You can deploy this model and start earning money today!

satkinson/
DialoGPT-small-marvin

Name: DialoGPT-small-marvin
Availability: InStock

text-generation-inference

endpoints_compatible

Views

No views yet

DialoGPT model fine-tuned using Amazon's Topical Chat Dataset

This model is fine-tuned from the original DialoGPT-small.

This model was fine-tuned on a subset of messages from Amazon's Topical Chat dataset (due to processing limitations, I restricted my training data to 50,000 observations.

The dataset spands 8 broad topics and contains conversation partner who do not have defined roles. It was created with the goal of aiding in the effort to build a socialbot that can have deep, engaging open-domain conversations with humans.

The eight broad topics are:

fashion
politics
books
sports
general entertainment
music
science and technology
movies

Sample dialogue:

Role	Response
User:	Do you like Kanye?
Bot:	He is okay, I like some of his music
User:	Any other thoughts on him?
Bot:	He is not a great person, but I like some of his music, so I'm not too surprised
User:	What does that say about you?
Bot:	I think he's trying to be funny. It's just that he's always out there and out there. Always out there. That's all I'll say.
User:	You're strange.
Bot:	Yeah, I guess so.

Using the model

Example code for trying out the model (taken directly from the DialoGPT-medium model card):

python

from transformers import AutoModelWithLMHead, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("satkinson/DialoGPT-small-marvin")
model = AutoModelWithLMHead.from_pretrained("satkinson/DialoGPT-small-marvin")
# Let's chat for 5 lines
for step in range(5):
	# encode the new user input, add the eos_token and return a tensor in Pytorch
	new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
	# append the new user input tokens to the chat history
	bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
	# generated a response while limiting the total chat history to 1000 tokens, 
	chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
	# pretty print last ouput tokens from bot
	print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))