Update README.md

README.md

@@ -39,26 +39,23 @@ The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tence
 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
+                      --seq_length 320 --data_processor 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 \
+                    --output_model_path models/ancient_chinese_gpt2_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
+                    --learning_rate 5e-4 --batch_size 32
 ```
 
 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 \
+python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path ancient_chinese_gpt2_model.bin-500000 \
                                                         --output_model_path pytorch_model.bin \
                                                         --layers_num 12
 ```
@@ -79,6 +76,4 @@ python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path ancie
   pages={241},
   year={2019}
 }
-
-胡韧奋,李绅,诸雨辰.基于深层语言模型的古汉语知识表示及自动断句研究[C].第十八届中国计算语言学大会（CCL 2019）.
 ```