enginex-ascend-910-llama.cpp/examples/run/README.md

# llama.cpp/example/run

The purpose of this example is to demonstrate a minimal usage of llama.cpp for running models.

```bash
./llama-run Meta-Llama-3.1-8B-Instruct.gguf
...
Introduce llama-run (#10291) It's like simple-chat but it uses smart pointers to avoid manual memory cleanups. Less memory leaks in the code now. Avoid printing multiple dots. Split code into smaller functions. Uses no exception handling. Signed-off-by: Eric Curtin <ecurtin@redhat.com> 2024-11-25 16:56:24 -05:00			`# llama.cpp/example/run`

			`The purpose of this example is to demonstrate a minimal usage of llama.cpp for running models.`

			```bash
			`./llama-run Meta-Llama-3.1-8B-Instruct.gguf`
			`...`