tuhailong commited on
Commit
11730aa
1 Parent(s): b10af24

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -0
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: zh
3
+ tags:
4
+ - cross-encoder
5
+ datasets:
6
+ - dialogue
7
+ ---
8
+
9
+ # Data
10
+ train data is similarity sentence data from E-commerce dialogue, about 50w sentence pairs.
11
+
12
+ ## Model
13
+ model created by [sentence-tansformers](https://www.sbert.net/index.html),model struct is bi-encoder.
14
+ This model structure is as same as [tuhailong/cross_encoder_roberta-wwm-ext_v1](https://huggingface.co/tuhailong/cross_encoder_roberta-wwm-ext_v1),the difference is changing the epoch from 5 to 1, the performance is better in my dataset.
15
+
16
+ ### Usage
17
+ ```python
18
+ >>> from sentence_transformers.cross_encoder import CrossEncoder
19
+ >>> model = CrossEncoder(model_save_path, device="cuda", max_length=64)
20
+ >>> sentences = ["今天天气不错", "今天心情不错"]
21
+ >>> score = model.predict([sentences])
22
+ >>> print(score[0])
23
+ ```