minor fix
#7
by
KennethEnevoldsen
- opened
README.md
CHANGED
@@ -2618,7 +2618,7 @@ library_name: sentence-transformers
|
|
2618 |
|
2619 |
This is our [2DMSE](https://arxiv.org/abs/2402.14776) sentence embedding model. It supports the adaptive transformer layer and embedding size. Find out more in our [blog post](https://mixedbread.ai/blog/mxbai-embed-2d-large-v1).
|
2620 |
|
2621 |
-
TLDR:
|
2622 |
|
2623 |
## Quickstart
|
2624 |
|
|
|
2618 |
|
2619 |
This is our [2DMSE](https://arxiv.org/abs/2402.14776) sentence embedding model. It supports the adaptive transformer layer and embedding size. Find out more in our [blog post](https://mixedbread.ai/blog/mxbai-embed-2d-large-v1).
|
2620 |
|
2621 |
+
TLDR: 2D-🪆 allows you to shrink the model and the embeddings layer. Shrinking only the embeddings model yields competetive results to other models like [nomics embeddings model](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5). Shrinking the model to ~50% maintains upto 85% of the performance without further training.
|
2622 |
|
2623 |
## Quickstart
|
2624 |
|