sentence-transformers/paraphrase-MiniLM-L6-v2 cover image

sentence-transformers/paraphrase-MiniLM-L6-v2

We present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.

We present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.

Public
$0.005 / Mtoken
512

OpenAI-compatible HTTP API

DeepInfra supports the OpenAI embeddings API. The following creates an embedding vector representing the input text

curl "https://api.deepinfra.com/v1/openai/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
  -d '{
    "input": "The food was delicious and the waiter...",
    "model": "sentence-transformers/paraphrase-MiniLM-L6-v2",
    "encoding_format": "float"
  }'

which will return something similar to

{
  "object":"list",
  "data":[
    {
      "object": "embedding",
      "index":0,
      "embedding":[
        -0.010480394586920738,
        -0.0026091758627444506
        ...
        0.031979579478502274,
        0.02021978422999382
      ]
    }
  ],
  "model": "sentence-transformers/paraphrase-MiniLM-L6-v2",
  "usage": {
    "prompt_tokens":12,
    "total_tokens":12
  }
}

Input fields

modelstring

model name


inputarray

sequences to embed


encoding_formatstring

format used when encoding

Default value: "float"

Allowed values: float

Input Schema

Output Schema