1services:
2 splade-jp-v1:
3 # image の部分はアーキテクチャにあったものに変えること
4 image: ghcr.io/huggingface/text-embeddings-inference:86-1.5
5 ports:
6 - "8080:80"
7 volumes:
8 - /tmp/docker-tei-data:/data
9 command: [ "--model-id", "hotchpotch/japanese-splade-base-v1-dummy-fast-tokenizer-for-tei", "--dtype", "float16", "--pooling", "splade"]
10 deploy:
11 resources:
12 reservations:
13 devices:
14 - driver: nvidia
15 count: 1
16 capabilities: [ gpu ]