Update app.py

app.py

@@ -1,15 +1,14 @@
 import gradio as gr
 import pandas as pd
 import torch
-import transformers
+from transformers import pipeline
 
-# Load the model pipeline
-model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-pipeline = transformers.pipeline(
+# Load the Zephyr-7B-Beta model pipeline
+pipe = pipeline(
     "text-generation",
-    model=model_id,
-    model_kwargs={"torch_dtype": torch.bfloat16},
-    device_map="auto",
+    model="HuggingFaceH4/zephyr-7b-beta",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
 )
 
 # Define the initial system message
@@ -55,17 +54,15 @@ def chat(user_input, messages):
         messages.append({"role": "user", "content": user_input})
 
         # Prepare the input for the model
-        input_text = messages.copy()  # Make a copy of messages
+        input_text = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
 
         # Generate a response using the pipeline
         try:
-            # Convert the messages to a format the model can understand
-            formatted_input = "\n".join([f"{msg['role']}: {msg['content']}" for msg in input_text])
-            response = pipeline(formatted_input, max_new_tokens=256)
+            response = pipe(input_text, max_new_tokens=256, return_full_text=False)
 
             # Extract the assistant's response
-            response_content = response[0]["generated_text"].strip()
-            
+            response_content = response[0]['generated_text'].strip()
+
             # Store assistant response in the chat history
             messages.append({"role": "assistant", "content": response_content})
 
@@ -77,7 +74,7 @@ def chat(user_input, messages):
 
 # Gradio Interface
 with gr.Blocks() as demo:
-    gr.Markdown("## Fashion Assistant Chatbot")
+    gr.Markdown("## FRIDAY")
 
     # Sidebar for user inputs
     with gr.Row():