Xlmroberta Squadv2

🚀 XLM-ROBERTA-LARGE在SQuADv2上微调

本项目是在SQuADv2数据集上针对问答任务微调的xlm-roberta-large模型，可有效解决问答相关问题，为问答系统的构建提供强大的模型支持。

🚀 快速开始

以下是使用该模型进行问答的示例代码：

from transformers import XLMRobertaTokenizer, XLMRobertaForQuestionAnswering
import torch

tokenizer = XLMRobertaTokenizer.from_pretrained('a-ware/xlmroberta-squadv2')
model = XLMRobertaForQuestionAnswering.from_pretrained('a-ware/xlmroberta-squadv2')

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
encoding = tokenizer(question, text, return_tensors='pt')
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']

start_scores, end_scores = model(input_ids, attention_mask=attention_mask, output_attentions=False)[:2]

all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0])
answer = ' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1])
answer = tokenizer.convert_tokens_to_ids(answer.split())
answer = tokenizer.decode(answer)
#answer => 'a nice puppet' 

✨ 主要特性

本模型基于XLM-Roberta架构，在SQuADv2数据集上进行微调，可用于问答任务。

📚 详细文档

模型详情

XLM-Roberta在论文 XLM-R: State-of-the-art cross-lingual understanding through self-supervision 中被提出。

模型训练

该模型使用simpletransformers包装器，以下列参数进行训练：

train_args = {
    'learning_rate': 1e-5,
    'max_seq_length': 512,
    'doc_stride': 512,
    'overwrite_output_dir': True,
    'reprocess_input_data': False,
    'train_batch_size': 8,
    'num_train_epochs': 2,
    'gradient_accumulation_steps': 2,
    'no_cache': True,
    'use_cached_eval_features': False,
    'save_model_every_epoch': False,
    'output_dir': "bart-squadv2",
    'eval_batch_size': 32,
    'fp16_opt_level': 'O2',
    }

结果

{"correct": 6961, "similar": 4359, "incorrect": 553, "eval_loss": -12.177856394381962}

本项目由 A-ware UG 用心打造