scripts : improve get-wikitext-2.sh (#19952)

* scripts : improve get-wikitext-2.sh

Switch to sh, add curl fallback, and avoid redundant downloads

Signed-off-by: Adrien Gallouët <redacted>
* fix indent

Signed-off-by: Adrien Gallouët <redacted>
---------

Signed-off-by: Adrien Gallouët <redacted>
Signed-off-by: Adrien Gallouët <redacted>

diff --git a/scripts/get-wikitext-2.sh b/scripts/get-wikitext-2.sh
index 67b0b0118b41c29a0fb84c20ab91bbfa3413bf56..bd03ad35263e033bb96c8cd31314ccc422ebddb7 100755 (executable)
--- a/scripts/get-wikitext-2.sh
+++ b/scripts/get-wikitext-2.sh
@@ -1,11 +1,43 @@
-#!/usr/bin/env bash
+#!/bin/sh
+# vim: set ts=4 sw=4 et:
 
-wget https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip
-unzip wikitext-2-raw-v1.zip
+ZIP="wikitext-2-raw-v1.zip"
+FILE="wikitext-2-raw/wiki.test.raw"
+URL="https://huggingface.co/datasets/ggml-org/ci/resolve/main/$ZIP"
 
-echo "Usage:"
-echo ""
-echo "  ./llama-perplexity -m model.gguf -f wikitext-2-raw/wiki.test.raw [other params]"
-echo ""
+die() {
+    printf "%s\n" "$@" >&2
+    exit 1
+}
 
-exit 0
+have_cmd() {
+    for cmd; do
+        command -v "$cmd" >/dev/null || return
+    done
+}
+
+dl() {
+    [ -f "$2" ] && return
+    if have_cmd wget; then
+        wget "$1" -O "$2"
+    elif have_cmd curl; then
+        curl -L "$1" -o "$2"
+    else
+        die "Please install wget or curl"
+    fi
+}
+
+have_cmd unzip || die "Please install unzip"
+
+if [ ! -f "$FILE" ]; then
+    dl "$URL" "$ZIP" || exit
+    unzip -o "$ZIP"  || exit
+    rm -f -- "$ZIP"
+fi
+
+cat <<EOF
+Usage:
+
+  llama-perplexity -m model.gguf -f $FILE [other params]
+
+EOF