rcarmo/asterisk-embedding-model
A small text embedding model for low-resource hardware
This project helps operations engineers or data analysts working with large volumes of text, like news summaries or personal notes, quickly find similar content or group related documents together. It takes text inputs and converts them into compact numerical representations that can be used for tasks such as semantic search, clustering, or deduplication, all on devices with limited computing power. This is ideal for those needing efficient text analysis without relying on powerful external services.
Use this if you need to perform semantic search, clustering, or deduplication on text data using low-resource hardware, like edge devices or older laptops, and require fast, real-time results.
Not ideal if your primary concern is achieving the absolute highest accuracy on complex, nuanced semantic tasks and you have access to powerful computing resources.
Stars
8
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/rcarmo/asterisk-embedding-model"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MinishLab/model2vec
Fast State-of-the-Art Static Embeddings
AnswerDotAI/ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
tensorflow/hub
A library for transfer learning by reusing parts of TensorFlow models.
Embedding/Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
twang2218/vocab-coverage
语言模型中文认知能力分析