chatbot / app.py
import transformers
import gradio as gr
import torch
from transformers import GPT2LMHeadModel, GPT2Tokenizer
model_name = 'microsoft/DialoGPT-large'
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)
def predict(input, history=[]):
# tokenize the new input sentence
new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
# append the new user input tokens to the chat history
bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
# generate a response
history = model.generate(
bot_input_ids,
max_length=1000,
pad_token_id=tokenizer.eos_token_id,
no_repeat_ngram_size=3,
top_p = 0.92,
top_k = 50
).tolist()
# convert the tokens to text, and then split the responses into lines
response = tokenizer.decode(history[0]).split("<|endoftext|>")
response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)] # convert to tuples of list
return response, history
gr.Interface(fn=predict,
title="DialoGPT-large",
inputs=["text", "state"],
outputs=["chatbot", "state"],
).launch()