tuhailong commited on
Commit
5b77b2c
1 Parent(s): f609e16

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -0
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: zh
3
+ tags:
4
+ - sbert
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
+
15
+ ### Usage
16
+ ```python
17
+ >>> from sentence_transformers import SentenceTransformer, util
18
+ >>> model = SentenceTransformer("tuhailong/bi_encoder_roberta-wwm-ext", device="cuda:1")
19
+ >>> model.max_seq_length=32
20
+ >>> sentences = ["今天天气不错", "今天心情不错"]
21
+ >>> embeddings1 = model.encode([sentences[0]], convert_to_tensor=True)
22
+ >>> embeddings2 = model.encode([sentences[1]], convert_to_tensor=True)
23
+ >>> scores = util.cos_sim(embeddings1, embeddings2).cpu().numpy()
24
+ >>> print(scores)
25
+ ```
26
+
27
+ ### PS
28
+ Because add the pooling layer and dense layer after model,has folders in model files. So here will
29
+ be additional files "1_Pooling-config.json", "2_Dense-config.json" and "2_Dense-pytorch_model.bin".
30
+ after download these files, rename them as "1_Pooling/config.json", "2_Dense/config.json" and "2_Dense/pytorch_model.bin".