Prediction

lucataco/bge-m3:3af6c861

Model

lucataco/bge-m3:3af6c861

ID

tdyhblrbhppnc7cf45f5jwvavu

Status

Succeeded

Source

Web

Hardware

T4

Total duration

2m 53s

Created

about 1 year ago

Input

max_length: 4096
sentences_1: What is BGE M3? Defination of BM25
sentences_2: BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction. BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document
embedding_type: dense

{
  "max_length": 4096,
  "sentences_1": "What is BGE M3?\nDefination of BM25",
  "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
  "embedding_type": "dense"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/bge-m3:3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
  {
    input: {
      max_length: 4096,
      sentences_1: "What is BGE M3?\nDefination of BM25",
      sentences_2: "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
      embedding_type: "dense"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/bge-m3:3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
    input={
        "max_length": 4096,
        "sentences_1": "What is BGE M3?\nDefination of BM25",
        "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
        "embedding_type": "dense"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
    "input": {
      "max_length": 4096,
      "sentences_1": "What is BGE M3?\\nDefination of BM25",
      "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
      "embedding_type": "dense"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

[[0.626 0.3477] [0.3499 0.678 ]]

Generated in

53.5 seconds

Tweak it Share Report

Prediction

lucataco/bge-m3:3af6c861

Model

lucataco/bge-m3:3af6c861

ID

wu2utkjbymdffjnyr4dgrroqjm

Status

Succeeded

Source

Web

Hardware

T4

Total duration

47.7s

Created

about 1 year ago

Input

max_length: 8192
sentences_1: What is BGE M3? Defination of BM25
sentences_2: BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction. BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document
embedding_type: sparse

{
  "max_length": 8192,
  "sentences_1": "What is BGE M3?\nDefination of BM25",
  "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
  "embedding_type": "sparse"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/bge-m3:3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
  {
    input: {
      max_length: 8192,
      sentences_1: "What is BGE M3?\nDefination of BM25",
      sentences_2: "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
      embedding_type: "sparse"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/bge-m3:3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
    input={
        "max_length": 8192,
        "sentences_1": "What is BGE M3?\nDefination of BM25",
        "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
        "embedding_type": "sparse"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
    "input": {
      "max_length": 8192,
      "sentences_1": "What is BGE M3?\\nDefination of BM25",
      "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
      "embedding_type": "sparse"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

0.19549560546875 0

Generated in

47.7 seconds

Tweak it Share Report

Prediction

lucataco/bge-m3:3af6c861

Model

lucataco/bge-m3:3af6c861

ID

vy65tbbbpvldplp3fqaqvodhti

Status

Succeeded

Source

Web

Hardware

T4

Total duration

49.0s

Created

about 1 year ago

Input

max_length: 8192
sentences_1: What is BGE M3? Defination of BM25
sentences_2: BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction. BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document
embedding_type: colbert

{
  "max_length": 8192,
  "sentences_1": "What is BGE M3?\nDefination of BM25",
  "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
  "embedding_type": "colbert"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/bge-m3:3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
  {
    input: {
      max_length: 8192,
      sentences_1: "What is BGE M3?\nDefination of BM25",
      sentences_2: "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
      embedding_type: "colbert"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/bge-m3:3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
    input={
        "max_length": 8192,
        "sentences_1": "What is BGE M3?\nDefination of BM25",
        "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
        "embedding_type": "colbert"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/bge-m3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "3af6c861256a2a8e07a54a478813e6632f339f05235b59374f292f4759555bfb",
    "input": {
      "max_length": 8192,
      "sentences_1": "What is BGE M3?\\nDefination of BM25",
      "sentences_2": "BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.\\nBM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document",
      "embedding_type": "colbert"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

tensor(0.7796) tensor(0.4622)

Generated in

49.0 seconds

Tweak it Share Report

lucataco / bge-m3

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (tdyhblrbhppnc7cf45f5jwvavu)

Logs (wu2utkjbymdffjnyr4dgrroqjm)

Logs (vy65tbbbpvldplp3fqaqvodhti)