|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
<br><br> |
|
|
|
<p align="center"> |
|
<img src="https://github.com/jina-ai/finetuner/blob/main/docs/_static/finetuner-logo-ani.svg?raw=true" alt="Finetuner logo: Finetuner helps you to create experiments in order to improve embeddings on search tasks. It accompanies you to deliver the last mile of performance-tuning for neural search applications." width="150px"> |
|
</p> |
|
|
|
|
|
<p align="center"> |
|
<b>The text embedding suit trained by Jina AI, Finetuner team.</b> |
|
</p> |
|
|
|
|
|
## Intented Usage & Model Info |
|
|
|
`jina-embedding-s-en-v1` is a language model that has been trained using Jina AI's Linnaeus-Clean dataset. |
|
This dataset consists of 380 million pairs of sentences, which include both query-document pairs. |
|
These pairs were obtained from various domains and were carefully selected through a thorough cleaning process. |
|
The Linnaeus-Full dataset, from which the Linnaeus-Clean dataset is derived, originally contained 1.6 billion sentence pairs. |
|
|
|
The model has a range of use cases, including information retrieval, semantic textual similarity, text reranking, and more. |
|
|
|
With a compact size of just 35 million parameters, |
|
the model enables lightning-fast inference while still delivering impressive performance. |
|
Additionally, we provide the following options: |
|
|
|
- `jina-embedding-b-en-v1`: 110 million parameters. |
|
- `jina-embedding-l-en-v1`: 800 million parameters. |
|
- `jina-embedding-xl-en-v1`: 3 billion parameters. |
|
- `jina-embedding-xxl-en-v1`: 11 billion parameters. |
|
|
|
## Data & Parameters |
|
|
|
More info will be released together with the technique report. |
|
|
|
## Metrics |
|
|
|
We compared the model against `all-minilm-l6-v2` from sbert and `text-embeddings-ada-002` from OpenAI: |
|
|
|
|FIELD1 |STS12|STS13|STS14|STS15|STS16|STS17|TRECOVID|Quora|SciFact|param |context length| |
|
|------------------------------|-----|-----|-----|-----|-----|-----|--------|-----|-------|---------|------| |
|
|all-minilm-l6-v2 |0.724|0.806|0.756|0.854|0.79 |0.876|0.473 |0.876|0.645 |33m |256| |
|
|all-mpnet--base-v2 |0.726|0.835|0.78 |0.857|0.8 |0.906|0.513 |0.875|0.656 |110m |256| |
|
|ada-embedding-002 |0.698|0.833|0.761|0.861|0.86 |0.903|0.685 |0.876|0.726 |Unknown |8024| |
|
|jina-embedding-small |0.738|0.781|0.732|0.833|0.785|0.859|0.471 |0.852|0.567 |35m |512| |
|
|
|
For more tasks and metrics, please checkout [MTEB](https://huggingface.co/spaces/mteb/leaderboard) benchmark. |
|
|
|
## Usage |
|
|
|
```python |
|
!pip install finetuner[text] |
|
import finetuner |
|
model = finetuner.get_model('jinaai/jina-embedding-s-en-v1') |
|
embeddings = model.encode(['sentence 1', 'sentence 2']) |
|
``` |
|
|
|
## Fine-tuning |
|
|
|
Please consider [Finetuner](https://github.com/jina-ai/finetuner). |
