Getting error : Unsupported storage type LongStorage #37
Description
System Info
I ma using T4 GPU, and building the docker image with -
model=sentence-transformers/all-MiniLM-L6-v2
revision=main
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all -p 8080:80 -v $volume:/data --pull alwaysghcr.io/huggingface/text-embeddings-inference:turing-0.2.2 --model-id $model --revision $revision
Returns embeddings as -
[[null, null, null................................................................................., null]]
Information
- Docker
- The CLI directly
Tasks
- An officially supported command
- My own modifications
Reproduction
When running the docker for model - sentence-transformers/all-MiniLM-L6-v2, I am getting the error :
skipping embeddinggs.position_ids: Msg("Unsupported storage type LongStorage")
model=sentence-transformers/all-MiniLM-L6-v2
revision=main
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all -p 8080:80 -v $volume:/data --pull alwaysghcr.io/huggingface/text-embeddings-inference:turing-0.2.2 --model-id $model --revision $revision
Expected behavior
On running curl request, a list of embeddings should have been returned. However, now just a list of null values is being returned, on the curl request-
curl 127.0.0.1:8080/embed \
-X POST \
-d '{"inputs":"What is Deep Learning?"}' \
-H 'Content-Type: application/json'