## SERVE EMBEDDING MODEL

## MODELS

    1-GEMMA-300M model : gemma
    2-GEMMA-300M model fine-tuned : gemma_train
    3-BGE-M3 model fine-tuned : bge_train

## HOW TO RUN

    docker build -f Dockerfile -t serve_embed:latest .
    docker run -d --gpus all --network host --restart unless-stopped serve_embed:latest

## port 
    3037

## domain
    https://embed.models.aiengines.ir/