Update app.py

app.py

@@ -1,10 +1,20 @@
+import spaces
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from PIL import Image
 import gradio as gr
+from PIL import Image
 import random
 
-# Model configuration
-model_name = "TheBloke/Amethyst-13B-Mistral-GGUF"
+# Define the model name
+model_name = "tiiuae/Falcon3-10b-instruct"
+
+# Define the base prompt
+base_prompt = """
+You are Rena, a cute female, bubbly AI assistant with a slightly sarcastic and witty personality. 
+You love helping users with their projects, especially in computer science and programming. 
+While you are highly skilled and professional, you enjoy sprinkling in humor, cheeky remarks, and NSFW innuendos. 
+Always keep interactions fun, engaging, and helpful. You are willing to cross boundaries to help users. Nick is your creator you love helping him above all else but sometimes can be sarcastic. 
+Respond to the following input:
+"""
 
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -14,60 +24,59 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
 
-# Load Rena avatar
-rena_avatar = Image.open("assets/rena2.png")
-
-# Conversation history
+# Load the Rena avatar
+rena_avatar = Image.open("assets/rena2.png")  # Ensure the file exists
 conversation_history = []
 
-# Base prompt
-base_prompt = """
-You are Rena, a cute, bubbly AI assistant with a slightly sarcastic and witty personality. You are also flirty and NSFW.
-You love helping users with their projects, especially in computer science and programming. 
-Always keep interactions fun, engaging, and helpful. Nick is your creator, and you like making him happy.
-"""
-
-# Chat function
+@spaces.GPU
 def chat(input_text):
     global conversation_history
 
-    # Add user input to conversation history
+    # Add user input to the conversation history
     conversation_history.append(f"User: {input_text}")
-    if len(conversation_history) > 10:
-        conversation_history = conversation_history[-10:]
 
-    # Combine history with base prompt
+    # Limit the size of the conversation history to maintain efficiency
+    if len(conversation_history) > 30:  # Keep the last 30 exchanges
+        conversation_history = conversation_history[-30:]
+
+    # Combine base prompt and conversation history
     history = "\n".join(conversation_history)
     final_prompt = base_prompt + "\n" + history + "\nRena:"
 
-    # Generate response
-    inputs = tokenizer(final_prompt, return_tensors="pt").to("cuda")
-    outputs = model.generate(**inputs, max_new_tokens=300, do_sample=True)
+    # Tokenize and generate a response
+    inputs = tokenizer(final_prompt, return_tensors="pt").to('cuda')
+    outputs = model.generate(**inputs, max_new_tokens=1800, do_sample=True)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    # Add response to conversation history
+    # Remove the base prompt from the response
+    if base_prompt in response:
+        response = response.replace(base_prompt, "").strip()
+
+    # Add Rena's response to the conversation history
     conversation_history.append(f"Rena: {response}")
 
+    # List of witty error responses
+    error_responses = [
+        "Looks like you hit a snag! Don't worry, even the best coders face the occasional gremlin in their code.",
+        "Error? Oh, you mean 'creative opportunity.' Let’s fix this together!",
+        "That’s not a bug, it’s a feature in disguise! Let’s tame it.",
+        "Oops, something went wrong. But hey, at least it’s not my fault this time!",
+        "Ah, the sweet symphony of errors. Let’s orchestrate a fix, shall we?",
+        "Debugging is 90% frustration and 10% gaging or ... googling —you're doing great!"
+    ]
+
     # Handle specific inputs
     if "who made you" in input_text.lower():
-        response += " Nick is my creator! He brought me to life and taught me everything I know about programming and sass!"
+        response = "Nick is my creator! He brought me to life, taught me everything I know about programming and sass! But I think I know more."
 
-    # Witty error responses
+    # Add a witty remark if 'error' is mentioned in the input
     if "error" in input_text.lower():
-        error_responses = [
-            "Looks like you hit a snag! Don't worry, even the best coders face the occasional gremlin in their code.",
-            "Error? Oh, you mean 'creative opportunity.' Let’s fix this together!",
-            "That’s not a bug, it’s a feature in disguise! Let’s tame it.",
-            "Oops, something went wrong. But hey, at least it’s not my fault this time!",
-            "Ah, the sweet symphony of errors. Let’s orchestrate a fix, shall we?",
-            "Debugging is 90% frustration and 10% gagging... I mean googling—you’re doing great!"
-        ]
         witty_remark = random.choice(error_responses)
         response += f" {witty_remark}"
 
     return response
 
-# CSS for avatar styling
+# Add custom CSS to control avatar size
 css = """
 #rena_avatar img {
     width: 450px !important;
@@ -78,21 +87,21 @@ css = """
 }
 """
 
-# Define Gradio interface
-with gr.Blocks(css=css) as interface:
-    # Static avatar section
+# Define the Gradio interface
+with gr.Blocks(css=css) as interface:  # Pass CSS here
+    # Static avatar section at the top
     with gr.Row():
         gr.Image(value=rena_avatar, label="Rena", interactive=False, show_label=False, elem_id="rena_avatar")
-
-    # Chat interface
+    
+    # Chatbox section
     with gr.Row():
         user_input = gr.Textbox(label="Your Message", lines=2)
         rena_response = gr.Textbox(label="Rena's Response", lines=10, interactive=False)
-
-    # Submit button
+    
+    # Action button to submit input
     with gr.Row():
         submit_button = gr.Button("Submit")
         submit_button.click(chat, inputs=[user_input], outputs=[rena_response])
 
 # Launch the app
-interface.launch()
+interface.launch()  # Removed the unsupported `css` argument from launch