llama-stack/llama_stack/templates/cerebras/run.yaml
Ashwin Bharambe e951852848 Miscellaneous fixes around telemetry, library client and run yaml autogen
Also add a `venv` image-type for llama stack build
2024-12-08 20:40:22 -08:00

66 lines
1.7 KiB
YAML

version: '2'
image_name: cerebras
docker_image: null
conda_env: cerebras
apis:
- agents
- inference
- memory
- safety
- telemetry
providers:
inference:
- provider_id: cerebras
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
api_key: ${env.CEREBRAS_API_KEY}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
memory:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/faiss_store.db
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/cerebras/trace_store.db}
metadata_store:
namespace: null
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/registry.db
models:
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: null
provider_model_id: llama3.1-8b
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: null
provider_model_id: llama3.1-70b
shields:
- params: null
shield_id: meta-llama/Llama-Guard-3-8B
provider_id: null
provider_shield_id: null
memory_banks: []
datasets: []
scoring_fns: []
eval_tasks: []