import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
pip install accelerate

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-1.8B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-1.8B", device_map="auto", trust_remote_code=True)

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=generate_text, inputs="text", outputs="text", title="Qwen Text Generator").launch()