tanaos/artifex
Small Language Model Inference, Fine-Tuning and Observability. No GPU, no labeled data needed.
This project helps you classify, summarize, or detect specific information in text data, right on your computer without needing expensive graphics cards or external services. You feed it raw text, along with instructions for what you want to do, and it provides categorized text, sentiment scores, or other processed outputs. It's designed for data analysts, content moderators, or anyone handling large volumes of text who needs custom, private, and efficient text processing.
Available on PyPI.
Use this if you need to perform specific text analysis tasks like content moderation, sentiment analysis, or topic classification, and want to keep your data private while running everything locally on your standard computer.
Not ideal if you need a general-purpose, large-scale language model for creative writing or complex conversational AI, as this tool focuses on specialized text understanding tasks.
Stars
90
Forks
12
Language
Python
License
MIT
Category
Last pushed
Feb 03, 2026
Commits (30d)
0
Dependencies
13
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tanaos/artifex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
google/langfun
OO for LLMs
allenai/RL4LMs
A modular RL library to fine-tune language models to human preferences
emredeveloper/Mem-LLM
Mem-LLM is a Python library for building memory-enabled AI assistants that run entirely on local...
cloudguruab/modsysML
Human reinforcement learning (RLHF) framework for AI models. Evaluate and compare LLM outputs,...
josh-ashkinaze/plurals
Plurals: A System for Guiding LLMs Via Simulated Social Ensembles