[PR PATCH] new package: alpaca.cpp

[atk <atk@users.noreply.github.com>]

[-- Attachment #1: Type: text/plain, Size: 1084 bytes --]

There is a new pull request by atk against master on the void-packages repository

https://github.com/atk/void-packages alpaca.cpp
https://github.com/void-linux/void-packages/pull/43080

new package: alpaca.cpp
<!-- Uncomment relevant sections and delete options which are not applicable -->

#### Testing the changes
- I tested the changes in this PR: **YES**

#### New package
- This new package conforms to the [package requirements](https://github.com/void-linux/void-packages/blob/master/CONTRIBUTING.md#package-requirements): **YES**

<!-- Note: If the build is likely to take more than 2 hours, please add ci skip tag as described in
https://github.com/void-linux/void-packages/blob/master/CONTRIBUTING.md#continuous-integration
and test at least one native build and, if supported, at least one cross build.
Ignore this section if this PR is not skipping CI.
-->

#### Local build testing
- I built this PR locally for my native architecture, (ARCH-LIBC) x86_64+glibc


A patch file from https://github.com/void-linux/void-packages/pull/43080.patch is attached

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: github-pr-alpaca.cpp-43080.patch --]
[-- Type: text/x-diff, Size: 1858 bytes --]

From 5df7480d0b1fefba17aef8c32f6b7d7b9d1aadf5 Mon Sep 17 00:00:00 2001
From: Alex Lohr <alex.lohr@logmein.com>
Date: Tue, 28 Mar 2023 22:11:08 +0200
Subject: [PATCH] new package: alpaca.cpp

---
 srcpkgs/alpaca.cpp/INSTALL.msg | 10 ++++++++++
 srcpkgs/alpaca.cpp/template    | 20 ++++++++++++++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 srcpkgs/alpaca.cpp/INSTALL.msg
 create mode 100644 srcpkgs/alpaca.cpp/template

diff --git a/srcpkgs/alpaca.cpp/INSTALL.msg b/srcpkgs/alpaca.cpp/INSTALL.msg
new file mode 100644
index 000000000000..16f108863275
--- /dev/null
+++ b/srcpkgs/alpaca.cpp/INSTALL.msg
@@ -0,0 +1,10 @@
+To use alpaca.cpp, you need to download a ggml model.
+
+A pre-trained model (~4GB) with 7 billion quantifiers can be downloaded at 
+https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/resolve/main/ggml-alpaca-7b-q4.bin
+
+A pre-trained model (~7.6GB) with 13 billion quantifiers is located at
+https://gateway.estuary.tech/gw/ipfs/Qme6wyw9MzqbrUMpFNVq42rC1kSdko7MGT9CL7o1u9Cv9G
+
+To run alpaca.cpp, call
+$ alpaca-chat -m [insert model]
diff --git a/srcpkgs/alpaca.cpp/template b/srcpkgs/alpaca.cpp/template
new file mode 100644
index 000000000000..869bc36f833c
--- /dev/null
+++ b/srcpkgs/alpaca.cpp/template
@@ -0,0 +1,20 @@
+# Template file for 'alpaca.cpp'
+pkgname=alpaca.cpp
+version=9116ae9
+revision=1
+short_desc="Locally run an Instruction-Tuned Chat-Style LLM"
+maintainer="Alex Lohr <alex.lohr@logmein.com>"
+license="MIT"
+homepage="https://github.com/antimatter15/alpaca.cpp"
+changelog="https://github.com/antimatter15/alpaca.cpp/releases"
+distfiles="https://github.com/antimatter15/${pkgname}/archive/refs/tags/${version}.tar.gz"
+checksum=f8faab389abe214ba7c828b592c274e8e017f0e7f69c4265dde38f542e8b0092
+
+do_build() {
+	make chat
+}
+
+do_install() {
+	vbin chat alpaca-chat
+	vlicense LICENSE
+}