0_app.py

import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

def runLLM ():
    model = AutoModelForCausalLM.from_pretrained("cyberagent/open-calm-small", device_map="auto", torch_dtype=torch.float16)
    tokenizer = AutoTokenizer.from_pretrained("cyberagent/open-calm-small")

    inputs = tokenizer("AIによって私達の暮らしは、", return_tensors="pt").to(model.device)

    with torch.no_grad():
        tokens = model.generate(
            **inputs,
            max_new_tokens=640,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
            repetition_penalty=1.05,
            pad_token_id=tokenizer.pad_token_id,
        )
    
    output = tokenizer.decode(tokens[0], skip_special_tokens=True)
   
    return output

def display_message():
    msg = runLLM()
    return msg

iface = gr.Interface(fn=display_message, inputs=None, outputs="text")
iface.launch()