phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 09:32:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Start auto-generating { build, run, doc.md } for distributions

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-14 17:44:45 -08:00
parent 20bf2f50c2
commit cfa913fdd5
11 changed files with 362 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

16
distributions/ollama-gpu/run.yaml
View file

@ -13,20 +13,15 @@ apis:
- safety
providers:
inference:
- provider_id: ollama0
- provider_id: ollama
provider_type: remote::ollama
config:
url: http://127.0.0.1:14343
url: ${env.OLLAMA_URL:http://127.0.0.1:11434}
safety:
- provider_id: meta0
provider_type: inline::llama-guard
config:
model: Llama-Guard-3-1B
excluded_categories: []
- provider_id: meta1
provider_type: inline::prompt-guard
config:
model: Prompt-Guard-86M
memory:
- provider_id: meta0
provider_type: inline::meta-reference
@ -43,3 +38,10 @@ providers:
- provider_id: meta0
provider_type: inline::meta-reference
config: {}
models:
- model_id: ${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}
provider_id: ollama
- model_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}
provider_id: ollama
shields:
- shield_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}