first commit for the pre-trained pai-bert-base-zh model

README.md

@@ -1,3 +1,27 @@
 ---
+language: zh
+pipeline_tag: fill-mask
+# widget:
+# - text: "感冒需要吃[MASK]"
+# - text: "人类的[MASK]温是37度"
+tags:
+- bert
 license: apache-2.0
 ---
+## Alibaba PAI BERT Base Chinese
+
+This project provides Chinese pre-trained language models and various types of NLP tools. The models are pre-trained on the large-scale corpura hosted by the Alibaba PAI team. It is developed based on the EasyNLP framework: https://github.com/alibaba/EasyNLP  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} 
+} 
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "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,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ded5a5a1c7841dee6e47942f7b5bf2bcf6f73ff19197580f852f7f638f86b35
+size 411578458