backend: bert-embeddings
embeddings: true
f16: true

gpu_layers: 90
mmap: true
name: text-embedding-ada-002

parameters:
  model: huggingface://mudler/all-MiniLM-L6-v2/ggml-model-q4_0.bin

usage: |
    You can test this model with curl like this:

    curl http://localhost:8080/embeddings -X POST -H "Content-Type: application/json" -d '{
      "input": "Your text string goes here",
      "model": "text-embedding-ada-002"
    }'