brunneis/fastc
Unattended Lightweight Text Classifiers with LLM Embeddings
This project helps data scientists, machine learning engineers, and Python developers quickly build and deploy text classification models. It takes in text data labeled with categories (like 'positive' or 'negative') and outputs a model that can automatically sort new, unlabeled text into those same categories. The tool is designed for efficient execution, even on systems with limited memory.
186 stars. No commits in the last 6 months.
Use this if you need to classify large volumes of text into predefined categories efficiently, without the overhead of fine-tuning large language models.
Not ideal if you require highly complex, nuanced text understanding beyond straightforward classification or if you need to train models from scratch on massive datasets.
Stars
186
Forks
10
Language
Python
License
GPL-3.0
Category
Last pushed
Sep 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/brunneis/fastc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
realityinspector/waivelets-v0.1
Wavelet-derived structural fingerprints for text. MiniLM embeddings → 7-number dynamics → 4...
DioBey7/GameHorizon
GameHorizon, oyuncuların zevklerine en uygun oyunları anlamsal arama (NLP) ve gelişmiş hibrit...
shresth03/docarrange
AI-powered file organization using semantic search, topic modeling, and knowledge graphs
NeoOne601/Toori
A Pure local world-model ecosystem for visual intelligence, the world-model intelligence layer...
ronaldgosso/semantic-keywords
TF-IDF counts words. semantic-keywords understands meaning. It uses sentence embeddings...