vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama2.c: update default path for vocab model + readme

Browse source
This commit is contained in:
ochafik 2023-08-26 20:59:46 +01:00
parent c88362d194
commit df3b81ab29
2 changed files with 9 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/convert-llama2c-to-ggml/README.md
View file

@ -12,14 +12,14 @@ usage: ./convert-llama2c-to-ggml [options]
options: options:
-h, --help show this help message and exit -h, --help show this help message and exit
--copy-vocab-from-model FNAME model path from which to copy vocab (default 'tokenizer.bin') --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-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') --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](https://huggingface.co/karpathy/tinyllamas) is as follows: An example command using a model from [karpathy/tinyllamas](https://huggingface.co/karpathy/tinyllamas) is as follows:
`$ ./convert-llama2c-to-ggml --copy-vocab-from-model ../llama2.c/tokenizer.bin --llama2c-model stories42M.bin --llama2c-output-model stories42M.gguf.bin` `$ ./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`
Now you can use the model with a command like: Now you can use the model with a command like:

4
examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
View file

@ -766,7 +766,7 @@ void save_as_llama_model(struct llama_vocab * vocab, struct my_llama_model * mod
struct train_params get_default_train_params() { struct train_params get_default_train_params() {
struct train_params params; struct train_params params;
params.fn_vocab_model = "tokenizer.bin"; params.fn_vocab_model = "models/7B/ggml-model-f16.gguf";
params.fn_llama2c_output_model = "ak_llama_model.bin"; params.fn_llama2c_output_model = "ak_llama_model.bin";
params.fn_train_data = "shakespeare.txt"; params.fn_train_data = "shakespeare.txt";
params.fn_checkpoint_in = "checkpoint.bin"; params.fn_checkpoint_in = "checkpoint.bin";
@ -819,7 +819,7 @@ void print_usage(int /*argc*/, char ** argv, const struct train_params * params)
fprintf(stderr, "\n"); fprintf(stderr, "\n");
fprintf(stderr, "options:\n"); fprintf(stderr, "options:\n");
fprintf(stderr, " -h, --help show this help message and exit\n"); fprintf(stderr, " -h, --help show this help message and exit\n");
fprintf(stderr, " --copy-vocab-from-model FNAME llama2.c vocabulary or ggmlv3 model path from which to copy vocab (default '%s')\n", params->fn_vocab_model); fprintf(stderr, " --copy-vocab-from-model FNAME path of gguf llama model or llama2.c vocabulary from which to copy vocab (default '%s')\n", params->fn_vocab_model);
fprintf(stderr, " --llama2c-model FNAME [REQUIRED] model path from which to load Karpathy's llama2.c model\n"); fprintf(stderr, " --llama2c-model FNAME [REQUIRED] model path from which to load Karpathy's llama2.c model\n");
fprintf(stderr, " --llama2c-output-model FNAME model path to save the converted llama2.c model (default %s')\n", params->fn_llama2c_output_model); fprintf(stderr, " --llama2c-output-model FNAME model path to save the converted llama2.c model (default %s')\n", params->fn_llama2c_output_model);
fprintf(stderr, "\n"); fprintf(stderr, "\n");