app.py

import gradio as gr
import transformers
import torch

import os

hf_key = os.getenv("HF_TOKEN")

# Initialize the model
model_id = "bmi-labmedinfo/Igea-350M-v0.0.1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    token=hf_key
)

# Define the function to generate text
def generate_text(input_text, max_new_tokens, temperature, top_k, top_p):
    output = pipeline(
        input_text,
        max_new_tokens=max_new_tokens,
        temperature=temperature,
        top_k=top_k,
        top_p=top_p,
    )
    return output[0]['generated_text']

# Create the Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(lines=2, placeholder="Enter your text here...", label="Input Text"),
        gr.Slider(minimum=1, maximum=200, value=128, step=1, label="Max New Tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, value=1.0, step=0.1, label="Temperature"),
        gr.Slider(minimum=1, maximum=100, value=50, step=1, label="Top-k"),
        gr.Slider(minimum=0.0, maximum=1.0, value=0.95, step=0.01, label="Top-p")
    ],
    outputs="text",
    title="Text Generation Interface",
    description="Enter a prompt to generate text using the Igea-350M model and adjust the hyperparameters."
)

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