takarajordan commited on
Commit
6096590
·
verified ·
1 Parent(s): 4e9d98f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -9
README.md CHANGED
@@ -11,10 +11,14 @@ tags:
11
  pipeline_tag: sentence-similarity
12
  ---
13
 
14
- # e5-small-v2-distilled Model Card
 
15
 
16
- This [Model2Vec](https://github.com/MinishLab/model2vec) model is a distilled version of the [intfloat/e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) Sentence Transformer. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical.
17
 
 
 
 
18
 
19
  ## Installation
20
 
@@ -24,13 +28,12 @@ pip install model2vec
24
  ```
25
 
26
  ## Usage
 
27
  Load this model using the `from_pretrained` method:
28
  ```python
29
  from model2vec import StaticModel
30
-
31
  # Load a pretrained Model2Vec model
32
  model = StaticModel.from_pretrained("takara-ai/e5-small-v2-static-distilled")
33
-
34
  # Compute text embeddings
35
  embeddings = model.encode(["Example sentence"])
36
  ```
@@ -38,13 +41,10 @@ embeddings = model.encode(["Example sentence"])
38
  Alternatively, you can distill your own model using the `distill` method:
39
  ```python
40
  from model2vec.distill import distill
41
-
42
  # Choose a Sentence Transformer model
43
  model_name = "BAAI/bge-base-en-v1.5"
44
-
45
  # Distill the model
46
  m2v_model = distill(model_name=model_name, pca_dims=256)
47
-
48
  # Save the model
49
  m2v_model.save_pretrained("m2v_model")
50
  ```
@@ -62,7 +62,7 @@ It works by passing a vocabulary through a sentence transformer model, then redu
62
  - [Model2Vec Results](https://github.com/MinishLab/model2vec?tab=readme-ov-file#results)
63
  - [Model2Vec Tutorials](https://github.com/MinishLab/model2vec/tree/main/tutorials)
64
 
65
- ## Library Authors
66
 
67
  Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled).
68
 
@@ -76,4 +76,9 @@ Please cite the [Model2Vec repository](https://github.com/MinishLab/model2vec) i
76
  year = {2024},
77
  url = {https://github.com/MinishLab/model2vec},
78
  }
79
- ```
 
 
 
 
 
 
11
  pipeline_tag: sentence-similarity
12
  ---
13
 
14
+ <img src="https://takara.ai/images/logo-24/TakaraAi.svg" width="200" alt="Takara.ai Logo" />
15
+ From the Frontier Research Team at **Takara.ai** we present a distilled version of the e5-small-v2 model using Model2Vec technology for ultra-fast text embeddings.
16
 
17
+ ---
18
 
19
+ # e5-small-v2-distilled
20
+
21
+ This [Model2Vec](https://github.com/MinishLab/model2vec) model is a distilled version of the [intfloat/e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) Sentence Transformer. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical.
22
 
23
  ## Installation
24
 
 
28
  ```
29
 
30
  ## Usage
31
+
32
  Load this model using the `from_pretrained` method:
33
  ```python
34
  from model2vec import StaticModel
 
35
  # Load a pretrained Model2Vec model
36
  model = StaticModel.from_pretrained("takara-ai/e5-small-v2-static-distilled")
 
37
  # Compute text embeddings
38
  embeddings = model.encode(["Example sentence"])
39
  ```
 
41
  Alternatively, you can distill your own model using the `distill` method:
42
  ```python
43
  from model2vec.distill import distill
 
44
  # Choose a Sentence Transformer model
45
  model_name = "BAAI/bge-base-en-v1.5"
 
46
  # Distill the model
47
  m2v_model = distill(model_name=model_name, pca_dims=256)
 
48
  # Save the model
49
  m2v_model.save_pretrained("m2v_model")
50
  ```
 
62
  - [Model2Vec Results](https://github.com/MinishLab/model2vec?tab=readme-ov-file#results)
63
  - [Model2Vec Tutorials](https://github.com/MinishLab/model2vec/tree/main/tutorials)
64
 
65
+ ## Original Credits
66
 
67
  Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled).
68
 
 
76
  year = {2024},
77
  url = {https://github.com/MinishLab/model2vec},
78
  }
79
+ ```
80
+
81
+ ---
82
+ For research inquiries and press, please reach out to [email protected]
83
+
84
+ > 人類を変革する