jina-code-embeddings-0.5b

13.5K

16

license:cc-by-nc-4.0

by

jinaai

Embedding Model

OTHER

0.5B params

Fair

14K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

2GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

1GB+ RAM

Code Examples

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

tensor([[0.8168, 0.1236],pythonpytorch

# !pip install sentence_transformers>=5.0.0 torch>=2.7.1

import torch
from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer(
    "jinaai/jina-code-embeddings-0.5b",
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "cuda"
    },
    tokenizer_kwargs={"padding_side": "left"},
)

# The queries and documents to embed
queries = [
    "print hello world in python",
    "initialize array of 5 zeros in c++"
]
documents = [
    "print('Hello World!')",
    "int arr[5] = {0, 0, 0, 0, 0};"
]

query_embeddings = model.encode(queries, prompt_name="nl2code_query")
document_embeddings = model.encode(documents, prompt_name="nl2code_document")

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.8169, 0.1214],
#         [0.1190, 0.5500]])

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.

Replicate

One-click model deployment

Easiest Setup

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

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