docker run \
-p 8080:80 \
-v $(pwd)/data:/data \
--privileged \
ghcr.io/huggingface/neuronx-tgi:latest \
--model-id /data/AWS-Neuron-llama-3-Korean-Bllossom-8B

curl 127.0.0.1:8080/generate \
-X POST \
-d '{"inputs":"딥러닝이 뭐야?","parameters":{"max_new_tokens":512}}' \
-H 'Content-Type: application/json'

curl localhost:8080/v1/chat/completions \
    -X POST \
    -d '{
"model": "tgi",
"messages": [
    {
    "role": "system",
    "content": "당신은 인공지능 전문가 입니다."
    },
    {
    "role": "user",
    "content": "딥러닝이 무엇입니까?"
    }
],
"stream": false,
"max_tokens": 512
}' \
    -H 'Content-Type: application/json'