app.py

import gradio
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("cyberagent/open-calm-3b", device_map="auto", torch_dtype=torch.float32)
tokenizer = AutoTokenizer.from_pretrained("cyberagent/open-calm-3b")

def my_inference_function(mail):
    mail=mail.replace("\n", "")
    inputs = tokenizer(mail, return_tensors="pt").to(model.device)
    with torch.no_grad():
        tokens = model.generate(
            **inputs,
            max_new_tokens=4,
            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)
    output=output.replace("(上司へのメール敬語で)","")
    output=output.replace(mail,"")
    output=output.replace("\n", "")
    return output

gradio_interface = gradio.Interface(
  fn = my_inference_function,
  inputs = "text",
  outputs = "text"
)
gradio_interface.launch()