phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 13:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

issue w/ safety

Browse source
This commit is contained in:
Xi Yan 2024-09-22 23:15:34 -07:00
parent e0ad4fb99c
commit 4586692dee
8 changed files with 50 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

63
tests/examples/router-local-run.yaml
View file

@ -20,40 +20,29 @@ api_providers:
namespace: null
type: sqlite
db_path: /home/xiyan/.llama/runtime/kvstore.db
routing_tables:
models:
entries:
- 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
- routing_key: Meta-Llama3.1-8B
provider_id: meta-reference
config:
model: Meta-Llama3.1-8B
quantization: null
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
memory_banks:
entries:
- routing_key: vector
provider_id: meta-reference
config: {}
shields:
entries:
- routing_key: llama_guard_shield
provider_id: meta-reference
config:
model: Llama-Guard-3-8B
excluded_categories: []
disable_input_check: false
disable_output_check: false
- routing_key: prompt_guard_shield
provider_id: meta-reference
config:
model: Prompt-Guard-86M
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:
model: Llama-Guard-3-8B
excluded_categories: []
disable_input_check: false
disable_output_check: false
- routing_key: prompt_guard
provider_id: meta-reference
config:
model: Prompt-Guard-86M