Hugging Face's logo

AITeamVN
/
Vietnamese_Embedding

Sentence Similarity
sentence-transformers
ONNX
Safetensors
Vietnamese
xlm-roberta
Embedding
text-embeddings-inference
Model card Files
xet
Community
3
AITeamVN commited on
Commit
402542b
·
verified ·
1 Parent(s): 0386e44

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -20,13 +20,6 @@ Vietnamese_Embedding is an embedding model fine-tuned from the BGE-M3 model (htt
20
  * The model was trained with a maximum sequence length of 2048.
21
 
22
 
23
- | Model | Accuracy@1 | Accuracy@3 | Accuracy@5 | Accuracy@10 | Accuracy@100 | MRR@10 |
24
- |----------------------|------------|------------|------------|-------------|-------------|--------------|
25
- | Vietnamese_Embedding | 0.7274 | 0.8992 | 0.9305 | 0.9568 | 0.9922 | 0.8181 |
26
- | Vietnamese-bi-encoder | 0.7109 | 0.8680 | 0.9014 | 0.9299 | 0.9772 | 0.7951 |
27
- | BGE-M3 | 0.5682 | 0.7728 | 0.8382 | 0.8921 | 0.9772 | 0.6822 |
28
-
29
-
30
  ## Usage
31
 
32
  ```python
@@ -50,4 +43,11 @@ array([[0.6621206 , 0.33066636],
50
 
51
  ### Evaluation:
52
 
53
- - Dataset: Entire training dataset of Legal Zalo 2021. Our model did not train on this dataset.
 
 
 
 
 
 
 
 
20
  * The model was trained with a maximum sequence length of 2048.
21
 
22
 
 
 
 
 
 
 
 
23
  ## Usage
24
 
25
  ```python
 
43
 
44
  ### Evaluation:
45
 
46
+ - Dataset: Entire training dataset of Legal Zalo 2021. Our model did not train on this dataset.
47
+
48
+ | Model | Accuracy@1 | Accuracy@3 | Accuracy@5 | Accuracy@10 | Accuracy@100 | MRR@10 |
49
+ |----------------------|------------|------------|------------|-------------|-------------|--------------|
50
+ | Vietnamese_Embedding | 0.7274 | 0.8992 | 0.9305 | 0.9568 | 0.9922 | 0.8181 |
51
+ | Vietnamese-bi-encoder | 0.7109 | 0.8680 | 0.9014 | 0.9299 | 0.9772 | 0.7951 |
52
+ | BGE-M3 | 0.5682 | 0.7728 | 0.8382 | 0.8921 | 0.9772 | 0.6822 |
53
+