gte-multilingual-base-Ko-embedding

5
license:apache-2.0
by
jaeyong2
Embedding Model
OTHER
New
5 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

- H/W : colab A100 40GB - Data : jaeyong2/Ko-emb-PreView Accuracy - Alibaba-NLP/gte-multilingual-base : 0.

Code Examples

Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")
Evaluationtextpytorch
import torch
import numpy as np
from sklearn.metrics import pairwise_distances
from tqdm import tqdm


dataset = datasets.load_dataset("jaeyong2/Ko-emb-PreView")
validation_dataset = dataset["test"].select(range((1000)))

model.eval()

def evaluate(validation_dataset):
    correct_count = 0

    for item in tqdm(validation_dataset):
        query_embedding = get_embedding(item["context"], model, tokenizer)
        document_embedding = get_embedding(item["Title"], model, tokenizer)
        negative_embedding = get_embedding(item["Fake Title"], model, tokenizer)
      

        # 쿼리와 모든 문서 간의 유사도 계산 (코사인 거리 사용)
        positive_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), document_embedding.detach().cpu().float().numpy(), metric="cosine")
        negative_distances = pairwise_distances(query_embedding.detach().cpu().float().numpy(), negative_embedding.detach().cpu().float().numpy(), metric="cosine")

        if positive_distances < negative_distances:
            correct_count += 1

    accuracy = correct_count / len(validation_dataset)
    return accuracy

results = evaluate(validation_dataset)
print(f"Validation Results: {results}")

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.