Sākums Izpētīt Palīdzība
Pierakstīties
cturan
/
llama.cpp
spogulis no https://github.com/cturan/llama.cpp
1
0
Atdalīts 0
Faili Problēmas 0 Vikivietne
Koks: 862f5e41ab
Atzari Tagi
llama.cpp
/
examples
/
export-lora
Daniel Bevenius 930f907d3e export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894) 2 gadi atpakaļ
..
CMakeLists.txt 0e76a8992c train : finetune LORA (#2632) 2 gadi atpakaļ
README.md 0e76a8992c train : finetune LORA (#2632) 2 gadi atpakaļ
export-lora.cpp 930f907d3e export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894) 2 gadi atpakaļ

README.md

export-lora

Apply LORA adapters to base model and export the resulting model.

usage: export-lora [options]

options:
  -h, --help                         show this help message and exit
  -m FNAME, --model-base FNAME       model path from which to load base model (default '')
  -o FNAME, --model-out FNAME        path to save exported model (default '')
  -l FNAME, --lora FNAME             apply LoRA adapter
  -s FNAME S, --lora-scaled FNAME S  apply LoRA adapter with user defined scaling S
  -t N, --threads N                  number of threads to use during computation (default: 4)

For example:

./bin/export-lora \
    -m open-llama-3b-v2-q8_0.gguf \
    -o open-llama-3b-v2-q8_0-english2tokipona-chat.gguf \
    -l lora-open-llama-3b-v2-q8_0-english2tokipona-chat-LATEST.bin

Multiple LORA adapters can be applied by passing multiple -l FN or -s FN S command line parameters.