You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
According to the Air gapped deployment section in the readme, you should probably use the path as model id.
Maybe something like MODEL_ID=/data/models/bge-m3 ?
System Info
Information
Tasks
Reproduction
docker run -d \ --name text-embedding-service \ --restart always \ --gpus all \ -p 8082:80 \ -v /data/models/bge-m3:/data/ \ -v /data/models/.cache:/root/.cache \ -e MODEL_ID=BAAI/bge-m3 \ -e TOKENIZATION_WORKERS=10 \ -e MAX_BATCH_REQUESTS=10 \ -e MAX_CLIENT_BATCH_SIZE=500 \ -e HOSTNAME=0.0.0.0 \ ghcr.io/huggingface/text-embeddings-inference:1.5
Expected behavior
If I download the model and mounted, there is no need to download it again.
The text was updated successfully, but these errors were encountered: