import os import gradio as gr HF_TOKEN = os.getenv('HF_TOKEN') hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "Rick-bot-flags") title = "Talk To Me Morty" description = """

The bot was trained on Rick and Morty dialogues Kaggle Dataset using DialoGPT. rick

""" article = "

Complete Tutorial

Project is Available at DAGsHub

visitor badge

" from transformers import AutoModelForCausalLM, AutoTokenizer import torch tokenizer = AutoTokenizer.from_pretrained("ericzhou/DialoGPT-Medium-Rick_v2") model = AutoModelForCausalLM.from_pretrained("ericzhou/DialoGPT-Medium-Rick_v2") 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).tolist() # convert the tokens to text, and then split the responses into the right format 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, inputs = ["textbox","state"], outputs = ["chatbot","state"],allow_flagging = "manual",title = title, flagging_callback = hf_writer, description = description, article = article ).launch(enable_queue=True) # customizes the input component #theme ="grass", #title = title, #flagging_callback=hf_writer, #description = description, #article = article