init

README.md

@@ -1,3 +1,32 @@
 ---
-license: apache-2.0
+language: 
+- zh
+license: "apache-2.0"
 ---
+
+## Chinese-MobileBERT
+> The original [Chinese-MobileBERT](https://github.com/ymcui/Chinese-MobileBERT) repository does not provide pytorch weights, here the weights are converted via the [model_convert](https://github.com/CycloneBoy/model_convert) repository.
+
+This repository is developed based on：https://github.com/ymcui/Chinese-MobileBERT
+
+You may also be interested in,
+- Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm
+- Chinese MacBERT: https://github.com/ymcui/MacBERT
+- Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA
+- Chinese XLNet: https://github.com/ymcui/Chinese-XLNet
+- Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer
+
+More resources by HFL: https://github.com/ymcui/HFL-Anthology
+
+## Citation
+If you find the technical report or resource is useful, please cite the following technical report in your paper.
+
+
+```
+@misc{cui-2022-chinese-mobilebert,
+  title={Chinese MobileBERT},
+  author={Cui, Yiming},
+  howpublished={\url{https://github.com/ymcui/Chinese-MobileBERT}},
+  year={2022}
+}
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "cycloneboy/chinese_mobilebert_base_f2",
+  "architectures": [
+    "MobileBertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "embedding_size": 768,
+  "trigram_input": true,
+  "use_bottleneck": true,
+  "intra_bottleneck_size": 144,
+  "use_bottleneck_attention": true,
+  "num_feedforward_networks": 2,
+  "normalization_type": "no_norm",
+  "pad_token_id": 0,
+  "model_type": "mobilebert",
+  "transformers_version": "4.6.0.dev0",
+  "classifier_activation": false,
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d4a2b2143d2d60b9b00758bfe1be04234d6065b2ace034a0bc680810282a3d
+size 110552707