Update app.py

app.py

@@ -1,61 +1,63 @@
 import gradio as gr
 
 
-# gr.load("models/microsoft/Phi-3.5-mini-instruct", max_new_tokens=50).launch(share=True)
 
+model = gr.load("models/microsoft/Phi-3.5-mini-instruct").
 
-# gradio_app = gr.Interface(
-#     fn=model,
-#     inputs="text",
-#     outputs="text",
-#     title="Advertisment companion",
-# )
+
+gradio_app = gr.Interface(
+    fn=model,
+    inputs="text",
+    outputs="text",
+    max_batch_size=50,
+    title="Advertisment companion",
+)
 
 
 
-# gradio_app
+gradio_app.launch(share=True)
 
 
 
 
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+# from transformers import AutoTokenizer, AutoModelForCausalLM
+# import torch
 
-# Load the model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-mini-instruct", trust_remote_code=True)
+# # Load the model and tokenizer
+# tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct", trust_remote_code=True)
+# model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-mini-instruct", trust_remote_code=True)
 
-# Define the role prompt for advertisement assistance
-# role_prompt = "You are an advertisement assistant. Respond professionally and helpfully to advertising-related questions.\n\n"
+# # Define the role prompt for advertisement assistance
+# # role_prompt = "You are an advertisement assistant. Respond professionally and helpfully to advertising-related questions.\n\n"
 
-# Function to generate responses
-def generate_response(user_input):
-    # Prepend role information to user input
-    # input_text =  user_input
+# # Function to generate responses
+# def generate_response(user_input):
+#     # Prepend role information to user input
+#     # input_text =  user_input
     
-    # Tokenize and generate response
-    inputs = tokenizer(user_input, return_tensors="pt")
-    outputs = model.generate(
-        **inputs, 
-        max_new_tokens=100,   # Increase this if you want longer responses
-                 # Nucleus sampling to control randomness
-    )
+#     # Tokenize and generate response
+#     inputs = tokenizer(user_input, return_tensors="pt")
+#     outputs = model.generate(
+#         **inputs, 
+#         max_new_tokens=100,   # Increase this if you want longer responses
+#                  # Nucleus sampling to control randomness
+#     )
     
-    # Decode and return the response
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+#     # Decode and return the response
+#     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+#     return response
 
-# Set up Gradio interface
-interface = gr.Interface(
-    fn=generate_response,
-    inputs="text",
-    outputs="text",
-    title="Advertisement Assistant Chatbot",
-    description="Ask me anything related to advertising. I'm here to help!"
-)
+# # Set up Gradio interface
+# interface = gr.Interface(
+#     fn=generate_response,
+#     inputs="text",
+#     outputs="text",
+#     title="Advertisement Assistant Chatbot",
+#     description="Ask me anything related to advertising. I'm here to help!"
+# )
 
-# Launch the Gradio app with sharing enabled
-interface.launch(share=True)
+# # Launch the Gradio app with sharing enabled
+# interface.launch(share=True)
 
 
 # import gradio as gr