llama_set_causal_attn: Set causal attention mode
In llamaR: Interface for Large Language Models via 'llama.cpp'

llama_set_causal_attn

R Documentation

Set causal attention mode

Description

When disabled, the model uses full (bidirectional) attention. This is useful for embedding models.

Usage

llama_set_causal_attn(ctx, causal)

Arguments

`ctx`	Context handle returned by [llama_new_context]
`causal`	Logical; `TRUE` for causal (autoregressive) attention, `FALSE` for full bidirectional attention

Value

No return value, called for side effects.

Examples

## Not run: 
model <- llama_load_model("model.gguf")
ctx <- llama_new_context(model)
llama_set_causal_attn(ctx, FALSE)  # for embeddings

## End(Not run)

llamaR documentation built on May 28, 2026, 1:06 a.m.