finalfusion/finalfrontier
Context-sensitive word embeddings with subwords. In Rust.
This tool helps machine learning engineers and NLP researchers create contextual word embeddings from large text datasets. It takes raw text as input and produces high-quality word embeddings in formats like word2vec, fastText, or GloVe, which can then be used in downstream NLP tasks such as sentiment analysis or machine translation. The primary users are those building and training custom NLP models.
No commits in the last 6 months.
Use this if you need to train custom, context-sensitive word embeddings for your specific textual data, rather than using pre-trained, general-purpose embeddings.
Not ideal if you're looking for a ready-to-use, off-the-shelf solution for NLP tasks without needing to train custom embeddings from scratch.
Stars
90
Forks
5
Language
Rust
License
—
Category
Last pushed
Oct 20, 2023
Monthly downloads
47
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/finalfusion/finalfrontier"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Anush008/fastembed-rs
Rust library for vector embeddings and reranking.
huggingface/text-embeddings-inference
A blazing fast inference solution for text embeddings models
MinishLab/model2vec-rs
Official Rust Implementation of Model2Vec
finalfusion/finalfusion-rust
finalfusion embeddings in Rust
finalfusion/finalfusion-python
Finalfusion embeddings in Python