A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)
DialoGPT is a SOTA large-scale pretrained dialogue response generation model for multiturn conversations. The human evaluation results indicate that the response generated from DialoGPT is comparable to human response quality under a single-turn conversation Turing test. The model is trained on 147M multi-turn dialogue from Reddit discussion thread.
- Multi-turn generation examples from an interactive environment:
Role | Response |
---|---|
User | Does money buy happiness? |
Bot | Depends how much money you spend on it . |
User | What is the best way to buy happiness ? |
Bot | You just have to be a millionaire by your early 20s, then you can be happy . |
User | This is so difficult ! |
Bot | You have no idea how hard it is to be a millionaire and happy . There is a reason the rich have a lot of money |
Please find the information about preprocessing, training and full details of the DialoGPT in the original DialoGPT repository
ArXiv paper: https://arxiv.org/abs/1911.00536
How to use
Now we are ready to try out how the model works as a chatting partner!
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")
# 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)))
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 25.02 |
ARC (25-shot) | 25.77 |
HellaSwag (10-shot) | 25.79 |
MMLU (5-shot) | 25.81 |
TruthfulQA (0-shot) | 47.49 |
Winogrande (5-shot) | 50.28 |
GSM8K (5-shot) | 0.0 |
DROP (3-shot) | 0.0 |
- Downloads last month
- 36,885
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.