mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
67 lines
1.6 KiB
YAML
67 lines
1.6 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
|
|
provider_map:
|
|
telemetry:
|
|
provider_id: meta-reference
|
|
config: {}
|
|
# safety:
|
|
# 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
|
|
# inference:
|
|
# provider_id: meta-reference
|
|
# config:
|
|
# model: Meta-Llama3.1-8B-Instruct
|
|
# quantization: null
|
|
# torch_seed: null
|
|
# max_seq_len: 4096
|
|
# max_batch_size: 1
|
|
# inference:
|
|
# provider_id: remote::ollama
|
|
# config:
|
|
# url: https:ollama-1.com
|
|
# agents:
|
|
# provider_id: meta-reference
|
|
# config: {}
|
|
provider_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
|
|
- routing_key: Meta-Llama3.1-8B
|
|
provider_id: remote::ollama
|
|
config:
|
|
url: https:://ollama.com
|
|
|
|
# memory:
|
|
# - routing_key: keyvalue
|
|
# provider_id: remote::pgvector
|
|
# config:
|
|
# host: localhost
|
|
# port: 5432
|
|
# db: vectordb
|
|
# user: vectoruser
|
|
# password: xxxx
|
|
# - routing_key: vector
|
|
# provider_id: meta-reference
|
|
# config: {}
|