app.py

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, AutoConfig
#from transformers import T5Tokenizer, T5ForConditionalGeneration, AutoConfig
import gradio as gr
from torch.nn import functional as F
import seaborn
import matplotlib
import platform
from transformers.file_utils import ModelOutput

if platform.system() == "Darwin":

    print("MacOS")
    matplotlib.use('Agg')

import matplotlib.pyplot as plt
import io
from PIL import Image
import matplotlib.font_manager as fm

# global var

MODEL_NAME = 'https://huggingface.co/yseop/FNP_T5_D2T_complete'
#tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
#model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)

tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME)
model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME)
config = AutoConfig.from_pretrained(MODEL_NAME)

MODEL_BUF = {
    "name": MODEL_NAME,
    "tokenizer": tokenizer,
    "model": model,
    "config": config
}

font_dir = ['./']

for font in fm.findSystemFonts(font_dir):
    print(font)
    fm.fontManager.addfont(font)

plt.rcParams["font.family"] = 'NanumGothicCoding'

def change_model_name(name):

    MODEL_BUF["name"] = name
    MODEL_BUF["tokenizer"] = AutoTokenizer.from_pretrained(name)
    MODEL_BUF["model"] = AutoModelForSequenceClassification.from_pretrained(name)
    MODEL_BUF["config"] = AutoConfig.from_pretrained(name)


def generate(text, model, tokenizer):
   model.eval()
   input_ids = tokenizer.encode("webNLG:{}".format(text), return_tensors="pt")
   outputs = model.generate(input_ids, max_length=200, num_beams=2, repetition_penalty=2.5, top_k=50, top_p=0.98, length_penalty=1.0, early_stopping=True)
   return tokenizer.decode(outputs[0])




if __name__ == '__main__':

    text = 'Group profit | valIs | € 115.7 million && € 115.7 million | dTime | in 2019'

    model_name_list = [

        'yseop/distilbert-base-financial-relation-extraction'

    ]


app = gr.Interface(

    fn=predict,

    inputs=[gr.inputs.Dropdown(model_name_list, label="Model Name"), 'triples'], outputs=['text'], 

    examples = [[MODEL_BUF["name"], text]],

    title="FReE",

    description="Financial relations classifier"

    )

app.launch(inline=False)