embedded/models/bert-cpp.yaml

backend: bert-embeddings
embeddings: true
f16: true

gpu_layers: 90
mmap: true
name: bert-cpp-minilm-v6

parameters:
  model: bert-MiniLM-L6-v2q4_0.bin

download_files:
- filename: "bert-MiniLM-L6-v2q4_0.bin"
  sha256: "a5a174d8772c8a569faf9f3136c441f2c3855b5bf35ed32274294219533feaad"
  uri: "https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/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": "bert-cpp-minilm-v6"
    }'