Spaces:
Runtime error
Runtime error
File size: 1,254 Bytes
f9877eb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
from transformers import AutoModelWithLMHead, AutoTokenizer
import torch
import gradio as gr
tokenizer = AutoTokenizer.from_pretrained('microsoft/DialoGPT-medium')
model = AutoModelWithLMHead.from_pretrained('output-medium')
chat_history_ids = None
step = 0
def predict(input, chat_history_ids=chat_history_ids, step=step):
# encode the new user input, add the eos_token and return a tensor in Pytorch
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(
[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,
no_repeat_ngram_size=3,
do_sample=True,
top_k=100,
top_p=0.7,
temperature=0.8
)
step = step + 1
output = tokenizer.decode(
chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
return output
gr.Interface(fn=predict, inputs="text", outputs="text").launch(debug=True)
|