mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
78 lines
1.9 KiB
YAML
78 lines
1.9 KiB
YAML
built_at: '2024-09-18T13:41:17.656743'
|
|
image_name: local
|
|
docker_image: null
|
|
conda_env: local
|
|
apis_to_serve:
|
|
- inference
|
|
- memory
|
|
- telemetry
|
|
- agents
|
|
- safety
|
|
- models
|
|
api_providers:
|
|
inference:
|
|
providers:
|
|
- meta-reference
|
|
- remote::ollama
|
|
memory:
|
|
providers:
|
|
- meta-reference
|
|
- remote::pgvector
|
|
safety:
|
|
providers:
|
|
- meta-reference
|
|
telemetry:
|
|
provider_id: meta-reference
|
|
config: {}
|
|
agents:
|
|
provider_id: meta-reference
|
|
config:
|
|
persistence_store:
|
|
namespace: null
|
|
type: sqlite
|
|
db_path: /home/xiyan/.llama/runtime/kvstore.db
|
|
routing_table:
|
|
inference:
|
|
- routing_key: Meta-Llama3.1-8B-Instruct
|
|
provider_id: meta-reference
|
|
config:
|
|
model: Meta-Llama3.1-8B-Instruct
|
|
quantization: null
|
|
torch_seed: null
|
|
max_seq_len: 4096
|
|
max_batch_size: 1
|
|
memory:
|
|
- routing_key: vector
|
|
provider_id: meta-reference
|
|
config: {}
|
|
safety:
|
|
- routing_key: llama_guard
|
|
provider_id: meta-reference
|
|
config:
|
|
llama_guard_shield:
|
|
model: Llama-Guard-3-8B
|
|
excluded_categories: []
|
|
disable_input_check: false
|
|
disable_output_check: false
|
|
prompt_guard_shield:
|
|
model: Prompt-Guard-86M
|
|
- routing_key: prompt_guard
|
|
provider_id: meta-reference
|
|
config:
|
|
llama_guard_shield:
|
|
model: Llama-Guard-3-8B
|
|
excluded_categories: []
|
|
disable_input_check: false
|
|
disable_output_check: false
|
|
prompt_guard_shield:
|
|
model: Prompt-Guard-86M
|
|
- routing_key: injection_shield
|
|
provider_id: meta-reference
|
|
config:
|
|
llama_guard_shield:
|
|
model: Llama-Guard-3-8B
|
|
excluded_categories: []
|
|
disable_input_check: false
|
|
disable_output_check: false
|
|
prompt_guard_shield:
|
|
model: Prompt-Guard-86M
|