Update

README.md

@@ -1,12 +1,12 @@
 ---
 language: Chinese
 widget: 
-- question: "小王在哪上学？"
-- context: "小王在北京上学，他今年二十岁。"
+- text: "小王在哪上学？"
+  context: "小王在北京上学，他今年二十岁。"
 
 ---
 
-# Chinese RoBERTa Model
+# Chinese RoBERTa Base Model for QA
 
 ## Model description
 
@@ -44,12 +44,12 @@ python3 run_cmrc.py --dataset_path lyric_dataset.pt \
                     --embedding word_pos_seg --encoder transformer --mask fully_visible
 ```
 
-Finally, we convert the pre-trained model into Huggingface's format:
+Finally, we convert the fine-tuned model into Huggingface's format:
 
 ```
 python3 scripts/convert_roberta_extractive_qa_from_uer_to_huggingface.py --input_model_path extractive_qa_model.bin \
-                                                        --output_model_path pytorch_model.bin \
-                                                        --layers_num 12
+                                                                         --output_model_path pytorch_model.bin \
+                                                                         --layers_num 12
 ```
 
 ### BibTeX entry and citation info