uer commited on
Commit
638100a
1 Parent(s): d695f1a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -45,12 +45,12 @@ Models are fine-tuned by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent
45
  Taking the case of roberta-base-finetuned-chinanews-chinese
46
 
47
  ```
48
- python3 run_classifier.py --pretrained_model_path models/cluecorpussmall_roberta_base_seq512_model.bin-250000 \
49
- --vocab_path models/google_zh_vocab.txt \
50
- --train_path datasets/glyph/chinanews/train.tsv \
51
- --dev_path datasets/glyph/chinanews/dev.tsv \
52
- --output_model_path models/chinanews_classifier_model.bin \
53
- --learning_rate 3e-5 --epochs_num 3 --batch_size 32 --seq_length 512
54
  ```
55
 
56
  Finally, we convert the pre-trained model into Huggingface's format:
 
45
  Taking the case of roberta-base-finetuned-chinanews-chinese
46
 
47
  ```
48
+ python3 finetune/run_classifier.py --pretrained_model_path models/cluecorpussmall_roberta_base_seq512_model.bin-250000 \
49
+ --vocab_path models/google_zh_vocab.txt \
50
+ --train_path datasets/glyph/chinanews/train.tsv \
51
+ --dev_path datasets/glyph/chinanews/dev.tsv \
52
+ --output_model_path models/chinanews_classifier_model.bin \
53
+ --learning_rate 3e-5 --epochs_num 3 --batch_size 32 --seq_length 512
54
  ```
55
 
56
  Finally, we convert the pre-trained model into Huggingface's format: