# Embeddig model information **URL:** \ **Category:** Beginners\ **Created:** [October 20, 2024, 11:32am UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923 "2024-10-20T11:32:06Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![gsvc](https://avatars.discourse-cdn.com/v4/letter/g/73ab20/32.png) [@gsvc](https://discuss.huggingface.co/u/gsvc)\ **Post date:** [October 20, 2024, 11:32am UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/1 "2024-10-20T11:32:06Z")
Hi Guys, Is there any embedding model from the huggingface where the size of the `returned embedding` with dimension `1536` as openai’s `text-embedding-ada-002`? ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [October 20, 2024, 12:00pm UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/2 "2024-10-20T12:00:58Z")
There are many models that are too long or too short for that purpose. > **[MTEB Leaderboard - a Hugging Face Space by mteb](https://huggingface.co/spaces/mteb/leaderboard)** > > Discover amazing ML apps made by the community > **[OpenAI vs Open-Source Multilingual Embedding Models](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05)** > > Choosing the model that works best for your data ---
**Author:** ![gsvc](https://avatars.discourse-cdn.com/v4/letter/g/73ab20/32.png) [@gsvc](https://discuss.huggingface.co/u/gsvc)\ **Post date:** [October 20, 2024, 12:06pm UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/3 "2024-10-20T12:06:42Z")
Hey @John6666 . I have seen that blog. But the problem is that I dont have openai api keys. But I created my `faiss_index` with an dimension `1536`. So from that blog i cause mistral’s model. But that model was very large where my streamlit application gets failed to download the model. Is there any other model? I have `jina ai` where the embedding dimension was 786. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [October 20, 2024, 12:14pm UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/4 "2024-10-20T12:14:27Z")
I don’t know much about it, I’d have to do a search, but what about BAAI, dimension seems right and I don’t think it’s big. > **[Retrieval in LangChain: Part 3— Text Embeddings and Vector Stores](https://medium.com/@sushmithabhanu24/retrieval-in-langchain-part-3-text-embeddings-and-vector-stores-f8be7fb0508a)** > > Welcome to the third article of the series, where we explore Retrieval in LangChain. If you haven't checked out the previous articles from… Sorry, dimension is wrong… 1536 dimension models > **[Alibaba-NLP/gte-Qwen2-1.5B-instruct · Hugging Face](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. > **[izhx/udever-bloom-1b1 · Hugging Face](https://huggingface.co/izhx/udever-bloom-1b1)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. Simply ordered by popularity > **[Models - Hugging Face](https://huggingface.co/models?other=text-embeddings-inference&sort=trending)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. After all, it may be easiest to find from the MTEB leaderboard. ---
**Author:** ![gsvc](https://avatars.discourse-cdn.com/v4/letter/g/73ab20/32.png) [@gsvc](https://discuss.huggingface.co/u/gsvc)\ **Post date:** [October 20, 2024, 2:26pm UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/5 "2024-10-20T14:26:44Z")
Hey @John6666 . I have a doub that we cant use different embedding model in the time of vector store creation and in the inference. I mean i created faiss\_index where i used openai embedding model where in the inference time i used other embedding models which matches the openai’s dimension size. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [October 20, 2024, 10:42pm UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/6 "2024-10-20T22:42:47Z")
It’s not impossible to adjust to a lower dimension, apparently… > **[Introduction to Dimensionality Reduction - GeeksforGeeks](https://www.geeksforgeeks.org/dimensionality-reduction/)** > > A Computer Science portal for geeks. It contains well written, well thought and well explained computer science and programming articles, quizzes and practice/competitive programming/company interview Questions. > ---
**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\ **Post date:** [October 21, 2024, 12:17pm UTC](https://discuss.huggingface.co/t/embeddig-model-information/112923/7 "2024-10-21T12:17:38Z")
Closed on October 21, 2024, 12:17pm UTC This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.