from transformers import AutoModelForCausalLM, AutoTokenizer, BlenderbotForConditionalGeneration import torch chat_tkn = AutoTokenizer.from_pretrained('microsoft/DialoGPT-medium') mdl = AutoModelForCausalLM.from_pretrained('microsoft/DialoGPT-medium') # chat_tkn = AutoTokenizer.from_pretrained('facebook/blenderbot-400M-distill') # mdl = BlenderbotForConditionalGeneration.from_pretrained('facebook/blenderbot-400M-distill') def converse(user_input, chat_history = []): user_input_ids = chat_tkn(user_input + chat_tkn.eos_token, return_tensors = 'pt').input_ids # keep history in the tensor bot_input_ids = torch.cat([torch.LongTensor(chat_history), user_input_ids], dim = -1) # get response chat_history = mdl.generate( bot_input_ids, max_length = 1000, pad_token_id = chat_tkn.eos_token_id ).tolist() print(chat_history) response = chat_tkn.decode(chat_history[0]).split("<|endoftext|>") print("staring to print response") print(response) # html for display html = "