phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-20 10:36:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add embedding model by default

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-12 14:46:51 -08:00
parent 2a9b13dd52
commit 2f88006bd0
43 changed files with 446 additions and 85 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -19,6 +19,9 @@ providers:
model: ${env.INFERENCE_MODEL}
max_seq_len: 4096
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
- provider_id: meta-reference-safety
provider_type: inline::meta-reference
config:
@ -83,10 +86,18 @@ models:
model_id: ${env.INFERENCE_MODEL}
provider_id: meta-reference-inference
provider_model_id: null
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL}
provider_id: meta-reference-safety
provider_model_id: null
model_type: llm
- metadata:
embedding_dim: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
provider_model_id: null
model_type: embedding
shields:
- params: null
shield_id: ${env.SAFETY_MODEL}