T5用于抽象问答

这是使用文本到文本方法对T5-base模型进行精调的抽象问答模型

模型训练

该模型在Colab TPU上进行了2个时轮的训练，内存为35GB

模型运行情况 ?

from transformers import AutoModelWithLMHead, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("tuner007/t5_abs_qa")
model = AutoModelWithLMHead.from_pretrained("tuner007/t5_abs_qa")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)

def get_answer(question, context):
input_text = "context: %s <question for context: %s </s>" % (context,question)
features = tokenizer([input_text], return_tensors='pt')
out = model.generate(input_ids=features['input_ids'].to(device), attention_mask=features['attention_mask'].to(device))
return tokenizer.decode(out[0])

context = "In Norse mythology, Valhalla is a majestic, enormous hall located in Asgard, ruled over by the god Odin."
question = "What is Valhalla?"
get_answer(question, context)
# output: 'It is a hall of worship ruled by Odin.'

context = "In Norse mythology, Valhalla is a majestic, enormous hall located in Asgard, ruled over by the god Odin."
question = "What is Asgard?"
get_answer(question, context)
# output: 'No answer available in context.'

由Arpit Rajauria创建