BERT Models

**Overview**

The BERT models are language models developed by Google. The models provided in this listing are

- [bert_base_cased](https://huggingface.co/bert-base-cased)
- [bert_base_multilingual_cased](https://huggingface.co/bert-base-multilingual-cased)
- [bert_base_uncased](https://huggingface.co/bert-base-uncased)
- [bert_large_cased](https://huggingface.co/bert-large-cased)
- [bert_large_cased_whole_word_masking](https://huggingface.co/bert-large-cased-whole-word-masking)
- [bert_large_uncased](https://huggingface.co/bert-large-uncased)
- [bert_large_uncased_whole_word_masking](https://huggingface.co/bert-large-uncased-whole-word-masking)

The models are packaged using MLflow’s transformers flavor.
- [bert_base_cased](https://huggingface.co/bert-base-cased), [bert_base_multilingual_cased](https://huggingface.co/bert-base-multilingual-cased), [bert_base_uncased](https://huggingface.co/bert-base-uncased), [bert_large_cased](https://huggingface.co/bert-large-cased), [bert_large_cased_whole_word_masking](https://huggingface.co/bert-large-cased-whole-word-masking), [bert_large_uncased](https://huggingface.co/bert-large-uncased), [bert_large_uncased_whole_word_masking](https://huggingface.co/bert-large-uncased-whole-word-masking): pretrained models using a masked language modeling (MLM) objective and can be further fine-tuning on specific applications.

Bert models are licensed under the [Apache 2.0 License](https://github.com/google-research/bert/blob/master/LICENSE). By installing this listing, you acknowledge and agree to the license.

For example notebooks of using the bert model in various use cases on Databricks, refer to [the Databricks ML example repository](https://github.com/databricks/databricks-ml-examples/tree/master/llm-models/bert).

**Use cases**

[bert_base_cased](https://huggingface.co/bert-base-cased), [bert_base_multilingual_cased](https://huggingface.co/bert-base-multilingual-cased), [bert_base_uncased](https://huggingface.co/bert-base-uncased), [bert_large_cased](https://huggingface.co/bert-large-cased), [bert_large_cased_whole_word_masking](https://huggingface.co/bert-large-cased-whole-word-masking), [bert_large_uncased](https://huggingface.co/bert-large-uncased), [bert_large_uncased_whole_word_masking](https://huggingface.co/bert-large-uncased-whole-word-masking):
- Fine-tuning on specific applications such as text classification

**Product details**

The pre-trained model can be used for further fine-tuning on specific applications. The fine-tuned model in this listing can be deployed directly to Databricks Model Serving for immediate use, or loaded for fine-tuning or batch inference use cases. For more details, install the listing and view the provided model cards for each model.

**概述**
BERT模型（Bidirectional Encoder Representations from Transformers）是由谷歌（Google）开发的语言模型。本列表收录的模型包括：
- [bert_base_cased](https://huggingface.co/bert-base-cased)
- [bert_base_multilingual_cased](https://huggingface.co/bert-base-multilingual-cased)
- [bert_base_uncased](https://huggingface.co/bert-base-uncased)
- [bert_large_cased](https://huggingface.co/bert-large-cased)
- [bert_large_cased_whole_word_masking](https://huggingface.co/bert-large-cased-whole-word-masking)
- [bert_large_uncased](https://huggingface.co/bert-large-uncased)
- [bert_large_uncased_whole_word_masking](https://huggingface.co/bert-large-uncased-whole-word-masking)

上述模型均采用MLflow的Transformers封装格式进行打包。

以下模型均基于掩码语言建模（Masked Language Modeling，MLM）目标完成预训练，可针对特定应用场景开展进一步微调：
[bert_base_cased](https://huggingface.co/bert-base-cased)、[bert_base_multilingual_cased](https://huggingface.co/bert-base-multilingual-cased)、[bert_base_uncased](https://huggingface.co/bert-base-uncased)、[bert_large_cased](https://huggingface.co/bert-large-cased)、[bert_large_cased_whole_word_masking](https://huggingface.co/bert-large-cased-whole-word-masking)、[bert_large_uncased](https://huggingface.co/bert-large-uncased)、[bert_large_uncased_whole_word_masking](https://huggingface.co/bert-large-uncased-whole-word-masking)

本系列BERT模型采用[Apache 2.0许可证](https://github.com/google-research/bert/blob/master/LICENSE)进行授权。安装本列表中的模型包即表示您已知晓并同意该许可证的相关条款。

如需查看在Databricks平台上针对各类应用场景使用BERT模型的示例笔记本，请参阅[Databricks ML示例仓库](https://github.com/databricks/databricks-ml-examples/tree/master/llm-models/bert)。

**应用场景**
[bert_base_cased](https://huggingface.co/bert-base-cased)、[bert_base_multilingual_cased](https://huggingface.co/bert-base-multilingual-cased)、[bert_base_uncased](https://huggingface.co/bert-base-uncased)、[bert_large_cased](https://huggingface.co/bert-large-cased)、[bert_large_cased_whole_word_masking](https://huggingface.co/bert-large-cased-whole-word-masking)、[bert_large_uncased](https://huggingface.co/bert-large-uncased)、[bert_large_uncased_whole_word_masking](https://huggingface.co/bert-large-uncased-whole-word-masking)：
- 针对特定应用场景开展微调工作，例如文本分类

**产品详情**
本预训练模型可针对特定应用场景开展进一步微调。本列表中提供的微调完成模型可直接部署至Databricks模型服务以实现即时使用，也可加载后用于微调或批量推理场景。如需了解更多细节，请安装本模型包并查阅各模型附带的模型卡片。