blaifa/multilingual-e5-large-instruct

blaifa/ multilingual-e5-large-instruct

277 Downloads Updated 7 months ago

A Q8_0 quantization of the famous embedding model of intfloat

embedding

ollama pull blaifa/multilingual-e5-large-instruct

curl http://localhost:11434/api/embed \
  -d '{
    "model": "blaifa/multilingual-e5-large-instruct",
    "input": "Why is the sky blue?"
  }'

import ollama

response = ollama.embed(
    model='blaifa/multilingual-e5-large-instruct',
    input='The sky is blue because of Rayleigh scattering',
)
print(response.embeddings)

import ollama from 'ollama'

const response = await ollama.embed({
  model: 'blaifa/multilingual-e5-large-instruct',
  input: 'The sky is blue because of Rayleigh scattering',
})
console.log(response.embeddings)

Models

View all →

Name

2 models

Size

Context

Input

multilingual-e5-large-instruct:latest

603MB · 512 context window · Text · 7 months ago

multilingual-e5-large-instruct:latest

603MB

512

Text

multilingual-e5-large-instruct:Q8_0

603MB · 512 context window · Text · 8 months ago

multilingual-e5-large-instruct:Q8_0

603MB

512

Text

Readme

Multilingual E5 Text Embeddings: A Technical Report. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024

This model has 24 layers and the embedding size is 1024.

Original Model on HF