uer commited on
Commit
2ac081d
1 Parent(s): 007ba1e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  language: zh
3
  widget:
4
- - text: "北京上个月召开了两会"
5
 
6
  ---
7
 
@@ -48,8 +48,7 @@ python3 run_classifier.py --pretrained_model_path models/cluecorpussmall_roberta
48
  --train_path datasets/glyph/chinanews/train.tsv \
49
  --dev_path datasets/glyph/chinanews/dev.tsv \
50
  --output_model_path models/chinanews_classifier_model.bin \
51
- --learning_rate 3e-5 --batch_size 32 --epochs_num 3 --seq_length 512 \
52
- --embedding word_pos_seg --encoder transformer --mask fully_visible
53
  ```
54
 
55
  Finally, we convert the pre-trained model into Huggingface's format:
 
1
  ---
2
  language: zh
3
  widget:
4
+ - text: "这本书真的很不错"
5
 
6
  ---
7
 
 
48
  --train_path datasets/glyph/chinanews/train.tsv \
49
  --dev_path datasets/glyph/chinanews/dev.tsv \
50
  --output_model_path models/chinanews_classifier_model.bin \
51
+ --learning_rate 3e-5 --epochs_num 3 --batch_size 32 --seq_length 512
 
52
  ```
53
 
54
  Finally, we convert the pre-trained model into Huggingface's format: