Abid
png added
ac41d61
import os
import gradio as gr
HF_TOKEN = os.getenv('HF_TOKEN')
hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "Rick-bot-flags")
title = "Have Fun With RickBot"
description = """
<p>
<center>
The bot is trained on Rick and Morty dialogues Kaggle Dataset using DialoGPT.
<img src="https://gradio.app/assets/img/rick.png">
</center>
</p>
"""
article = "<p style='text-align: center'><a href='https://medium.com/geekculture/discord-bot-using-dailogpt-and-huggingface-api-c71983422701' target='_blank'>Complete Tutorial</a></p><p style='text-align: center'><a href='https://dagshub.com/kingabzpro/DailoGPT-RickBot' target='_blank'>Project is Available at DAGsHub</a></p></center></p>"
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("kingabzpro/DialoGPT-small-Rick-Bot")
model = AutoModelForCausalLM.from_pretrained("kingabzpro/DialoGPT-small-Rick-Bot")
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 lines
response = tokenizer.decode(history[0]).replace("<|endoftext|>", "\n")
return response, history
gr.Interface(fn = predict, inputs = ["textbox","state"], outputs = ["chatbot","state"],allow_flagging = "manual",theme ="grass",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