Downloads · 30 days
17
2% of all-time downloads
sophiadt/DialoGPT-medium-reigen
DialoGPT-medium-reigen is a text generation model from sophiadt. Use it when you need the model to write or continue text. It is set up for transformers.
This is an instance of microsoft/DialoGPT-medium trained on an anime character, Reigen Arataka from Mob Psycho 100. The data comes from a Kaggle dataset of the transcript from season 1, 2, and the OVA.
Downloads · 30 days
17
2% of all-time downloads
All-time downloads
884
Public
Parameters
380M
2.9 GB on disk
Likes
1
Public
Click a slice to open those files.
.bin1.4 GB · 50%
How the weights are stored.
F32355M · 93%
From the Hugging Face model README
This is an instance of microsoft/DialoGPT-medium trained on an anime character, Reigen Arataka from Mob Psycho 100. The data comes from a Kaggle dataset of the transcript from season 1, 2, and the OVA.
Credits to Lynn Zheng and her Discord AI Chatbot tutorial for helping me build this.
Chat with the model:
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("sophiadt/DialoGPT-medium-reigen")
model = AutoModelWithLMHead.from_pretrained("sophiadt/DialoGPT-medium-reigen")
# Let's chat for 4 lines
for step in range(4):
# 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')
# print(new_user_input_ids)
# 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=200,
pad_token_id=tokenizer.eos_token_id,
no_repeat_ngram_size=3,
do_sample=True,
top_k=100,
top_p=0.7,
temperature=0.8
)
# pretty print last ouput tokens from bot
print("Reigen Bot: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))