Llama

# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.

set -e

read -p "Enter the URL from email: " PRESIGNED_URL
echo ""
read -p "Enter the list of models to download without spaces (7B,13B,70B,7B-chat,13B-chat,70B-chat), or press Enter for all: " MODEL_SIZE
TARGET_FOLDER="." # where all files should end up
mkdir -p ${TARGET_FOLDER}

if [[ $MODEL_SIZE == "" ]]; then
MODEL_SIZE="7B,13B,70B,7B-chat,13B-chat,70B-chat"
fi

echo "Downloading LICENSE and Acceptable Usage Policy"
wget --continue ${PRESIGNED_URL/'*'/"LICENSE"} -O ${TARGET_FOLDER}"/LICENSE"
wget --continue ${PRESIGNED_URL/'*'/"USE_POLICY.md"} -O ${TARGET_FOLDER}"/USE_POLICY.md"

echo "Downloading tokenizer"
wget --continue ${PRESIGNED_URL/'*'/"tokenizer.model"} -O ${TARGET_FOLDER}"/tokenizer.model"
wget --continue ${PRESIGNED_URL/'*'/"tokenizer_checklist.chk"} -O ${TARGET_FOLDER}"/tokenizer_checklist.chk"
CPU_ARCH=$(uname -m)
if [ "$CPU_ARCH" = "arm64" ]; then
(cd ${TARGET_FOLDER} && md5 tokenizer_checklist.chk)
else
(cd ${TARGET_FOLDER} && md5sum -c tokenizer_checklist.chk)
fi

for m in ${MODEL_SIZE//,/ }
do
if [[ $m == "7B" ]]; then
SHARD=0
MODEL_PATH="llama-2-7b"
elif [[ $m == "7B-chat" ]]; then
SHARD=0
MODEL_PATH="llama-2-7b-chat"
elif [[ $m == "13B" ]]; then
SHARD=1
MODEL_PATH="llama-2-13b"
elif [[ $m == "13B-chat" ]]; then
SHARD=1
MODEL_PATH="llama-2-13b-chat"
elif [[ $m == "70B" ]]; then
SHARD=7
MODEL_PATH="llama-2-70b"
elif [[ $m == "70B-chat" ]]; then
SHARD=7
MODEL_PATH="llama-2-70b-chat"
fi

echo "Downloading ${MODEL_PATH}"
mkdir -p ${TARGET_FOLDER}"/${MODEL_PATH}"

for s in $(seq -f "0%g" 0 ${SHARD})
do
wget ${PRESIGNED_URL/'*'/"${MODEL_PATH}/consolidated.${s}.pth"} -O ${TARGET_FOLDER}"/${MODEL_PATH}/consolidated.${s}.pth"
done