Update README.md

README.md

@@ -114,7 +114,7 @@ python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --vocab_path models/google_zh_vocab.txt \
                       --dataset_path cluecorpussmall_seq128_dataset.pt \
                       --processes_num 32 --seq_length 128 \
-                      --dynamic_masking --target mlm
+                      --dynamic_masking --data_processor mlm
 ```
 
 ```
@@ -125,7 +125,7 @@ python3 pretrain.py --dataset_path cluecorpussmall_seq128_dataset.pt \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
                     --total_steps 1000000 --save_checkpoint_steps 100000 --report_steps 50000 \
                     --learning_rate 1e-4 --batch_size 64 \
-                    --embedding word_pos_seg --encoder transformer --mask fully_visible --target mlm --tie_weights
+                    --data_processor mlm --target mlm
 ```
 
 Stage2:
@@ -135,19 +135,19 @@ python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --vocab_path models/google_zh_vocab.txt \
                       --dataset_path cluecorpussmall_seq512_dataset.pt \
                       --processes_num 32 --seq_length 512 \
-                      --dynamic_masking --target mlm
+                      --dynamic_masking --data_processor mlm
 ```
 
 ```
 python3 pretrain.py --dataset_path cluecorpussmall_seq512_dataset.pt \
-                    --pretrained_model_path models/cluecorpussmall_roberta_medium_seq128_model.bin-1000000 \
                     --vocab_path models/google_zh_vocab.txt \
+                    --pretrained_model_path models/cluecorpussmall_roberta_medium_seq128_model.bin-1000000 \
                     --config_path models/bert/medium_config.json \
                     --output_model_path models/cluecorpussmall_roberta_medium_seq512_model.bin \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
                     --total_steps 250000 --save_checkpoint_steps 50000 --report_steps 10000 \
                     --learning_rate 5e-5 --batch_size 16 \
-                    --embedding word_pos_seg --encoder transformer --mask fully_visible --target mlm --tie_weights
+                    --data_processor mlm --target mlm
 ```
 
 Finally, we convert the pre-trained model into Huggingface's format:
@@ -155,7 +155,7 @@ Finally, we convert the pre-trained model into Huggingface's format:
 ```
 python3 scripts/convert_bert_from_uer_to_huggingface.py --input_model_path models/cluecorpussmall_roberta_medium_seq512_model.bin-250000 \                                                        
                                                         --output_model_path pytorch_model.bin \
-                                                        --layers_num 8 --target mlm
+                                                        --layers_num 8 --type mlm
 ```
 
 ### BibTeX entry and citation info
@@ -198,7 +198,7 @@ python3 scripts/convert_bert_from_uer_to_huggingface.py --input_model_path model
 [4_128]:https://huggingface.co/uer/chinese_roberta_L-4_H-128
 [4_256]:https://huggingface.co/uer/chinese_roberta_L-4_H-256
 [4_512]:https://huggingface.co/uer/chinese_roberta_L-4_H-512
-[4_768]:https://huggingface.co/uer/chinese_roberta_L-4_H-768  
+[4_768]:https://huggingface.co/uer/chinese_roberta_L-4_H-768
 [6_128]:https://huggingface.co/uer/chinese_roberta_L-6_H-128
 [6_256]:https://huggingface.co/uer/chinese_roberta_L-6_H-256
 [6_512]:https://huggingface.co/uer/chinese_roberta_L-6_H-512