Update README.md

README.md

@@ -36,30 +36,30 @@ Training data contains 3,000,000 ancient Chinese which are collected by [daizhig
 The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud](https://cloud.tencent.com/). We pre-train 500,000 steps with a sequence length of 320. We use extended vocabulary to handle out-of-vocabulary words. The Chinese character that occurs greater than or equal to 100 in ancient Chinese corpus is added to the vocabulary.
 
 ```
-python3 preprocess.py --corpus_path corpora/ancient_chinese.txt \\
-                      --vocab_path models/google_zh_vocab.txt \\
-                      --dataset_path ancient_chinese_dataset.pt --processes_num 16 \\
+python3 preprocess.py --corpus_path corpora/ancient_chinese.txt \
+                      --vocab_path models/google_zh_vocab.txt \
+                      --dataset_path ancient_chinese_dataset.pt --processes_num 16 \
                       --seq_length 320 --target lm
 ```
 
 ```
-python3 pretrain.py --dataset_path ancient_chinese_dataset.pt \\
-                    --vocab_path models/google_zh_vocab.txt \\
-                    --config_path models/bert_base_config.json \\
-                    --output_model_path models/ancient_chinese_base_model.bin \\
-                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \\
-                    --total_steps 500000 --save_checkpoint_steps 100000 --report_steps 10000 \\
-                    --learning_rate 5e-4 --batch_size 32 \\
-                    --embedding word_pos --remove_embedding_layernorm \\
-                    --encoder transformer --mask causal --layernorm_positioning pre \\
-                    --target lm --tie_weight
+python3 pretrain.py --dataset_path ancient_chinese_dataset.pt \
+                    --vocab_path models/google_zh_vocab.txt \
+                    --config_path models/bert_base_config.json \
+                    --output_model_path models/ancient_chinese_base_model.bin \
+                    --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
+                    --total_steps 500000 --save_checkpoint_steps 100000 --report_steps 10000 \
+                    --learning_rate 5e-4 --batch_size 32 \
+                    --embedding word_pos --remove_embedding_layernorm \
+                    --encoder transformer --mask causal --layernorm_positioning pre \
+                    --target lm --tie_weights
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format:
 
 ```
-python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path ancient_chinese_base_model.bin-500000 \\
-                                                        --output_model_path pytorch_model.bin \\
+python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path ancient_chinese_base_model.bin-500000 \
+                                                        --output_model_path pytorch_model.bin \
                                                         --layers_num 12
 ```