llama.cpp/examples/convert-llama2c-to-ggml
2024-05-09 10:16:45 +02:00
..
CMakeLists.txt Adding support for llama2.c models (#2559) 2023-08-12 01:17:25 +02:00
convert-llama2c-to-ggml.cpp llama2c : open file as binary (#6332) 2024-03-27 09:16:02 +02:00
README.md TypoFix (#7162) 2024-05-09 10:16:45 +02:00

Convert llama2.c model to ggml

This example reads weights from project llama2.c and saves them in ggml compatible format. The vocab that is available in models/ggml-vocab.bin is used by default.

To convert the model first download the models from the llama2.c repository:

$ make -j

After successful compilation, following usage options are available:

usage: ./convert-llama2c-to-ggml [options]

options:
  -h, --help                       show this help message and exit
  --copy-vocab-from-model FNAME    path of gguf llama model or llama2.c vocabulary from which to copy vocab (default 'models/7B/ggml-model-f16.gguf')
  --llama2c-model FNAME            [REQUIRED] model path from which to load Karpathy's llama2.c model
  --llama2c-output-model FNAME     model path to save the converted llama2.c model (default ak_llama_model.bin')

An example command using a model from karpathy/tinyllamas is as follows:

$ ./convert-llama2c-to-ggml --copy-vocab-from-model llama-2-7b-chat.gguf.q2_K.bin --llama2c-model stories42M.bin --llama2c-output-model stories42M.gguf.bin

Note: The vocabulary for stories260K.bin should be its own tokenizer tok512.bin found in karpathy/tinyllamas/stories260K.

Now you can use the model with a command like:

$ ./main -m stories42M.gguf.bin -p "One day, Lily met a Shoggoth" -n 500 -c 256