llama-stack/distributions/meta-reference-quantized-gpu/run.yaml
Yuan Tang 6da3053c0e
More generic image type for OCI-compliant container technologies (#802)
It's a more generic term and applicable to alternatives of Docker, such
as Podman or other OCI-compliant technologies.

---------

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
2025-01-17 16:37:42 -08:00

58 lines
1.3 KiB
YAML

version: '2'
image_name: local
container_image: null
conda_env: local
apis:
- shields
- agents
- models
- memory
- memory_banks
- inference
- safety
providers:
inference:
- provider_id: meta0
provider_type: inline::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
- provider_id: meta1
provider_type: inline::meta-reference-quantized
config:
# not a quantized model !
model: Llama-Guard-3-1B
quantization: null
torch_seed: null
max_seq_len: 2048
max_batch_size: 1
safety:
- provider_id: meta0
provider_type: inline::llama-guard
config:
model: Llama-Guard-3-1B
excluded_categories: []
- provider_id: meta1
provider_type: inline::prompt-guard
config:
model: Prompt-Guard-86M
memory:
- provider_id: meta0
provider_type: inline::meta-reference
config: {}
agents:
- provider_id: meta0
provider_type: inline::meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta0
provider_type: inline::meta-reference
config: {}