File size: 4,290 Bytes
7500954 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
import gradio as gr
import torch
from transformers import pipeline
def initialize_model():
"""Initialize the text generation pipeline with device detection"""
# Check if CUDA is available, otherwise fall back to CPU
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {device}")
try:
generator = pipeline(
"text-generation",
model="akhaliq/gemma-3-270m-gradio-coder",
device=device
)
return generator
except Exception as e:
print(f"Error loading model: {e}")
# Fallback to CPU if CUDA fails
if device == "cuda":
print("Falling back to CPU...")
generator = pipeline(
"text-generation",
model="akhaliq/gemma-3-270m-gradio-coder",
device="cpu"
)
return generator
raise e
# Initialize the model globally
print("Loading model...")
generator = initialize_model()
print("Model loaded successfully!")
def chat_response(message, history):
"""Generate response for the chatbot"""
try:
# Format the message for the model
input_message = [{"role": "user", "content": message}]
# Generate response
output = generator(
input_message,
max_new_tokens=128,
return_full_text=False,
do_sample=True,
temperature=0.7,
pad_token_id=generator.tokenizer.eos_token_id
)[0]
response = output["generated_text"]
return response
except Exception as e:
return f"Sorry, I encountered an error: {str(e)}"
# Create the Gradio interface
def create_chatbot():
"""Create and launch the Gradio chatbot interface"""
# Custom CSS for better styling
css = """
.gradio-container {
max-width: 800px !important;
margin: auto !important;
}
.chat-message {
padding: 10px !important;
margin: 5px !important;
border-radius: 10px !important;
}
"""
# Create the chatbot interface
with gr.Blocks(css=css, title="AI Chatbot") as demo:
gr.Markdown("# 🤖 AI Chatbot")
gr.Markdown("*Powered by Gemma-3-270m model via Transformers*")
chatbot = gr.Chatbot(
height=500,
bubble_full_width=False,
show_label=False
)
with gr.Row():
msg = gr.Textbox(
placeholder="Type your message here...",
show_label=False,
scale=4
)
send_btn = gr.Button("Send", scale=1, variant="primary")
clear_btn = gr.Button("Clear", scale=1)
# Example questions
gr.Examples(
examples=[
"If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?",
"What's the most important lesson you've learned in life?",
"How do you think AI will change the world in the next 10 years?",
"What would you do if you had unlimited resources for one day?"
],
inputs=msg
)
def respond(message, chat_history):
if not message.strip():
return chat_history, ""
# Get bot response
bot_message = chat_response(message, chat_history)
# Add to chat history
chat_history.append((message, bot_message))
return chat_history, ""
def clear_chat():
return [], ""
# Event handlers
msg.submit(respond, [msg, chatbot], [chatbot, msg])
send_btn.click(respond, [msg, chatbot], [chatbot, msg])
clear_btn.click(clear_chat, None, [chatbot, msg])
return demo
if __name__ == "__main__":
print("Creating Gradio interface...")
demo = create_chatbot()
print("Starting Gradio server...")
demo.launch(
share=False, # Set to True if you want a public link
server_name="0.0.0.0", # Allow external connections
server_port=7860,
show_error=True
)
|