deberta-v3-large用于问答

这是 deberta-v3-large 模型，使用 SQuAD2.0 数据集进行微调。它已经针对问答对进行了训练，包括包含无法回答的问题。任务是问答。

概述

语言模型：deberta-v3-large 语言：英语下游任务：提取型问答训练数据：SQuAD 2.0 评估数据：SQuAD 2.0 代码：见 an example QA pipeline on Haystack 基础设施：1x NVIDIA A10G

超参数

batch_size = 2
grad_acc_steps = 32
n_epochs = 6
base_LM_model = "microsoft/deberta-v3-large"
max_seq_len = 512
learning_rate = 7e-6
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64

使用方法

在Haystack中

Haystack是deepset的一个NLP框架。您可以在Haystack流水线中使用该模型进行大规模的问答（对许多文档进行问答）。要在 Haystack 中加载模型：

reader = FARMReader(model_name_or_path="deepset/deberta-v3-large-squad2")
# or 
reader = TransformersReader(model_name_or_path="deepset/deberta-v3-large-squad2",tokenizer="deepset/deberta-v3-large-squad2")

在Transformers中

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/deberta-v3-large-squad2"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

性能

在SQuAD 2.0开发集上使用 official eval script 进行评估。

"exact": 87.6105449338836,
"f1": 90.75307008866517,

"total": 11873,
"HasAns_exact": 84.37921727395411,
"HasAns_f1": 90.6732795483674,
"HasAns_total": 5928,
"NoAns_exact": 90.83263246425568,
"NoAns_f1": 90.83263246425568,
"NoAns_total": 5945