uer
/

roberta-base-word-chinese-cluecorpussmall

Inference Endpoints

Model card Files Files and versions Community

uer commited on Mar 9, 2021

Commit

1380449

•

1 Parent(s): f9ddf5f

Update README.md

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -87,14 +87,14 @@ Stage1:
 ```
 python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --spm_model_path models/clue_6.model \
-                      --dataset_path cluecorpussmall_seq128_dataset.pt \
                       --processes_num 32 --seq_length 128 \
                       --dynamic_masking --target mlm
 ```
 ```
-python3 pretrain.py --dataset_path cluecorpussmall_seq128_dataset.pt \
-                    --spm_model_path models/clue_6.model \
                     --config_path models/bert/base_config.json \
                     --output_model_path models/cluecorpussmall_word_roberta_base_128.bin \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
@@ -108,16 +108,16 @@ Stage2:
 ```
 python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
-                      --spm_model_path models/clue_6.model \
-                      --dataset_path cluecorpussmall_seq512_dataset.pt \
                       --processes_num 32 --seq_length 512 \
                       --dynamic_masking --target mlm
 ```
 ```
-python3 pretrain.py --dataset_path cluecorpussmall_seq128_dataset.pt \
                     --pretrained_model_path models/cluecorpussmall_word_roberta_base_128.bin-1000000 \
-                    --spm_model_path models/clue_6.model \
                     --config_path models/bert/base_config.json \
                     --output_model_path models/cluecorpussmall_word_roberta_base_512.bin \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \

 ```
 python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
                       --spm_model_path models/clue_6.model \
+                      --dataset_path cluecorpussmall_word_seq128_dataset.pt \
                       --processes_num 32 --seq_length 128 \
                       --dynamic_masking --target mlm
 ```
 ```
+python3 pretrain.py --dataset_path cluecorpussmall_word_seq128_dataset.pt \
+                    --spm_model_path models/cluecorpussmall_spm.model \
                     --config_path models/bert/base_config.json \
                     --output_model_path models/cluecorpussmall_word_roberta_base_128.bin \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
 ```
 python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
+                      --spm_model_path models/cluecorpussmall_spm.model \
+                      --dataset_path cluecorpussmall_word_seq512_dataset.pt \
                       --processes_num 32 --seq_length 512 \
                       --dynamic_masking --target mlm
 ```
 ```
+python3 pretrain.py --dataset_path cluecorpussmall_word_seq512_dataset.pt \
                     --pretrained_model_path models/cluecorpussmall_word_roberta_base_128.bin-1000000 \
+                    --spm_model_path models/cluecorpussmall_spm.model \
                     --config_path models/bert/base_config.json \
                     --output_model_path models/cluecorpussmall_word_roberta_base_512.bin \
                     --world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \