init

README.md

@@ -1,3 +1,24 @@
 ---
-license: apache-2.0
+language: 
+- zh
+tags:
+- bert
+license: "apache-2.0"
 ---
+
+# Please use 'Bert' related functions to load this model!
+
+## Chinese small pre-trained model MiniRBT
+For further accelerating Chinese natural language processing, we launched a Chinese small pre-training model MiniRBT based on the self-developed knowledge distillation tool TextBrewer, combined with Whole Word Masking technology and Knowledge Distillation technology.
+
+This repository is developed based on：https://github.com/iflytek/ta-minilm-demo
+
+You may also interested in,
+- Chinese LERT: https://github.com/ymcui/LERT
+- Chinese PERT: https://github.com/ymcui/PERT
+- 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/iflytek/HFL-Anthology

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "D:\\order\\TA_model\\commit\\MiniRBT-H256",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.22.2",
+  "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 sha256:6728ca573fd5197f28198eb7e6119a76e4d5dc626f953fca8c0dc5ba2798f9fc
+size 41514155

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3302d877d3565b8b01c65be9aa862977a1cc58431163c190b2b2b38c4aa168a8
+size 63787792