Skip to content

Issue on docs #350

Open
Open
@curvedinf

Description

@curvedinf

Path: /vector/features/embeddingmodels

[mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1)	1024	512	64.68
[WhereIsAI/UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1)	1024	512	64.64
[BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5)	1024	512	64.23
[BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5)	768	512	63.55
[BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)	384	512	62.17
[sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)	384	256	56.26
[BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3)	1024	8192	*
[google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased)	768	512	38.33

I'd like more long token limit options with higher performance. 8k tokens is my minimum for consideration. Something like these would be ideal:

https://huggingface.co/dunzhang/stella_en_400M_v5
https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

      Participants

      @curvedinf

      Issue actions

        Issue on docs · Issue #350 · upstash/docs