-adapter_name = "custom_adapter"  # Define your adapter name
-model.load_adapter(adapter_path, load_as=adapter_name)
+pipeline = pipeline(task="text-classification", model="Preetham04/sentiment-analysis")
 
-# Activate the adapter
-model.set_active_adapters(adapter_name)
+def predict(input_img):
+    predictions = pipeline(input_img)
+    return input_img, {p["label"]: p["score"] for p in predictions} 
 
-import streamlit as st
+gradio_app = gr.Interface(
+    predict,
+    inputs="textbox",
+    outputs="text",
+    title="Sentiment- good or bad?",
+)
 
-st.title("🤖 Chatbot with Adapter-Enhanced Model")
-st.write("Interact with your custom adapter-enhanced model. Type a message and get responses!")
-
-# Initialize or retrieve the chat history
-if 'history' not in st.session_state:
-    st.session_state['history'] = []
-
-# Initialize Gradio
-chatbot = gr.Interface(fn=message_handler, inputs="text", outputs="text", live=True)
-
-# Define responses for user messages
-def message_handler(user_input):
-    inputs = tokenizer(user_input, return_tensors="pt")
-    outputs = model(**inputs)
-    response = tokenizer.decode(outputs.logits.argmax(dim=-1))
-    return response
-
-# Run Gradio
 if __name__ == "__main__":
-    chatbot.launch()
+    gradio_app.launch()