Downloads · 30 days
3
16% of all-time downloads
kofdai/verantyx
verantyx is a machine learning model from kofdai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Downloads · 30 days
3
16% of all-time downloads
All-time downloads
19
Public
Repo size
1.5 MB
Likes
0
Public
Click a slice to open those files.
.mp41.5 MB · 56%
From the Hugging Face model README
VERANTYX is an experimental logical inference system designed to control, constrain, and audit reasoning rather than to generate language.
At the present stage, VERANTYX relies on conventional large language models only because its internal rule and definition database is still incomplete. This reliance is not a design goal, but a temporary engineering compromise.
VERANTYX is explicitly designed so that, as its database grows, the role of traditional LLMs diminishes — and eventually becomes unnecessary.
VERANTYX should therefore not be understood as an LLM-based system. It is a database-centric reasoning engine that currently uses LLMs as external, replaceable mining tools.
Modern AI systems overwhelmingly equate intelligence with probabilistic language generation. VERANTYX was created to challenge this assumption.
We observe persistent structural problems in mainstream LLM reasoning:
VERANTYX does not claim superiority. It exists to explore whether explicit logic, rules, counterexamples, and necessity checks can form a more auditable foundation for reasoning.
rules.json and registered definitions. Zero noise.VERANTYX は、文章生成ではなく 推論そのものを制御・拘束・監査する ことを目的とした実験的論理推論システムです。
現時点では、VERANTYX は内部のルール・定義データベースが十分に成長していないため、従来の大規模言語モデル(LLM)を補助的に利用しています。しかしこれは 設計思想ではなく暫定的措置 です。
VERANTYX は、データベースが拡張されるにつれて、従来の LLM が不要になることを前提に設計されています。したがって VERANTYX は LLM ベースのシステムではありません。現在は LLM を「外部の採掘ツール」として利用している データベース中心の推論エンジン です。
現代の AI は、確率的な言語生成を知性と同一視する傾向があります。VERANTYX はその前提自体を問い直すために作られました。
LLM による推論には、以下の構造的問題があります:
VERANTYX は優位性を主張しません。明示的ルール・反例・必要条件検証 による推論が、別の可能性を持つかを検証するための実験です。
VERANTYX is designed to run locally or in a containerized environment. Follow these steps to install and set up the system.
git clone https://huggingface.co/kofdai/verantyx
cd verantyx
It is recommended to use a virtual environment.
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
VERANTYX uses external LLMs for Phase 2 mining. By default, it is configured to use nvidia/OpenMath2-Llama3.1-8B. Use the provided script to download it securely.
python3 scripts/download_models.py
Note: You must have a Hugging Face account and agree to the model provider's license terms.
Start the Flask-based web interface:
python3 axis/app.py
Once started, access the UI at: http://localhost:5001 (or the port specified in your environment).
Research Status: Experimental / Research Preview Author: kofdai