version: '2'
built_at: '2024-10-08T17:42:33.690666'
image_name: local-gpu
docker_image: local-gpu
conda_env: null
apis:
- memory
- inference
- agents
- shields
- safety
- models
- memory_banks
providers:
  inference:
  - provider_id: meta-reference
    provider_type: meta-reference
    config:
      model: Llama3.1-8B-Instruct
      quantization: null
      torch_seed: null
      max_seq_len: 4096
      max_batch_size: 1
  safety:
  - provider_id: meta-reference
    provider_type: meta-reference
    config:
      llama_guard_shield: null
      prompt_guard_shield: null
  memory:
  - provider_id: meta-reference
    provider_type: meta-reference
    config: {}
  agents:
  - provider_id: meta-reference
    provider_type: meta-reference
    config:
      persistence_store:
        namespace: null
        type: sqlite
        db_path: ~/.llama/runtime/kvstore.db
  telemetry:
  - provider_id: meta-reference
    provider_type: meta-reference
    config: {}
models:
- identifier: Llama3.1-8B-Instruct
  llama_model: Llama3.1-8B-Instruct
  provider_id: meta-reference
shields:
- identifier: llama_guard
  type: llama_guard
  provider_id: meta-reference
  params: {}
memory_banks:
- identifier: vector
  provider_id: meta-reference
  type: vector
  embedding_model: all-MiniLM-L6-v2
  chunk_size_in_tokens: 512
  overlap_size_in_tokens: null