Roberta Small Word Chinese Cluecorpussmall

🚀 Chinese word-based RoBERTa Miniatures

This project offers a set of 5 Chinese word-based RoBERTa models, which are faster and perform better than character-based models according to experimental results.

🚀 Quick Start

You can directly use these models with a pipeline for masked language modeling. For example, take the word-based RoBERTa-Medium:

>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='uer/roberta-medium-word-chinese-cluecorpussmall')
>>> unmasker("[MASK]的首都是北京。")
[
    {'sequence': '中国 的首都是北京。',
     'score': 0.21525809168815613, 
     'token': 2873, 
     'token_str': '中国'}, 
    {'sequence': '北京 的首都是北京。', 
     'score': 0.15194718539714813, 
     'token': 9502, 
     'token_str': '北京'}, 
    {'sequence': '我们 的首都是北京。', 
     'score': 0.08854265511035919, 
     'token': 4215, 
     'token_str': '我们'},
    {'sequence': '美国 的首都是北京。', 
     'score': 0.06808705627918243, 
     'token': 7810, 
     'token_str': '美国'}, 
    {'sequence': '日本 的首都是北京。', 
     'score': 0.06071401759982109, 
     'token': 7788, 
     'token_str': '日本'}
]

✨ Features

• Word-based Advantage: Most Chinese pre-trained weights are character-based. In contrast, word-based models are faster due to shorter sequence lengths and perform better according to experimental results.
• Multiple Sizes: Five Chinese word-based RoBERTa models of different sizes are released to meet various needs.
• Reproducibility: Publicly available corpus and word segmentation tools are used, and all training details are provided to facilitate users in reproducing the results.

💻 Usage Examples

Basic Usage

Here is how to use this model to get the features of a given text in PyTorch:

from transformers import AlbertTokenizer, BertModel
tokenizer = AlbertTokenizer.from_pretrained('uer/roberta-medium-word-chinese-cluecorpussmall')
model = BertModel.from_pretrained("uer/roberta-medium-word-chinese-cluecorpussmall")
text = "用你喜欢的任何文本替换我。"
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)

Advanced Usage

Here is the usage in TensorFlow:

from transformers import AlbertTokenizer, TFBertModel
tokenizer = AlbertTokenizer.from_pretrained('uer/roberta-medium-word-chinese-cluecorpussmall')
model = TFBertModel.from_pretrained("uer/roberta-medium-word-chinese-cluecorpussmall")
text = "用你喜欢的任何文本替换我。"
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)

Since BertTokenizer does not support sentencepiece, AlbertTokenizer is used here.

📚 Documentation

Model description

This is the set of 5 Chinese word-based RoBERTa models pre-trained by UER-py, which is introduced in this paper. Besides, the models could also be pre-trained by TencentPretrain introduced in this paper, which inherits UER-py to support models with parameters above one billion, and extends it to a multimodal pre-training framework.

You can download the 5 Chinese RoBERTa miniatures either from the UER-py Modelzoo page, or via HuggingFace from the links below:

Compared with char-based models, word-based models achieve better results in most cases. Here are scores on the devlopment set of six Chinese tasks:

For each task, we selected the best fine-tuning hyperparameters from the lists below, and trained with the sequence length of 128:

• epochs: 3, 5, 8
• batch sizes: 32, 64
• learning rates: 3e-5, 1e-4, 3e-4

Training data

CLUECorpusSmall is used as training data. Google's sentencepiece is used for word segmentation. The sentencepiece model is trained on CLUECorpusSmall corpus:

>>> import sentencepiece as spm
>>> spm.SentencePieceTrainer.train(input='cluecorpussmall.txt',
             model_prefix='cluecorpussmall_spm',
             vocab_size=100000,
             max_sentence_length=1024,
             max_sentencepiece_length=6,
             user_defined_symbols=['[MASK]','[unused1]','[unused2]',
                '[unused3]','[unused4]','[unused5]','[unused6]',
                '[unused7]','[unused8]','[unused9]','[unused10]'],
             pad_id=0,
             pad_piece='[PAD]',
             unk_id=1,
             unk_piece='[UNK]',
             bos_id=2,
             bos_piece='[CLS]',
             eos_id=3,
             eos_piece='[SEP]',
             train_extremely_large_corpus=True
            )

Training procedure

Models are pre-trained by UER-py on Tencent Cloud. We pre-train 1,000,000 steps with a sequence length of 128 and then pre-train 250,000 additional steps with a sequence length of 512. We use the same hyper-parameters on different model sizes.

Taking the case of word-based RoBERTa-Medium

Stage1:

python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                      --spm_model_path models/cluecorpussmall_spm.model \
                      --dataset_path cluecorpussmall_word_seq128_dataset.pt \
                      --processes_num 32 --seq_length 128 \
                      --dynamic_masking --data_processor mlm

python3 pretrain.py --dataset_path cluecorpussmall_word_seq128_dataset.pt \
                    --spm_model_path models/cluecorpussmall_spm.model \
                    --config_path models/bert/medium_config.json \
                    --output_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin \
                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
                    --total_steps 1000000 --save_checkpoint_steps 100000 --report_steps 50000 \
                    --learning_rate 1e-4 --batch_size 64 \
                    --data_processor mlm --target mlm

Stage2:

python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                      --spm_model_path models/cluecorpussmall_spm.model \
                      --dataset_path cluecorpussmall_word_seq512_dataset.pt \
                      --processes_num 32 --seq_length 512 \
                      --dynamic_masking --data_processor mlm

python3 pretrain.py --dataset_path cluecorpussmall_word_seq512_dataset.pt \
                    --spm_model_path models/cluecorpussmall_spm.model \
                    --pretrained_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-1000000 \
                    --config_path models/bert/medium_config.json \
                    --output_model_path models/cluecorpussmall_word_roberta_medium_seq512_model.bin \
                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
                    --total_steps 250000 --save_checkpoint_steps 50000 --report_steps 10000 \
                    --learning_rate 5e-5 --batch_size 16 \
                    --data_processor mlm --target mlm

Finally, we convert the pre-trained model into Huggingface's format:

python3 scripts/convert_bert_from_uer_to_huggingface.py --input_model_path models/cluecorpussmall_word_roberta_medium_seq512_model.bin-250000 \
                                                        --output_model_path pytorch_model.bin \
                                                        --layers_num 8 --type mlm

BibTeX entry and citation info

@article{devlin2018bert,
  title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1810.04805},
  year={2018}
}

@article{turc2019,
  title={Well-Read Students Learn Better: On the Importance of Pre-training Compact Models},
  author={Turc, Iulia and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1908.08962v2 },
  year={2019}
}

@article{zhao2019uer,
  title={UER: An Open-Source Toolkit for Pre-training Models},
  author={Zhao, Zhe and Chen, Hui and Zhang, Jinbin and Zhao, Xin and Liu, Tao and Lu, Wei and Chen, Xi and Deng, Haotang and Ju, Qi and Du, Xiaoyong},
  journal={EMNLP-IJCNLP 2019},
  pages={241},
  year={2019}
}

@article{zhao2023tencentpretrain,
  title={TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities},
  author={Zhao, Zhe and Li, Yudong and Hou, Cheng and Zhao, Jing and others},
  journal={ACL 2023},
  pages={217},
  year={2023}