Skills
.Work. You
Rest

neuralfn-torch

Community

Train and export Torch-backed NeuralFn models.

Software Engineering#presets#model-training#machine-learning#torch#neuralfn#export-weights
Authoradamdroberts
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Build, train, and export Torch-backed NeuralFn models using the Python API to enable rapid development and deployment of transformer-based systems.

Core Features & Use Cases

  • Build and configure Graphs: create model graphs using NeuralFn presets (nanogpt, llama, jamba, etc.), set ModelSpec/BlockSpec, and compile with Torch runtime.
  • Train and export: train Torch models with TorchTrainer and export weights to .pt for inference or deployment.
  • Inference-ready: generate autoregressive outputs and export fully runnable Torch modules for integration in Python projects.

Quick Start

Install NeuralFn, import the NeuralFn Python API, and run the provided end-to-end example to build, train, and export a Torch-backed model.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: neuralfn-torch
Download link: https://github.com/adamdroberts/NeuralFn/archive/main.zip#neuralfn-torch

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.