From 275efd336f5fb5e434bae3774a23b5977228f6ac Mon Sep 17 00:00:00 2001 From: Mike Jang Date: Wed, 21 Feb 2024 10:04:58 -0800 Subject: [PATCH] Update qdrant-landing/content/blog/binary-quantization-openai.md --- qdrant-landing/content/blog/binary-quantization-openai.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qdrant-landing/content/blog/binary-quantization-openai.md b/qdrant-landing/content/blog/binary-quantization-openai.md index 552bb9999..10f9e2b71 100644 --- a/qdrant-landing/content/blog/binary-quantization-openai.md +++ b/qdrant-landing/content/blog/binary-quantization-openai.md @@ -38,7 +38,7 @@ You can also try out these techniques with the following Jupyter notebook: [Open As the technology of embedding models has advanced, demand has grown. Users are looking more for powerful and efficient text-embedding models. OpenAI's Ada-003 embeddings offer state-of-the-art performance on a wide range of NLP tasks, including those noted in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) and [MIRACL](https://openai.com/blog/new-embedding-models-and-api-updates). - A notable feature of these models is their multi-lingual support, enabling encoding in over 100 languages, which addresses the needs of applications with diverse language requirements. Impressively, the transition from text-embedding-ada-002 to text-embedding-3-large has observed a significant jump in performance scores (from 31.4% to 54.9% on MIRACL), reflecting substantial advancements. +These models include multilingual support in over 100 languages. The transition from text-embedding-ada-002 to text-embedding-3-large has led to a significant jump in performance scores (from 31.4% to 54.9% on MIRACL). #### Matryoshka Representation Learning