Fabelous Embedder Mini

This repository contains a custom sentence transformer model named fabelous-mini-embedder, trained on 13 different programming languages and English.

Description

The model was built using the Sentence Transformer library, which provides an easy-to-use interface for working with sentence embeddings, including pre-trained models.

In addition to fabelous-mini-embedder, there is also have a proprietary model called fabelous-embedder-base. Both models are trained on a vast dataset covering various programming languages, including:

• Python
• Java
• Go
• C++
• TypeScript

Example Usage

Here’s how to use the model to generate sentence embeddings:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("fabelous-mini-embedder")

instruction = "This is an example sentence"
embeddings = model.encode(instruction)

print(embeddings)  # Output: (array of numerical embeddings)

The generated embeddings can be used for tasks like semantic search or classification.

Future Improvements

The second generation is in the works, focusing on:

• Enhanced Multilingual Support: Adding support for German in addition to English.
• Expanded Dataset: Increasing the code dataset significantly to improve model performance and accuracy.

Installation

To install the required libraries, run:

pip install sentence-transformers