Update README.md

c056704 6 months ago

No virus

4.64 kB

	---
	language: zh
	datasets: CLUECorpusSmall
	widget:
	- text: "内容丰富、版式设计考究、图片华丽、印制精美。[MASK]纸箱内还放了充气袋用于保护。"


	---

	# Chinese Pegasus

	## Model description

	This model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/), which is introduced in [this paper](https://arxiv.org/abs/1909.05658). Besides, the models could also be pre-trained by [TencentPretrain](https://github.com/Tencent/TencentPretrain) introduced in [this paper](https://arxiv.org/abs/2212.06385), 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 set of Chinese PEGASUS models either from the [UER-py Modelzoo page](https://github.com/dbiir/UER-py/wiki/Modelzoo), or via HuggingFace from the links below:

	\| \| Link \|
	\| ----------------- \| :----------------------------: \|
	\| PEGASUS-Base \| [L=12/H=768 (Base)][base] \|
	\| PEGASUS-Large \| [L=16/H=1024 (Large)][large] \|

	## How to use

	You can use this model directly with a pipeline for text2text generation (take the case of PEGASUS-Base):

	```python
	>>> from transformers import BertTokenizer, PegasusForConditionalGeneration, Text2TextGenerationPipeline
	>>> tokenizer = BertTokenizer.from_pretrained("uer/pegasus-base-chinese-cluecorpussmall")
	>>> model = PegasusForConditionalGeneration.from_pretrained("uer/pegasus-base-chinese-cluecorpussmall")
	>>> text2text_generator = Text2TextGenerationPipeline(model, tokenizer)
	>>> text2text_generator("内容丰富、版式设计考究、图片华丽、印制精美。[MASK]纸箱内还放了充气袋用于保护。", max_length=50, do_sample=False)
	[{'generated_text': '书的质量很好。'}]
	```

	## Training data

	[CLUECorpusSmall](https://github.com/CLUEbenchmark/CLUECorpus2020/) is used as training data.

	## Training procedure

	The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud](https://cloud.tencent.com/). We pre-train 1,000,000 steps with a sequence length of 512.
	Taking the case of PEGASUS-Base

	```
	python3 preprocess.py --corpus_path corpora/cluecorpussmall_bert.txt \
	--vocab_path models/google_zh_vocab.txt \
	--dataset_path cluecorpussmall_pegasus_seq512_dataset.pt \
	--processes_num 32 --seq_length 512 \
	--data_processor gsg --sentence_selection_strategy random
	```

	```
	python3 pretrain.py --dataset_path cluecorpussmall_pegasus_seq512_dataset.pt \
	--vocab_path models/google_zh_vocab.txt \
	--config_path models/pegasus/base_config.json \
	--output_model_path models/cluecorpussmall_pegasus_base_seq512_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 8
	```

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

	```
	python3 scripts/convert_pegasus_from_uer_to_huggingface.py --input_model_path models/cluecorpussmall_pegasus_base_seq512_model.bin-1000000 \
	--output_model_path pytorch_model.bin \
	--layers_num 12
	```


	### BibTeX entry and citation info

	```
	@inproceedings{zhang2020pegasus,
	title={Pegasus: Pre-training with extracted gap-sentences for abstractive summarization},
	author={Zhang, Jingqing and Zhao, Yao and Saleh, Mohammad and Liu, Peter},
	booktitle={International Conference on Machine Learning},
	pages={11328--11339},
	year={2020},
	organization={PMLR}
	}

	@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}
	```

	[base]:https://huggingface.co/uer/pegasus-base-chinese-cluecorpussmall
	[large]:https://huggingface.co/uer/pegasus-large-chinese-cluecorpussmall