python : 플라스크를 사용하여 heroku bert pytorch 모델에 배포: 오류: _pickle.UnpicklingError: 잘못된 로드 키, 'v'

Heroku에 bert 모델을 배포하려고 합니다.

import torch
import transformers
import numpy as np
from flask import Flask, render_template, request
from model import DISTILBERTBaseUncased
MAX_LEN= 320
TOKENIZER= transformers.DistilBertTokenizer.from_pretrained(
    "distilbert-base-uncased", do_lower_case=True
)
DEVICE= "cpu"
MODEL= DISTILBERTBaseUncased()
MODEL.load_state_dict(torch.load("weight.bin"))
MODEL.to(DEVICE)
MODEL.eval()
app= Flask(__name__)
def sentence_prediction(sentence):
    tokenizer= TOKENIZER
    max_len= MAX_LEN
    comment= str(sentence)
    comment= " ".join(comment.split())
    inputs= tokenizer.encode_plus(
        comment,
        None,
        add_special_tokens=True,
        max_length=max_len,
        pad_to_max_length=True,
    )
    ids= inputs["input_ids"]
    mask= inputs["attention_mask"]
    ids= torch.tensor(ids, dtype=torch.long).unsqueeze(0)
    mask= torch.tensor(mask, dtype=torch.long).unsqueeze(0)
    ids= ids.to(DEVICE, dtype=torch.long)
    mask= mask.to(DEVICE, dtype=torch.long)
    outputs= MODEL(ids=ids, mask=mask)
    outputs= torch.sigmoid(outputs).cpu().detach().numpy()
    return outputs[0][0]
@app.route("/")
def index_page():
    return render_template("index.html")
@app.route("/model")
def models():
    return render_template("model.html")
@app.route("/predict", methods=["POST", "GET"])
def predict():
    if request.method== "POST":
        sentence= request.form.get("text")
        Toxic_prediction= sentence_prediction(sentence)
        return render_template(
            "index.html", prediction_text=np.round((Toxic_prediction * 100), 2)
        )
    return render_template("index.html", prediction_text="")
if __name__== "__main__":
    app.run(debug=True)

오류

MODEL.load_state_dict(torch.load("weight.bin"))

2020-05-18T06:32:32.134536+00:00 앱[web.1]: 파일 "/app/.heroku/python/lib/python3.7/site-packages/torch/serialization.py", 라인 593, 로드 중

2020-05-18T06:32:32.134536+00:00 앱[web.1]: return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)

2020-05-18T06:32:32.134536+00:00 앱[web.1]: 파일 "/app/.heroku/python/lib/python3.7/site-packages/torch/serialization.py", 763행, _legacy_load

2020-05-18T06:32:32.134537+00:00 앱[web.1]: magic_number= pickle_module.load(f, **pickle_load_args)

2020-05-18T06:32:32.134537+00:00 앱[web.1]: _pickle.UnpicklingError: 로드 키 'v'가 잘못되었습니다.

1. code가 로컬에서 제대로 작동합니다.
2. Heroku 배포 방법은 Github입니다.
3. weight.bin 크기는 255MB입니다.
4. localhost에서 제대로 작동하는 플라스크 API