Skip to content

scripts : add hf.sh helper script #5501

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Feb 15, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
107 changes: 107 additions & 0 deletions scripts/hf.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,107 @@
#!/bin/bash
#
# Shortcut for downloading HF models
#
# Usage:
# ./main -m $(./examples/hf.sh https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/resolve/main/mixtral-8x7b-v0.1.Q4_K_M.gguf)
# ./main -m $(./examples/hf.sh --url https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_M.gguf)
# ./main -m $(./examples/hf.sh --repo TheBloke/Mixtral-8x7B-v0.1-GGUF --file mixtral-8x7b-v0.1.Q4_K_M.gguf)
#

# all logs go to stderr
function log {
echo "$@" 1>&2
}

function usage {
log "Usage: $0 [[--url] <url>] [--repo <repo>] [--file <file>] [-h|--help]"
exit 1
}

# check for curl or wget
function has_cmd {
if ! [ -x "$(command -v $1)" ]; then
return 1
fi
}

if has_cmd wget; then
cmd="wget -q --show-progress -c -O %s %s"
elif has_cmd curl; then
cmd="curl -C - -f -o %s -L %s"
else
log "[E] curl or wget not found"
exit 1
fi

url=""
repo=""
file=""

# parse args
while [[ $# -gt 0 ]]; do
case "$1" in
--url)
url="$2"
shift 2
;;
--repo)
repo="$2"
shift 2
;;
--file)
file="$2"
shift 2
;;
-h|--help)
usage
;;
*)
url="$1"
shift
;;
esac
done

if [ -n "$repo" ] && [ -n "$file" ]; then
url="https://huggingface.co/$repo/resolve/main/$file"
fi

if [ -z "$url" ]; then
log "[E] missing --url"
usage
fi

# check if the URL is a HuggingFace model, and if so, try to download it
is_url=false

if [[ ${#url} -gt 22 ]]; then
if [[ ${url:0:22} == "https://huggingface.co" ]]; then
is_url=true
fi
fi

if [ "$is_url" = false ]; then
log "[E] invalid URL, must start with https://huggingface.co"
exit 0
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

a log could be added here? otherwise non-HF/mistyped URIs will quit silently

fi

# replace "blob/main" with "resolve/main"
url=${url/blob\/main/resolve\/main}

basename=$(basename $url)

log "[+] attempting to download $basename"

if [ -n "$cmd" ]; then
cmd=$(printf "$cmd" "$basename" "$url")
log "[+] $cmd"
if $cmd; then
echo $basename
exit 0
fi
fi

log "[-] failed to download"

exit 1