llama-stack/distributions/meta-reference-quantized-gpu/run.yaml
2024-10-24 12:08:56 -07:00

51 lines
1.1 KiB
YAML

version: '2'
built_at: '2024-10-08T17:40:45.325529'
image_name: local
docker_image: null
conda_env: local
apis:
- shields
- agents
- models
- memory
- memory_banks
- inference
- safety
providers:
inference:
- provider_id: meta0
provider_type: meta-reference-quantized
config:
model: Llama3.2-3B-Instruct:int4-qlora-eo8
quantization:
type: int4
torch_seed: null
max_seq_len: 2048
max_batch_size: 1
safety:
- provider_id: meta0
provider_type: meta-reference
config:
llama_guard_shield:
model: Llama-Guard-3-1B
excluded_categories: []
disable_input_check: false
disable_output_check: false
prompt_guard_shield:
model: Prompt-Guard-86M
memory:
- provider_id: meta0
provider_type: meta-reference
config: {}
agents:
- provider_id: meta0
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta0
provider_type: meta-reference
config: {}