ag_embedding: Create an Embedding layer

In ggmlR: 'GGML' Tensor Operations for Machine Learning

Create an Embedding layer

Description

Maps 0-based integer indices to dense vectors via table lookup. Input: integer matrix or vector of 0-based indices. Output: float tensor [dim, length(idx)].

Usage

ag_embedding(vocab_size, dim)

Arguments

vocab_size	Vocabulary size
dim	Embedding dimension

Details

Backward: scatter-add — only the looked-up rows accumulate gradient.

Value

An ag_embedding environment

Examples

emb <- ag_embedding(100L, 16L)
idx <- c(0L, 3L, 7L, 2L)
out <- emb$forward(idx)   # [16, 4]

ggmlR documentation built on July 14, 2026, 1:08 a.m.