From 2a0138e5eaf678fa4156ccd60979aac5d5042373 Mon Sep 17 00:00:00 2001 From: Aniket Date: Tue, 8 Aug 2023 13:52:20 -0400 Subject: [PATCH] updating readme for instructions for compilation and use --- examples/convert-llama2c-to-ggml/README.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 examples/convert-llama2c-to-ggml/README.md diff --git a/examples/convert-llama2c-to-ggml/README.md b/examples/convert-llama2c-to-ggml/README.md new file mode 100644 index 000000000..18293947a --- /dev/null +++ b/examples/convert-llama2c-to-ggml/README.md @@ -0,0 +1,13 @@ +## Convert llama2.c model to ggml + +This example reads weights from project [llama2.c](https://github.com/karpathy/llama2.c) and saves them in ggml compatible format. + +To convert the model first download the models from the [llma2.c](https://github.com/karpathy/llama2.c) repository: + +`$ make -j` + +`$ ./convert-llama2c-to-ggml --vocab-model --llama2c-model --llama2c-output-model ` + +Now you can use the model with command: + +`$ ./main -m -p "One day, Lily met a Shoggoth" -n 500 -c 256 -eps 1e-5` \ No newline at end of file