dragon_export_gguf: Export a merged model to GGUF

In dragonfarm: Fine-Tune Small Language Models with LoRA from R

Export a merged model to GGUF

Description

Converts a merged model directory to GGUF for use with llama.cpp, Ollama, and similar runtimes. Requires a llama.cpp checkout; point the LLAMA_CPP_DIR environment variable at it.

Usage

dragon_export_gguf(
  merged_dir,
  out_file = NULL,
  quant = "q8_0",
  llama_cpp_dir = Sys.getenv("LLAMA_CPP_DIR", unset = "")
)

Arguments

merged_dir	A merged model directory from dragon_merge().
out_file	Output path. Defaults to ⁠model-<quant>.gguf⁠ next to the model.
quant	Output type passed to the converter, such as "q8_0", "f16", or "bf16".
llama_cpp_dir	Path to a llama.cpp checkout containing convert_hf_to_gguf.py.

Value

The output path, invisibly.

dragonfarm documentation built on Oct. 12, 2026, 5:07 p.m.