app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "zltd/zbrain_llm_0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Define a function for text generation
def generate_text(prompt, max_length=100):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(**inputs, max_length=max_length)
    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
    return generated_text

# Create a Gradio interface
demo = gr.Interface(
    fn=generate_text,
    inputs="text",
    outputs="text",
    title="Text Generation with Custom Model",
    description="Enter a prompt to generate text.",
)

if __name__ == "__main__":
    demo.launch()