forked from phoenix-oss/llama-stack-mirror
0e2a99e223
# What does this PR do? Cerebras is rolling out support for llama 3.3 70b and deprecating llama 3.1 70b. This PR updates the documentation, config, and internal mapping to reflect this change. cc: @ashwinb @raghotham
77 lines
2 KiB
YAML
77 lines
2 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}
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
config: {}
|
|
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: cerebras
|
|
provider_model_id: llama3.1-8b
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.3-70B-Instruct
|
|
provider_id: cerebras
|
|
provider_model_id: llama-3.3-70b
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
provider_model_id: null
|
|
model_type: embedding
|
|
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: []
|