Update README.md
Browse files
README.md
CHANGED
@@ -2598,4 +2598,32 @@ model-index:
|
|
2598 |
value: 85.91093266751166
|
2599 |
- type: max_f1
|
2600 |
value: 77.97001153402537
|
2601 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2598 |
value: 85.91093266751166
|
2599 |
- type: max_f1
|
2600 |
value: 77.97001153402537
|
2601 |
+
---
|
2602 |
+
|
2603 |
+
# Sionic AI Embedding API v2
|
2604 |
+
|
2605 |
+
## About Sionic AI
|
2606 |
+
|
2607 |
+
Homepage : https://sionic.ai/
|
2608 |
+
|
2609 |
+
Sionic AI delivers more accessible and cost-effective AI technology addressing the various needs to boost productivity and drive innovation.
|
2610 |
+
|
2611 |
+
The Large Language Model (LLM) is not for research and experimentation. We offer solutions that leverage LLM to add value to your business. Anyone can easily train and control AI.
|
2612 |
+
|
2613 |
+
You can try our product [here](https://www.s9m.ai) for free!
|
2614 |
+
|
2615 |
+
## How to get embeddings
|
2616 |
+
|
2617 |
+
TBU
|
2618 |
+
|
2619 |
+
## Massive Text Embedding Benchmark (MTEB) Evaluation
|
2620 |
+
|
2621 |
+
Both versions of Sionic AI's embedding show the state-of-the-art performances on the MTEB!
|
2622 |
+
|
2623 |
+
| Model Name | Dimension | Sequence Length | Average (56) |
|
2624 |
+
|:-----------------------------------------------------------------------:|:---------:|:---------------:|:------------:|
|
2625 |
+
| [sionic-ai/sionic-ai-v2](https://huggingface.co/sionic-ai/sionic-ai-v2) | 3072 | 512 | **65.23** |
|
2626 |
+
| [sionic-ai/sionic-ai-v1](https://huggingface.co/sionic-ai/sionic-ai-v1) | 2048 | 512 | 64.92 |
|
2627 |
+
| [bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | 64.23 |
|
2628 |
+
| [gte-large-en](https://huggingface.co/barisaydin/gte-large) | 1024 | 512 | 63.13 |
|
2629 |
+
| [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings/types-of-embedding-models) | 1536 | 8191 | 60.99 |
|