Skip to content

Instantly share code, notes, and snippets.

@1a1a11a
Last active July 11, 2023 19:47
Show Gist options
  • Save 1a1a11a/65be1a8623a6c32c91668c1058c9172e to your computer and use it in GitHub Desktop.
Save 1a1a11a/65be1a8623a6c32c91668c1058c9172e to your computer and use it in GitHub Desktop.
download_llama
#!/bin/bash
set -eux
PRESIGNED_URL="https://agi.gpt4.org/llama/LLaMA/*"
MODEL_SIZE="7B,13B,30B,65B" # edit this list with the model sizes you wish to download
TARGET_FOLDER="models/" # where all files should end up
mkdir -p ${TARGET_FOLDER} || true
declare -A N_SHARD_DICT
N_SHARD_DICT["7B"]="0"
N_SHARD_DICT["13B"]="1"
N_SHARD_DICT["30B"]="3"
N_SHARD_DICT["65B"]="7"
echo "Downloading tokenizer"
wget ${PRESIGNED_URL/'*'/"tokenizer.model"} -O ${TARGET_FOLDER}"/tokenizer.model"
wget ${PRESIGNED_URL/'*'/"tokenizer_checklist.chk"} -O ${TARGET_FOLDER}"/tokenizer_checklist.chk"
(cd ${TARGET_FOLDER} && md5sum -c tokenizer_checklist.chk)
for i in ${MODEL_SIZE//,/ }; do
echo "Downloading ${i}"
mkdir -p ${TARGET_FOLDER}"/${i}"
for s in $(seq -f "0%g" 0 ${N_SHARD_DICT[$i]}); do
echo wget ${PRESIGNED_URL/'*'/"${i}/consolidated.${s}.pth"} -O ${TARGET_FOLDER}"/${i}/consolidated.${s}.pth" >> /tmp/task;
done
wget ${PRESIGNED_URL/'*'/"${i}/params.json"} -O ${TARGET_FOLDER}"/${i}/params.json"
wget ${PRESIGNED_URL/'*'/"${i}/checklist.chk"} -O ${TARGET_FOLDER}"/${i}/checklist.chk"
done
sudo apt-get install -yqq parallel;
parallel -j4 < /tmp/task;
echo "Checking checksums"
for i in ${MODEL_SIZE//,/ };
(cd ${TARGET_FOLDER}"/${i}" && md5sum -c checklist.chk)
done
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment