Update README.md

README.md

@@ -45,7 +45,7 @@ Training data contains 700,000 Chinese couplets which are collected by [couplet-
 
 ## Training procedure
 
-Models are pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud TI-ONE](https://cloud.tencent.com/product/tione/). We pre-train 25,000  steps with a sequence length of 64.
+The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud TI-ONE](https://cloud.tencent.com/product/tione/). We pre-train 25,000 steps with a sequence length of 64.
 
 ```
 python3 preprocess.py --corpus_path corpora/couplet.txt \
@@ -58,7 +58,7 @@ python3 preprocess.py --corpus_path corpora/couplet.txt \
 python3 pretrain.py --dataset_path couplet_dataset.pt \
 				    --vocab_path models/google_zh_vocab.txt \
 					--output_model_path models/couplet_gpt2_base_model.bin \
-					--config_path models/bert_base_config.json \
+					--config_path models/gpt2/config.json \
 					--world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
 					--total_steps 25000 --save_checkpoint_steps 5000 --report_steps 1000 \
 					--learning_rate 5e-4 --batch_size 64 \
@@ -88,5 +88,4 @@ python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path coupl
 }
 ```
 
-[couplet]: https://huggingface.co/uer/gpt2-chinese-couplet
-
+[couplet]: https://huggingface.co/uer/gpt2-chinese-couplet