Sentence Similarity
sentence-transformers
Safetensors
qwen3
feature-extraction
dense
Generated from Trainer
dataset_size:1716
loss:ContrastiveLoss
text-embeddings-inference
Instructions to use hasinthakapiyumal/bge-reasoner-embed-ms-patterns with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use hasinthakapiyumal/bge-reasoner-embed-ms-patterns with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("hasinthakapiyumal/bge-reasoner-embed-ms-patterns") sentences = [ "This Spring `@Service` implementation (`UserServiceImpl`) retrieves user credentials by username from a `UserCredentialRepository`. It then maps the found `UserCredential` entity to a `UserDto` using `ModelMapper`, returning `null` if the user is not found.", "This Python file contains a comprehensive suite of `pytest` integration and end-to-end tests for multiple distinct RESTful APIs, including game, history, likes, favorites, file storage, task management, and user authentication/management services. It thoroughly validates API endpoints, data models, authentication, pagination, and various edge cases, leveraging the `requests` library for HTTP interactions and extensive fixtures for setup and teardown.", "This Python code defines a Thrift client (`Client` class) for user management, implementing methods for user registration, login, and retrieving/uploading user data. It utilizes a distinct `send_` and `recv_` pattern for each remote procedure call, handling message serialization, deserialization, and application-level exception handling.", "This Spring Boot `RestController` (`UserController`) provides a comprehensive set of RESTful API endpoints for user management, enabling operations such as retrieving all users, finding users by ID or username, registering new users, updating existing ones, and deleting users. It delegates all business logic to an injected `UserService`, consistently returning `ResponseEntity<Response>` and logging actions for each operation." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Welcome to the community
The community tab is the place to discuss and collaborate with the HF community!