inference-x-community/organ-architect
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Visualize AI model internals — layers, attention heads, weight distributions. https://inference-x.com
7 Commits 1 Branch 0 Tags 36 KiB
Python 100%
04a3ab9a93
Go to file
Inference-X 04a3ab9a93 docs: professional README — Feb 2026
2026-02-25 17:29:59 +00:00
.gitignore Initial commit 2026-02-25 00:53:39 +00:00
LICENSE Initial commit 2026-02-25 00:53:38 +00:00
organ_architect.py chore: remove internal framework references 2026-02-25 02:56:57 +00:00
README.md docs: professional README — Feb 2026 2026-02-25 17:29:59 +00:00
requirements.txt Initial commit 2026-02-25 00:53:39 +00:00

README.md

Organ Architect

Visualize and analyze AI model internals

Status

inference-x.com

What is Organ Architect?

Organ Architect is a visual tool for exploring the internals of GGUF AI models. Think of it as a surgical suite for neural networks — layer shapes, attention patterns, weight distributions, all visible.

Features

  • Architecture visualization — interactive graph of all layers
  • Attention head analysis — what each head attends to
  • Weight distribution — histograms per layer
  • Layer comparison — diff two models layer-by-layer
  • Export — save analysis as JSON or PDF report

Quick start

git clone https://git.inference-x.com/inference-x-community/organ-architect
cd organ-architect && npm install
npm start

# Open http://localhost:3000
# Drag and drop any .gguf file

Supported architectures

LLaMA · Mistral · Mixtral · Qwen · Phi · Gemma · Falcon · GPT-NeoX · Command-R · and all GGUF-format models

See also: organ-architecture · organ-store