namdp-ptit commited on
Commit
5102f69
1 Parent(s): 82dc9ae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -49,7 +49,7 @@ Get relevance scores (higher scores indicate more relevance):
49
  ```python
50
  from FlagEmbedding import FlagReranker
51
 
52
- reranker = FlagReranker('namdp/ViRanker',
53
  use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
54
 
55
  score = reranker.compute_score(['tỉnh nào có diện tích lớn nhất việt nam', 'nghệ an có diện tích lớn nhất việt nam'])
@@ -91,8 +91,8 @@ Get relevance scores (higher scores indicate more relevance):
91
  import torch
92
  from transformers import AutoModelForSequenceClassification, AutoTokenizer
93
 
94
- tokenizer = AutoTokenizer.from_pretrained('namdp/ViRanker')
95
- model = AutoModelForSequenceClassification.from_pretrained('namdp/ViRanker')
96
  model.eval()
97
 
98
  pairs = [
@@ -125,7 +125,7 @@ the [MS MMarco Passage Reranking - Vi - Dev](https://huggingface.co/datasets/uni
125
 
126
  | Model-Name | NDCG@3 | MRR@3 | NDCG@5 | MRR@5 | NDCG@10 | MRR@10 | Docs / Sec |
127
  |-----------------------------------------------------------------------------------------------------------------------------------------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
128
- | [namdp/ViRanker](https://huggingface.co/namdp/ViRanker) | **0.6685** | **0.6564** | 0.6842 | **0.6811** | 0.7278 | **0.6985** | 2.02
129
  | [itdainb/PhoRanker](https://huggingface.co/itdainb/PhoRanker) | 0.6625 | 0.6458 | **0.7147** | 0.6731 | **0.7422** | 0.6830 | **15**
130
  | [kien-vu-uet/finetuned-phobert-passage-rerank-best-eval](https://huggingface.co/kien-vu-uet/finetuned-phobert-passage-rerank-best-eval) | 0.0963 | 0.0883 | 0.1396 | 0.1131 | 0.1681 | 0.1246 | **15**
131
  | [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | 0.6087 | 0.5841 | 0.6513 | 0.6062 | 0.6872 | 0.62091 | 3.51
 
49
  ```python
50
  from FlagEmbedding import FlagReranker
51
 
52
+ reranker = FlagReranker('namdp-ptit/ViRanker',
53
  use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
54
 
55
  score = reranker.compute_score(['tỉnh nào có diện tích lớn nhất việt nam', 'nghệ an có diện tích lớn nhất việt nam'])
 
91
  import torch
92
  from transformers import AutoModelForSequenceClassification, AutoTokenizer
93
 
94
+ tokenizer = AutoTokenizer.from_pretrained('namdp-ptit/ViRanker')
95
+ model = AutoModelForSequenceClassification.from_pretrained('namdp-ptit/ViRanker')
96
  model.eval()
97
 
98
  pairs = [
 
125
 
126
  | Model-Name | NDCG@3 | MRR@3 | NDCG@5 | MRR@5 | NDCG@10 | MRR@10 | Docs / Sec |
127
  |-----------------------------------------------------------------------------------------------------------------------------------------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
128
+ | [namdp-ptit/ViRanker](https://huggingface.co/namdp-ptit/ViRanker) | **0.6685** | **0.6564** | 0.6842 | **0.6811** | 0.7278 | **0.6985** | 2.02
129
  | [itdainb/PhoRanker](https://huggingface.co/itdainb/PhoRanker) | 0.6625 | 0.6458 | **0.7147** | 0.6731 | **0.7422** | 0.6830 | **15**
130
  | [kien-vu-uet/finetuned-phobert-passage-rerank-best-eval](https://huggingface.co/kien-vu-uet/finetuned-phobert-passage-rerank-best-eval) | 0.0963 | 0.0883 | 0.1396 | 0.1131 | 0.1681 | 0.1246 | **15**
131
  | [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | 0.6087 | 0.5841 | 0.6513 | 0.6062 | 0.6872 | 0.62091 | 3.51