version: '2'
image_name: meta-reference-quantized-gpu
docker_image: null
conda_env: meta-reference-quantized-gpu
apis:
- agents
- inference
- memory
- safety
- 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
  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: {}
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
shields: []
memory_banks: []
datasets: []
scoring_fns: []
eval_tasks: []