app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_name = "infly/OpenCoder-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

@spaces.GPU
def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, padding=True)
    outputs = model.generate(inputs["input_ids"], max_length=100, num_return_sequences=1)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create Gradio interface
interface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
    outputs=gr.Textbox(label="Generated Text")
)

# Launch the Gradio app
if __name__ == "__main__":
    interface.launch()