forked from phoenix-oss/llama-stack-mirror
add embedding model by default to distribution templates (#617)
# What does this PR do? Adds the sentence transformer provider and the `all-MiniLM-L6-v2` embedding model to the default models to register in the run.yaml for all providers. ## Test Plan llama stack build --template together --image-type conda llama stack run ~/.llama/distributions/llamastack-together/together-run.yaml
This commit is contained in:
parent
e893b22868
commit
516e1a3e59
41 changed files with 473 additions and 64 deletions
|
@ -18,6 +18,9 @@ providers:
|
|||
config:
|
||||
url: https://api.together.xyz/v1
|
||||
api_key: ${env.TOGETHER_API_KEY}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
config: {}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
|
@ -74,36 +77,50 @@ metadata_store:
|
|||
models:
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-8B-Instruct
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-70B-Instruct
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.2-3B-Instruct
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-Guard-3-8B
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-Guard-3-11B-Vision
|
||||
provider_id: null
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
|
||||
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
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue