version: '2'
image_name: meta-reference-quantized-gpu
docker_image: null
conda_env: meta-reference-quantized-gpu
apis:
- agents
- datasetio
- eval
- inference
- memory
- safety
- scoring
- telemetry
providers:
  inference:
  - provider_id: meta-reference-inference
    provider_type: inline::meta-reference-quantized
    config:
      model: ${env.INFERENCE_MODEL}
      max_seq_len: 4096
      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
      quantization:
        type: fp8
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
  memory:
  - provider_id: faiss
    provider_type: inline::faiss
    config:
      kvstore:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/faiss_store.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config: {}
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence_store:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/agents_store.db
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-quantized-gpu/trace_store.db}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config: {}
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config: {}
  - provider_id: localfs
    provider_type: inline::localfs
    config: {}
  scoring:
  - provider_id: basic
    provider_type: inline::basic
    config: {}
  - provider_id: llm-as-judge
    provider_type: inline::llm-as-judge
    config: {}
  - provider_id: braintrust
    provider_type: inline::braintrust
    config:
      openai_api_key: ${env.OPENAI_API_KEY:}
metadata_store:
  namespace: null
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db
models:
- metadata: {}
  model_id: ${env.INFERENCE_MODEL}
  provider_id: meta-reference-inference
  provider_model_id: null
  model_type: llm
- metadata:
    embedding_dimension: 384
  model_id: all-MiniLM-L6-v2
  provider_id: sentence-transformers
  provider_model_id: null
  model_type: embedding
shields: []
memory_banks: []
datasets: []
scoring_fns: []
eval_tasks: []