From f49a7ac7c453669a73a960cae498b34b104293f7 Mon Sep 17 00:00:00 2001 From: eastriver Date: Sat, 27 Jan 2024 06:42:16 +0900 Subject: [PATCH] Update README.md --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index d913e86..41b84d2 100644 --- a/README.md +++ b/README.md @@ -56,6 +56,13 @@ dependencies: [ ], ``` +optionally, if you care more about stability rather than benefitting from speed of [`llama.cpp`](https://github.com/ggerganov/llama.cpp)'s development cycle you can choose the `pinned` branch with pinned dependency. +```swift +dependencies: [ + .package(url: "https://github.com/eastriverlee/LLM.swift/", branch: "pinned"), +], +``` + ## Overview `LLM.swift` is basically a lightweight abstraction layer over [`llama.cpp`](https://github.com/ggerganov/llama.cpp) package, so that it stays as performant as possible while is always up to date. so theoretically, any model that works on [`llama.cpp`](https://github.com/ggerganov/llama.cpp) should work with this library as well. It's only a single file library, so you can copy, study and modify the code however you want.