Edit model card

Chinese pre-trained dialogue model (CDial-GPT)

This project provides a large-scale Chinese GPT model pre-trained on the dataset LCCC.

We present a series of Chinese GPT model that are first pre-trained on a Chinese novel dataset and then post-trained on our LCCC dataset.

Similar to TransferTransfo, we concatenate all dialogue histories into one context sentence, and use this sentence to predict the response. The input of our model consists of word embedding, speaker embedding, and positional embedding of each word.

Paper: A Large-Scale Chinese Short-Text Conversation Dataset

How to use

from transformers import OpenAIGPTLMHeadModel, GPT2LMHeadModel, BertTokenizer
import torch
tokenizer = BertTokenizer.from_pretrained("thu-coai/CDial-GPT_LCCC-base")
model = OpenAIGPTLMHeadModel.from_pretrained("thu-coai/CDial-GPT_LCCC-base")

For more details, please refer to our repo. on github.

Downloads last month
4
Safetensors
Model size
98.6M params
Tensor type
F32
·
Unable to determine this model’s pipeline type. Check the docs .

Dataset used to train thu-coai/CDial-GPT_LCCC-base