From 939328111bf872954b48177eada5f06c05f79fce Mon Sep 17 00:00:00 2001
From: Junyi_Li <ljyduke@gmail.com>
Date: Thu, 19 Mar 2020 11:07:23 +0800
Subject: [PATCH] Create README.md

roberta_chinese_base card
---
 .../clue/roberta_chinese_base/README.md       | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 model_cards/clue/roberta_chinese_base/README.md

diff --git a/model_cards/clue/roberta_chinese_base/README.md b/model_cards/clue/roberta_chinese_base/README.md
new file mode 100644
index 00000000000..b0fcb124c1e
--- /dev/null
+++ b/model_cards/clue/roberta_chinese_base/README.md
@@ -0,0 +1,31 @@
+## roberta_chinese_base
+
+### Overview
+
+**Language model:** roberta-base
+**Model size:** 392M
+**Language:** Chinese
+**Training data:** [CLUECorpusSmall](https://github.com/CLUEbenchmark/CLUECorpus2020)
+**Eval data:** [CLUE dataset](https://github.com/CLUEbenchmark/CLUE)
+
+### Results
+
+For results on downstream tasks like text classification, please refer to [this repository](https://github.com/CLUEbenchmark/CLUE).
+
+### Usage
+
+**NOTE:** You have to call **BertTokenizer** instead of RobertaTokenizer !!!
+
+```
+import torch
+from transformers import BertTokenizer, BertModel
+tokenizer = BertTokenizer.from_pretrained("clue/roberta_chinese_base")
+roberta = BertModel.from_pretrained("clue/roberta_chinese_base")
+```
+
+### About CLUE benchmark
+
+Organization of Language Understanding Evaluation benchmark for Chinese: tasks & datasets, baselines, pre-trained Chinese models, corpus and leaderboard.
+
+Github: https://github.com/CLUEbenchmark
+Website: https://www.cluebenchmarks.com/