all-MiniLM-L6-v2

Name: all-MiniLM-L6-v2
Author: sentence-transformers

by sentence-transformers

Fast, lightweight sentence embeddings for semantic similarity

251.0Mdl/month

5,257likes

23Mparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

sentence-transformers/all-MiniLM-L6-v2

Feature URI

mixpeek://text_extractor@v1/st_minilm_l6_v2

Overview

all-MiniLM-L6-v2 is a compact sentence embedding model that maps sentences and paragraphs to a 384-dimensional dense vector space. Despite its small size, it achieves strong performance on semantic textual similarity benchmarks.

On Mixpeek, MiniLM is the fastest text embedding option, ideal for real-time search and high-throughput indexing where speed matters more than maximum embedding quality.

Architecture

MiniLM-L6 distilled from a larger teacher model. 6 transformer layers, 384-dim hidden size. Uses mean pooling over token embeddings. Fine-tuned on 1B+ sentence pairs.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so all-MiniLM-L6-v2 runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // The vector name has to match a vector index on the collection.
          vectors: { "text-embedding": yourVector },
          payload: { source_key: "archive/2026/asset-00412" },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// text_extractor@v1 runs intfloat/multilingual-e5-large-instruct
// (1024-d) over a bucket, with no inference of your own.