jina-ai/embedding-fingerprints
Identify which embedding model produced a vector using digit-level tokenization and a tiny transformer
This project helps machine learning engineers identify which embedding model was used to create a given vector. You provide an embedding vector, and it tells you which model (like OpenAI's, Cohere's, or a specific variant) likely generated it. This is for machine learning practitioners and MLOps engineers who need to manage or understand the origin of various embedding datasets.
Use this if you have a collection of embedding vectors and need to determine which specific model produced each one without prior metadata.
Not ideal if you already know the origin of your embedding vectors or if you need to reconstruct the original text from the embeddings.
Stars
16
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jina-ai/embedding-fingerprints"
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