llama-stack/llama_stack/templates/together/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

114 lines
3.1 KiB
YAML

version: '2'
image_name: together
docker_image: null
conda_env: together
apis:
- agents
- datasetio
- eval
- inference
- memory
- safety
- scoring
- telemetry
providers:
inference:
- provider_id: together
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
memory:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/faiss_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
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/together}/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/together/trace_store.db}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
- provider_id: localfs
provider_type: inline::localfs
config: {}
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config: {}
metadata_store:
namespace: null
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
models:
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: null
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: null
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
- metadata: {}
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: null
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: null
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: null
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: null
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: null
provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
- metadata: {}
model_id: meta-llama/Llama-Guard-3-11B-Vision
provider_id: null
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
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: []