Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
datasets: CLUECorpusSmall
|
4 |
widget:
|
5 |
- text: "最近一趟去北京的[MASK]几点发车"
|
@@ -172,7 +172,7 @@ python3 preprocess.py --corpus_path corpora/cluecorpussmall.txt \
|
|
172 |
python3 pretrain.py --dataset_path cluecorpussmall_word_seq512_dataset.pt \
|
173 |
--pretrained_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-1000000 \
|
174 |
--spm_model_path models/cluecorpussmall_spm.model \
|
175 |
-
--config_path models/bert/medium_config.json
|
176 |
--output_model_path models/cluecorpussmall_word_roberta_medium_seq512_model.bin \
|
177 |
--world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
|
178 |
--total_steps 250000 --save_checkpoint_steps 50000 --report_steps 10000 \
|
|
|
1 |
---
|
2 |
+
language: zh
|
3 |
datasets: CLUECorpusSmall
|
4 |
widget:
|
5 |
- text: "最近一趟去北京的[MASK]几点发车"
|
|
|
172 |
python3 pretrain.py --dataset_path cluecorpussmall_word_seq512_dataset.pt \
|
173 |
--pretrained_model_path models/cluecorpussmall_word_roberta_medium_seq128_model.bin-1000000 \
|
174 |
--spm_model_path models/cluecorpussmall_spm.model \
|
175 |
+
--config_path models/bert/medium_config.json \\
|
176 |
--output_model_path models/cluecorpussmall_word_roberta_medium_seq512_model.bin \
|
177 |
--world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 \
|
178 |
--total_steps 250000 --save_checkpoint_steps 50000 --report_steps 10000 \
|