pt_transformer: Build a piece transformer

In ggmlR: 'GGML' Tensor Operations for Machine Learning

Build a piece transformer

Description

Creates the model with its weights at their initial values. To run a trained one, use pt_transformer_load, which builds this and then fills it from a checkpoint.

Usage

pt_transformer(
  layout,
  d_model = 256L,
  n_heads = 8L,
  n_layers = 4L,
  ff_dim = 1024L,
  n_actions = 24L,
  activation = "relu"
)

Arguments

layout	A layout list, as pt_cube4_layout returns.
d_model	Width of the model (default 256).
n_heads	Attention heads (default 8).
n_layers	Encoder blocks (default 4).
ff_dim	Width of the feed-forward hidden layer (default 1024).
n_actions	Size of the output — one value per action (default 24).
activation	Feed-forward activation, "relu" (default) or "gelu" / "silu".

Value

A pt_transformer object.

See Also

pt_transformer_load, pt_forward

ggmlR documentation built on Oct. 23, 2026, 1:07 a.m.