Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: add nemo retriever text embedding models to nvidia inference provider #1218

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+67 −6
Open

feat: add nemo retriever text embedding models to nvidia inference provider #1218

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion docs/source/distributions/remote_hosted_distro/nvidia.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,10 @@ The following models are available by default:
- `meta-llama/Llama-3.2-3B-Instruct (meta/llama-3.2-3b-instruct)`
- `meta-llama/Llama-3.2-11B-Vision-Instruct (meta/llama-3.2-11b-vision-instruct)`
- `meta-llama/Llama-3.2-90B-Vision-Instruct (meta/llama-3.2-90b-vision-instruct)`
- `baai/bge-m3 (baai/bge-m3)`
- `nvidia/llama-3.2-nv-embedqa-1b-v2 (nvidia/llama-3.2-nv-embedqa-1b-v2)`
- `nvidia/nv-embedqa-e5-v5 (nvidia/nv-embedqa-e5-v5)`
- `nvidia/nv-embedqa-mistral-7b-v2 (nvidia/nv-embedqa-mistral-7b-v2)`
- `snowflake/arctic-embed-l (snowflake/arctic-embed-l)`


### Prerequisite: API Keys
Expand Down
41 changes: 39 additions & 2 deletions llama_stack/providers/remote/inference/nvidia/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,14 +48,51 @@
"meta/llama-3.2-90b-vision-instruct",
CoreModelId.llama3_2_90b_vision_instruct.value,
),
# NeMo Retriever Text Embedding models -
#
# https://docs.nvidia.com/nim/nemo-retriever/text-embedding/latest/support-matrix.html
#
# +-----------------------------------+--------+-----------+-----------+------------+
# | Model ID | Max | Publisher | Embedding | Dynamic |
# | | Tokens | | Dimension | Embeddings |
# +-----------------------------------+--------+-----------+-----------+------------+
# | nvidia/llama-3.2-nv-embedqa-1b-v2 | 8192 | NVIDIA | 2048 | Yes |
# | nvidia/nv-embedqa-e5-v5 | 512 | NVIDIA | 1024 | No |
# | nvidia/nv-embedqa-mistral-7b-v2 | 512 | NVIDIA | 4096 | No |
# | snowflake/arctic-embed-l | 512 | Snowflake | 1024 | No |
# +-----------------------------------+--------+-----------+-----------+------------+
ProviderModelEntry(
provider_model_id="baai/bge-m3",
provider_model_id="nvidia/llama-3.2-nv-embedqa-1b-v2",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 1024,
"embedding_dimension": 2048,
"context_length": 8192,
},
),
ProviderModelEntry(
provider_model_id="nvidia/nv-embedqa-e5-v5",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 1024,
"context_length": 512,
},
),
ProviderModelEntry(
provider_model_id="nvidia/nv-embedqa-mistral-7b-v2",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 4096,
"context_length": 512,
},
),
ProviderModelEntry(
provider_model_id="snowflake/arctic-embed-l",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 1024,
"context_length": 512,
},
),
# TODO(mf): how do we handle Nemotron models?
# "Llama3.1-Nemotron-51B-Instruct" -> "meta/llama-3.1-nemotron-51b-instruct",
]
27 changes: 24 additions & 3 deletions llama_stack/templates/nvidia/run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,11 +136,32 @@ models:
provider_model_id: meta/llama-3.2-90b-vision-instruct
model_type: llm
- metadata:
embedding_dimension: 1024
embedding_dimension: 2048
context_length: 8192
model_id: baai/bge-m3
model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
provider_id: nvidia
provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: nvidia/nv-embedqa-e5-v5
provider_id: nvidia
provider_model_id: nvidia/nv-embedqa-e5-v5
model_type: embedding
- metadata:
embedding_dimension: 4096
context_length: 512
model_id: nvidia/nv-embedqa-mistral-7b-v2
provider_id: nvidia
provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: snowflake/arctic-embed-l
provider_id: nvidia
provider_model_id: baai/bge-m3
provider_model_id: snowflake/arctic-embed-l
model_type: embedding
shields: []
vector_dbs: []
Expand Down
Loading