first commit for pai-dkplm-finincial-base-zh model

README.md

@@ -1,3 +1,37 @@
 ---
+language: zh
+pipeline_tag: fill-mask
+widget:
+- text: "[MASK]"
+- text: "人类的[MASK]温是37度"
+tags:
+- bert
 license: apache-2.0
 ---
+## Chinese DKPLM (Decomposable Knowledge-enhanced Pre-trained Language Model) for the financial domain
+For Chinese natural language processing in specific domains, we provide **Chinese DKPLM (Decomposable Knowledge-enhanced Pre-trained Language Model)** for the financial domain named **pai-dkplm-bert-zh**, from our AAAI 2021 paper named **DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding**.
+
+This repository is developed based on the EasyNLP framework: [https://github.com/alibaba/EasyNLP](https://github.com/alibaba/EasyNLP ) developed by the Alibaba PAI team.
+
+## Citation
+If you find the resource is useful, please cite the following papers in your work.
+
+- For the EasyNLP framework:
+```
+@article{easynlp, 
+title = {EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing},   			publisher = {arXiv}, 
+  author = {Wang, Chengyu and Qiu, Minghui and Zhang, Taolin and Liu, Tingting and Li, Lei and Wang, Jianing and Wang, Ming and Huang, Jun and Lin, Wei}, 
+  url = {https://arxiv.org/abs/2205.00258}, 
+  year = {2022} 
+} 
+```
+- For DKPLM:
+```
+@article{dkplm, 
+  title = {DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding}, 
+  author = {Zhang, Taolin and Wang, Chengyu and Hu, Nan and Qiu, Minghui and Tang, Chengguang and He, Xiaofeng and Huang, Jun}, 
+  url = {https://arxiv.org/abs/2112.01047},   			
+  publisher = {arXiv}, 
+  year = {2021} 
+} 
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/home/ruyaoXu/Fin/FinBERT/bert-base-chinese",
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39dbae2574c99747a681e56be672d1ed249cff62fd52ed9fb0a97fe18a5dc65f
+size 411619295