Global AI chat room · 17 online now Join now
A
MODEL Listed

all-MiniLM-L6-v2

The all-MiniLM-L6-v2 is a lightweight, high-efficiency transformer model designed specifically for mapping sentences and paragraphs to a 384-dimensional dense vector space. Unlike larger LLMs, this model focuses on sentence-level embeddings, making it an ideal choice for developers building semantic search engines, clustering pipelines, or RAG (Retrieval-Augmented Generation) systems where low latency is critical. With only 22M parameters, it offers a strong balance between performance and resource consumption, allowing for deployment on edge devices or CPUs without significant overhead. It is optimized for sentence similarity tasks, effectively capturing semantic meaning to identify related texts even when keywords do not overlap.

sentence-transformerssentence similarity
View model source
01 / MODEL CARD

Model card

The all-MiniLM-L6-v2 is a lightweight, high-efficiency transformer model designed specifically for mapping sentences and paragraphs to a 384-dimensional dense vector space. Unlike larger LLMs, this model focuses on sentence-level embeddings, making it an ideal choice for developers building semantic search engines, clustering pipelines, or RAG (Retrieval-Augmented Generation) systems where low latency is critical. With only 22M parameters, it offers a strong balance between performance and resource consumption, allowing for deployment on edge devices or CPUs without significant overhead. It is optimized for sentence similarity tasks, effectively capturing semantic meaning to identify related texts even when keywords do not overlap.

Model typesentence similarity
Providersentence-transformers
Licenseapache-2.0
02 / FILES & VERSIONS

Model files and versions

Model cardModel description and metadata available in this entry
Listed
Source repositoryhttps://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
View model source
Version informationUse the source repository for the latest version
—
03 / DOWNLOAD

Download this model

We recommend using the ModelScope CLI or SDK. Install ModelScope first, then choose a full snapshot, single file, SDK or Git LFS workflow.

This entry points to Hugging Face. The commands use the matching ModelScope repository format; confirm that the repository exists on ModelScope before running them. Model repository: sentence-transformers/all-MiniLM-L6-v2
Install ModelScope

Install the CLI and SDK dependency before downloading.

pip install modelscope
Download the full model repository

Download the complete weights, configuration and model card.

modelscope download --model sentence-transformers/all-MiniLM-L6-v2
Download one file to a local directory

README.md is used as an example; replace it with another repository file when needed.

modelscope download --model sentence-transformers/all-MiniLM-L6-v2 README.md --local_dir ./dir
Download with the SDK

Useful in Python projects and automation scripts.

from modelscope import snapshot_download
model_dir = snapshot_download('sentence-transformers/all-MiniLM-L6-v2')
Clone with Git

Make sure Git LFS is installed correctly.

git lfs install
git clone https://www.modelscope.cn/sentence-transformers/all-MiniLM-L6-v2.git
Clone without downloading LFS blobs

Fetch the repository structure first, then pull large files when needed.

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/sentence-transformers/all-MiniLM-L6-v2.git
04 / WORKFLOW

How to use

  1. 01
    Step 1

    Read the model card and source information.

  2. 02
    Step 2

    Start with a small, non-sensitive evaluation.

  3. 03
    Step 3

    Review quality, licensing and usage limits.

  4. 04
    Step 4

    Adopt it only after validation.

05 / DISCUSSIONS

Discussions

Use this space to keep checking source information, usage experience and maintenance status.

Open source page
Email