llama-stack-mirror/llama_stack/templates/hf-serverless/build.yaml
2024-11-12 12:54:44 -08:00

9 lines
364 B
YAML

name: hf-serverless
distribution_spec:
description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
providers:
inference: remote::hf::serverless
memory: inline::faiss
safety: inline::llama-guard
agents: inline::meta-reference
telemetry: inline::meta-reference