Update README.md

README.md

@@ -43,10 +43,10 @@ python3 preprocess.py --corpus_path corpora/lyric.txt \
 
 ```
 python3 pretrain.py --dataset_path lyric_dataset.pt \
-                    --pretrained_model_path models/cluecorpussmall_gpt2_seq512_model.bin-250000 \
+                    --pretrained_model_path models/cluecorpussmall_gpt2_seq1024_model.bin-250000 \
                     --vocab_path models/google_zh_vocab.txt \
-                    --output_model_path models/lyric_gpt2_base_model.bin \
-                    --config_path models/bert_base_config.json \
+                    --output_model_path models/lyric_gpt2_model.bin \
+                    --config_path models/gpt2/config.json \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
                     --total_steps 100000 --save_checkpoint_steps 10000 --report_steps 5000 \
                     --learning_rate 5e-5 --batch_size 64 \
@@ -58,7 +58,7 @@ python3 pretrain.py --dataset_path lyric_dataset.pt \
 Finally, we convert the pre-trained model into Huggingface's format:
 
 ```
-python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path lyric_gpt2_base_model.bin-100000 \
+python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path lyric_gpt2_model.bin-100000 \
                                                         --output_model_path pytorch_model.bin \
                                                         --layers_num 12
 ```