turingevo commited on
Commit
2976eae
·
verified ·
1 Parent(s): a34ac62

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BAAI/bge-reranker-base
3
+ language:
4
+ - en
5
+ - zh
6
+ library_name: sentence-transformers
7
+ license: mit
8
+ pipeline_tag: text-classification
9
+ tags:
10
+ - mteb
11
+ - text-embeddings-inference
12
+ - openvino
13
+ - nncf
14
+ - 8-bit
15
+ model-index:
16
+ - name: bge-reranker-base
17
+ results:
18
+ - task:
19
+ type: Reranking
20
+ dataset:
21
+ name: MTEB CMedQAv1
22
+ type: C-MTEB/CMedQAv1-reranking
23
+ config: default
24
+ split: test
25
+ revision: None
26
+ metrics:
27
+ - type: map
28
+ value: 81.27206722525007
29
+ - type: mrr
30
+ value: 84.14238095238095
31
+ - task:
32
+ type: Reranking
33
+ dataset:
34
+ name: MTEB CMedQAv2
35
+ type: C-MTEB/CMedQAv2-reranking
36
+ config: default
37
+ split: test
38
+ revision: None
39
+ metrics:
40
+ - type: map
41
+ value: 84.10369934291236
42
+ - type: mrr
43
+ value: 86.79376984126984
44
+ - task:
45
+ type: Reranking
46
+ dataset:
47
+ name: MTEB MMarcoReranking
48
+ type: C-MTEB/Mmarco-reranking
49
+ config: default
50
+ split: dev
51
+ revision: None
52
+ metrics:
53
+ - type: map
54
+ value: 35.4600511272538
55
+ - type: mrr
56
+ value: 34.60238095238095
57
+ - task:
58
+ type: Reranking
59
+ dataset:
60
+ name: MTEB T2Reranking
61
+ type: C-MTEB/T2Reranking
62
+ config: default
63
+ split: dev
64
+ revision: None
65
+ metrics:
66
+ - type: map
67
+ value: 67.27728847727172
68
+ - type: mrr
69
+ value: 77.1315192743764
70
+ ---
71
+
72
+ This model is a quantized version of [`BAAI/bge-reranker-base`](https://huggingface.co/BAAI/bge-reranker-base) and is converted to the OpenVINO format. This model was obtained via the [nncf-quantization](https://huggingface.co/spaces/echarlaix/nncf-quantization) space with [optimum-intel](https://github.com/huggingface/optimum-intel).
73
+
74
+ First make sure you have `optimum-intel` installed:
75
+
76
+ ```bash
77
+ pip install optimum[openvino]
78
+ ```
79
+
80
+ To load your model you can do as follows:
81
+
82
+ ```python
83
+ from optimum.intel import OVModelForSequenceClassification
84
+
85
+ model_id = "turingevo/bge-reranker-base-openvino-8bit"
86
+ model = OVModelForSequenceClassification.from_pretrained(model_id)
87
+ ```