institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1

$ docker login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

export NGC_API_KEY=<PASTE_API_KEY_HERE>
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
docker run -it --rm \
    --gpus all \
    --shm-size=16GB \
    -e NGC_API_KEY \
    -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
    -u $(id -u) \
    -p 8000:8000 \
    nvcr.io/nim/tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.1:latest

curl -X 'POST' \
'http://0.0.0.0:8000/v1/chat/completions' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
    "model": "tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.1",
    "messages": [{"role":"user", "content":"東京の夜空に打ち上がっている花火の下、向かい合っている燕とラマの温かい物語を書いてください。"}],
    "max_tokens": 64
}'