bwang0911 commited on
Commit
d7aff03
1 Parent(s): 3e36508

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -7
README.md CHANGED
@@ -44,7 +44,7 @@ This model has 137 million parameters, which enables fast and memory efficient i
44
  Additionally, we provide the following embedding models:
45
 
46
  - [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters.
47
- - [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters **(you are here)**.
48
  - [`jina-embeddings-v2-base-zh`](https://huggingface.co/jinaai/jina-embeddings-v2-base-zh): Chinese-English Bilingual embeddings.
49
  - [`jina-embeddings-v2-base-de`](https://huggingface.co/jinaai/jina-embeddings-v2-base-de): German-English Bilingual embeddings.
50
  - [`jina-embeddings-v2-base-es`](https://huggingface.co/jinaai/jina-embeddings-v2-base-es): Spanish-English Bilingual embeddings (soon).
@@ -148,6 +148,7 @@ embeddings = model.encode(
148
  ]
149
  )
150
  print(cos_sim(embeddings[0], embeddings[1]))
 
151
  ```
152
 
153
  If you only want to handle shorter sequence, such as 2k, pass the `max_length` parameter to the `encode` function:
@@ -159,14 +160,11 @@ embeddings = model.encode(
159
  )
160
  ```
161
 
162
- ## Fully-managed Embeddings Service
163
-
164
- Alternatively, you can use Jina AI's [Embeddings platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models.
165
-
166
  ## Plans
167
 
168
- The development of new bilingual models is currently underway. We will be targeting mainly the German and Spanish languages.
169
- The upcoming models will be called `jina-embeddings-v2-small-de/es`.
 
170
 
171
  ## Contact
172
 
 
44
  Additionally, we provide the following embedding models:
45
 
46
  - [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters.
47
+ - [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters.
48
  - [`jina-embeddings-v2-base-zh`](https://huggingface.co/jinaai/jina-embeddings-v2-base-zh): Chinese-English Bilingual embeddings.
49
  - [`jina-embeddings-v2-base-de`](https://huggingface.co/jinaai/jina-embeddings-v2-base-de): German-English Bilingual embeddings.
50
  - [`jina-embeddings-v2-base-es`](https://huggingface.co/jinaai/jina-embeddings-v2-base-es): Spanish-English Bilingual embeddings (soon).
 
148
  ]
149
  )
150
  print(cos_sim(embeddings[0], embeddings[1]))
151
+ >>> 0.7230249
152
  ```
153
 
154
  If you only want to handle shorter sequence, such as 2k, pass the `max_length` parameter to the `encode` function:
 
160
  )
161
  ```
162
 
 
 
 
 
163
  ## Plans
164
 
165
+ 1. Bilingual embedding models supporting more European & Asian languages, including Spanish, French, Italian and Japanese.
166
+ 2. Multimodal embedding models enable Multimodal RAG applications.
167
+ 3. High-performt rerankers.
168
 
169
  ## Contact
170