app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2.5-7B-Instruct"  # Replace with a smaller model if needed

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")

# Define the inference function
def chat_with_model(input_text):
    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
    outputs = model.generate(inputs["input_ids"], max_length=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create the Gradio interface
iface = gr.Interface(
    fn=chat_with_model,
    inputs=gr.Textbox(label="Enter your message"),
    outputs=gr.Textbox(label="Model's Response"),
    title="AI Chat with Qwen",
)

iface.launch()