[ GUIDE 01 ]

Getting started

Walk through composing your first transformer architecture in Otter — from canvas to exported PyTorch code.

[ 01 ]

Open the canvas

Navigate to the Canvas. You'll see a component library on the left and an empty canvas in the center.

→ First-time visitors see a short onboarding tour covering the canvas and validation.

[ 02 ]

Add components

Drag components from the library onto the canvas. The essential blocks are:

  • ›Embedding — Converts token IDs to dense vectors.
  • ›RMSNorm — Normalizes activations (Llama-style).
  • ›GroupedQueryAttention — Multi-head attention with KV sharing.
  • ›SwiGLU FFN — Feed-forward network with gated activations.
  • ›Output Head — Projects hidden states to vocabulary logits.
[ 03 ]

Connect components

Click on a component's output handle (bottom) and drag to another's input handle (top). Otter validates the connection as soon as it's drawn — amber means attention needed, paper means valid.

→ Dimensions propagate through the graph topologically. A mismatch at any edge lights up the offending path.

[ 04 ]

Configure parameters

Click any component to open its configuration panel. Adjust dimensions, head counts, intermediate sizes.

hidden_dim = 4096
num_heads = 32
intermediate_dim = 14336
[ 05 ]

Export the model

When the architecture validates (no error count in the canvas footer), click Export. You get a ZIP with:

  • ›model.py — Complete PyTorch model definition.
  • ›config.json — HuggingFace-compatible configuration.
  • ›train.py — Example training script.
  • ›requirements.txt — Python dependencies.
  • ›README.md — Usage instructions.