ARC-Neuron LLMBuilder

A governed, local-first system for training small language models that measures each new model against a benchmark, promotes only improvements through a regression-aware gate, and archives the evidence for every decision.

Visit website github.com

ARC-Neuron LLMBuilder trains or plugs in a small local language model, tests it against a benchmark set, and decides whether it has improved before promoting it. Runs that fail the gate are archived rather than discarded, and every promotion keeps a rollback path along with the evidence behind the decision.

The project reports being built and verified on older, GPU-less consumer hardware, running entirely on Python with no cloud dependency, and includes a public verification suite and a scorer-expanded benchmark inventory. It is part of a wider set of related ARC repositories.

More in Models

See all 405

mini-AGI
github.com
A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.
- Models
Applied Inference Lab: Compliance Control Embedding Stack
github.com
An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.
- Models
- Security
peekaboolean
github.com
A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.
- Models
- Inference

More in Models

mini-AGI

Applied Inference Lab: Compliance Control Embedding Stack

peekaboolean

Cookies