Unduh mlx embeddings - mlx embeddings Unduh kode sumber

mlx embeddings

Kode Sumber AI

1.0.0

Unduh

MLX-Sematan

MLX-Embeddings adalah paket untuk menjalankan model Vision dan Language Embedding secara lokal di Mac Anda menggunakan MLX.

Perangkat lunak bebas: Lisensi Publik Umum GNU v3

Fitur

Hasilkan penyematan untuk teks menggunakan model MLX
Dukungan untuk pemrosesan item tunggal dan batch
Utilitas untuk membandingkan kesamaan teks

Instalasi

Anda dapat menginstal mlx-embeddings menggunakan pip:

pip install mlx-embeddings

Penggunaan

Penyematan Item Tunggal

Untuk menghasilkan penyematan pada satu bagian teks:

 import mlx . core as mx
from mlx_embeddings . utils import load

# Load the model and tokenizer
model , tokenizer = load ( "sentence-transformers/all-MiniLM-L6-v2" )

# Prepare the text
text = "I like reading"

# Tokenize and generate embedding
input_ids = tokenizer . encode ( text , return_tensors = "mlx" )
outputs = model ( input_ids )
embeddings = outputs [ 0 ][:, 0 , :]

Membandingkan Beberapa Teks

Untuk membandingkan beberapa teks menggunakan penyematannya:

 from sklearn . metrics . pairwise import cosine_similarity
import matplotlib . pyplot as plt
import seaborn as sns
import mlx . core as mx
from mlx_embeddings . utils import load

# Load the model and tokenizer
model , tokenizer = load ( "sentence-transformers/all-MiniLM-L6-v2" )

def get_embedding ( text , model , tokenizer ):
    input_ids = tokenizer . encode ( text , return_tensors = "mlx" , padding = True , truncation = True , max_length = 512 )
    outputs = model ( input_ids )
    embeddings = outputs [ 0 ][:, 0 , :][ 0 ]
    return embeddings

# Sample texts
texts = [
    "I like grapes" ,
    "I like fruits" ,
    "The slow green turtle crawls under the busy ant."
]

# Generate embeddings
embeddings = [ get_embedding ( text , model , tokenizer ) for text in texts ]

# Compute similarity
similarity_matrix = cosine_similarity ( embeddings )

# Visualize results
def plot_similarity_matrix ( similarity_matrix , labels ):
    plt . figure ( figsize = ( 5 , 4 ))
    sns . heatmap ( similarity_matrix , annot = True , cmap = 'coolwarm' , xticklabels = labels , yticklabels = labels )
    plt . title ( 'Similarity Matrix Heatmap' )
    plt . tight_layout ()
    plt . show ()

labels = [ f"Text { i + 1 } " for i in range ( len ( texts ))]
plot_similarity_matrix ( similarity_matrix , labels )

Pemrosesan Batch

Untuk memproses banyak teks sekaligus:

 from sklearn . metrics . pairwise import cosine_similarity
import matplotlib . pyplot as plt
import seaborn as sns
import mlx . core as mx
from mlx_embeddings . utils import load

# Load the model and tokenizer
model , tokenizer = load ( "sentence-transformers/all-MiniLM-L6-v2" )

def get_embedding ( texts , model , tokenizer ):
    inputs = tokenizer . batch_encode_plus ( texts , return_tensors = "mlx" , padding = True , truncation = True , max_length = 512 )
    outputs = model (
        inputs [ "input_ids" ],
        attention_mask = inputs [ "attention_mask" ]
    )
    return outputs [ 0 ]

def compute_and_print_similarity ( embeddings ):
    B , Seq_len , dim = embeddings . shape
    embeddings_2d = embeddings . reshape ( B , - 1 )
    similarity_matrix = cosine_similarity ( embeddings_2d )

    print ( "Similarity matrix between sequences:" )
    print ( similarity_matrix )
    print ( " n " )

    for i in range ( B ):
        for j in range ( i + 1 , B ):
            print ( f"Similarity between sequence { i + 1 } and sequence { j + 1 } : { similarity_matrix [ i ][ j ]:.4f } " )

    return similarity_matrix

# Sample texts
texts = [
    "I like grapes" ,
    "I like fruits" ,
    "The slow green turtle crawls under the busy ant."
]

embeddings = get_embedding ( texts , model , tokenizer )
similarity_matrix = compute_and_print_similarity ( embeddings )

# Visualize results
labels = [ f"Text { i + 1 } " for i in range ( len ( texts ))]
plot_similarity_matrix ( similarity_matrix , labels )

Arsitektur Model yang Didukung

MLX-Embeddings mendukung berbagai arsitektur model untuk tugas penyematan teks. Berikut rincian arsitektur yang didukung saat ini:

XLM-RoBERTa (Model Bahasa Lintas Bahasa - Pendekatan BERT yang Dioptimalkan dengan Kuat)
BERT (Representasi Encoder Dua Arah dari Transformers)

Kami terus berupaya memperluas dukungan kami untuk arsitektur model tambahan. Periksa repositori atau dokumentasi GitHub kami untuk mengetahui daftar terbaru model yang didukung dan versi spesifiknya.