Roberta Large STS-B 模型

该模型是基于STS-B数据集微调的RoBERTA模型。训练参数如下：

!python /content/transformers/examples/text-classification/run_glue.py \
    --model_type roberta \
    --model_name_or_path roberta-large \
    --task_name STS-B \
    --do_train \
    --do_eval \
    --do_lower_case \
    --data_dir /content/glue_data/STS-B/ \
    --max_seq_length 128 \
    --per_gpu_eval_batch_size=8   \
    --per_gpu_train_batch_size=8   \
    --learning_rate 2e-5 \
    --num_train_epochs 3.0 \
    --output_dir /content/roberta-sts-b

使用方法

import toolz
import torch
batch_size = 6

def roberta_similarity_batches(to_predict):
  batches = toolz.partition(batch_size, to_predict)
  similarity_scores = []  
  for batch in batches: 
    sentences = [(sentence_similarity["sent1"], sentence_similarity["sent2"])  for sentence_similarity in batch]   
    batch_scores = similarity_roberta(model, tokenizer,sentences)
    similarity_scores = similarity_scores + batch_scores[0].cpu().squeeze(axis=1).tolist()
  return similarity_scores

def similarity_roberta(model, tokenizer, sent_pairs):
  batch_token = tokenizer(sent_pairs, padding='max_length', truncation=True, max_length=500)
  res = model(torch.tensor(batch_token['input_ids']).cuda(), attention_mask=torch.tensor(batch_token["attention_mask"]).cuda())  
  return res

similarity_roberta(model, tokenizer, [('纽约--(商业电讯)--全球投资者权益律师事务所Rosen Law Firm宣布，正在代表淡水河谷公司(VALE)股东调查潜在的证券索赔，指控淡水河谷可能向投资公众发布了实质性的误导性商业信息',
                                       '股票警报：Rosen Law Firm宣布对淡水河谷公司(VALE)证券索赔展开调查')])