Hugging Face's logo

jinaai
/
jina-embedding-s-en-v1

Sentence Similarity
sentence-transformers
PyTorch
English
t5
finetuner
mteb
feature-extraction
custom_code
Eval Results
Inference Endpoints
Model card Files Community
bwang0911 commited on
Commit
bc9ceaa
•
1 Parent(s): 5037733

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -5
README.md CHANGED
@@ -30,10 +30,11 @@ With a compact size of just 35 million parameters,
30
  the model enables lightning-fast inference while still delivering impressive performance.
31
  Additionally, we provide the following options:
32
 
 
33
  - `jina-embedding-b-en-v1`: 110 million parameters.
34
- - `jina-embedding-l-en-v1`: 800 million parameters.
35
- - `jina-embedding-xl-en-v1`: 3 billion parameters (soon).
36
- - `jina-embedding-xxl-en-v1`: 11 billion parameters (soon).
37
 
38
  ## Data & Parameters
39
 
@@ -41,15 +42,16 @@ More info will be released together with the technique report.
41
 
42
  ## Metrics
43
 
44
- We compared the model against `all-minilm-l6-v2` from sbert and `text-embeddings-ada-002` from OpenAI:
45
 
46
  |Name|param |context|
47
  |------------------------------|-----|------|
48
  |all-minilm-l6-v2|33m |128|
49
- |all-mpnet--base-v2 |110m |128|
50
  |ada-embedding-002|Unknown/API based |8192|
51
  |jina-embedding-s-en-v1|35m |512|
52
  |jina-embedding-b-en-v1|110m |512|
 
53
 
54
 
55
  |Name|STS12|STS13|STS14|STS15|STS16|STS17|TRECOVID|Quora|SciFact|
@@ -59,6 +61,7 @@ We compared the model against `all-minilm-l6-v2` from sbert and `text-embeddings
59
  |ada-embedding-002|0.698|0.833|0.761|0.861|0.86 |0.903|0.685 |0.876|0.726 |
60
  |jina-embedding-s-en-v1|0.738|0.781|0.732|0.833|0.785|0.859|0.471 |0.852|0.567 |
61
  |jina-embedding-b-en-v1|0.736|0.804|0.745|0.844|0.793|0.873|0.481 |0.87|0.616 |
 
62
 
63
  For more tasks and metrics, please checkout [MTEB](https://huggingface.co/spaces/mteb/leaderboard) benchmark.
64
 
 
30
  the model enables lightning-fast inference while still delivering impressive performance.
31
  Additionally, we provide the following options:
32
 
33
+ - `jina-embedding-s-en-v1`: 35 million parameters **(you are here)**.
34
  - `jina-embedding-b-en-v1`: 110 million parameters.
35
+ - `jina-embedding-l-en-v1`: 330 million parameters.
36
+ - `jina-embedding-1b-en-v1`: 1.2 billion parameters, 10* bert-base size (soon).
37
+ - `jina-embedding-6b-en-v1`: 6 billion parameters 30* bert-base size(soon).
38
 
39
  ## Data & Parameters
40
 
 
42
 
43
  ## Metrics
44
 
45
+ We compared the model against `all-minilm-l6-v2`/`all-mpnet-base-v2` from sbert and `text-embeddings-ada-002` from OpenAI:
46
 
47
  |Name|param |context|
48
  |------------------------------|-----|------|
49
  |all-minilm-l6-v2|33m |128|
50
+ |all-mpnet-base-v2 |110m |128|
51
  |ada-embedding-002|Unknown/API based |8192|
52
  |jina-embedding-s-en-v1|35m |512|
53
  |jina-embedding-b-en-v1|110m |512|
54
+ |jina-embedding-l-en-v1|330m |512|
55
 
56
 
57
  |Name|STS12|STS13|STS14|STS15|STS16|STS17|TRECOVID|Quora|SciFact|
 
61
  |ada-embedding-002|0.698|0.833|0.761|0.861|0.86 |0.903|0.685 |0.876|0.726 |
62
  |jina-embedding-s-en-v1|0.738|0.781|0.732|0.833|0.785|0.859|0.471 |0.852|0.567 |
63
  |jina-embedding-b-en-v1|0.736|0.804|0.745|0.844|0.793|0.873|0.481 |0.87|0.616 |
64
+ |jina-embedding-l-en-v1|0.735|0.829|0.759|0.844|0.8|0.888|0.465 |0.876|0.645 |
65
 
66
  For more tasks and metrics, please checkout [MTEB](https://huggingface.co/spaces/mteb/leaderboard) benchmark.
67