from transformers import AutoTokenizer, AutoModelForCausalLM import torch import gradio as gr tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large") model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large") def predict(input, history=[]): new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt') bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1) history = model.generate(bot_input_ids, max_length=500, pad_token_id=tokenizer.eos_token_id).tolist() response = tokenizer.decode(history[0]).split("<|endoftext|>") response.remove("") html = "