bio-lm-5090

A language model trained on data from a neuron science simulation

bio-lm-5090 media is blocked

Allow external media to connect to the provider and play this content.

Description

An experimental language model with 17.7 million parameters trained on synthetic data generated from a multistep neuron science simulation. The project explores training LLMs on evolved neuron outputs using a custom PyTorch data pipeline and local GPU acceleration.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: It is a novel technical experiment training an LLM on the outputs of a specialized neuron evolution simulation.
Attributed to: @HappyMonkeyAI
Built with: Moonshine Tiny q8 GPT-5.5 Pro Small 4 LTX 2.3 Pro 3.1 Pro Vidu Q3 Pro Seedream 5.0 Pro Seedance 1.5 Pro Flux 2 Pro Nano Banana Pro Gemini 3 Pro Redwood AI Gemini 2.5 Pro
Tags: #neuroscience #simulation #pytorch #synthetic-data

Discovered: X
First posted: X · Sep 9, 2026
Listed: Added 7d ago
Build: Strong
Models: Moderate

bio-lm-5090

Description

Timeline

bio-lm-5090

Description

Timeline