fix provider ids for together and fireworks

llama_stack/templates/cerebras/cerebras.py

@@ -46,6 +46,7 @@ def get_distribution_template() -> DistributionTemplate:
         ModelInput(
             model_id=core_model_to_hf_repo[m.llama_model],
             provider_model_id=m.provider_model_id,
+            provider_id="cerebras",
         )
         for m in model_aliases
     ]
@@ -54,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/cerebras/run.yaml

@@ -52,16 +52,16 @@ metadata_store:
 models:
 - metadata: {}
   model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: null
+  provider_id: cerebras
   provider_model_id: llama3.1-8b
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: null
+  provider_id: cerebras
   provider_model_id: llama3.1-70b
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/fireworks/fireworks.py

@@ -57,6 +57,7 @@ def get_distribution_template() -> DistributionTemplate:
         ModelInput(
             model_id=core_model_to_hf_repo[m.llama_model],
             provider_model_id=m.provider_model_id,
+            provider_id="fireworks",
         )
         for m in MODEL_ALIASES
     ]
@@ -65,7 +66,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/fireworks/run.yaml

@@ -77,51 +77,51 @@ metadata_store:
 models:
 - metadata: {}
   model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p1-8b-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p1-70b-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p1-405b-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-1B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-1b-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-3b-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-11b-vision-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-90b-vision-instruct
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-guard-3-8b
   model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-guard-3-11b-vision
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -91,7 +91,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/hf-endpoint/run.yaml

@@ -81,7 +81,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/hf-serverless/hf_serverless.py

@@ -56,7 +56,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -91,7 +91,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/hf-serverless/run.yaml

@@ -81,7 +81,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -59,7 +59,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
     safety_model = ModelInput(

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

@@ -93,7 +93,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -82,7 +82,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py

@@ -62,7 +62,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
     return DistributionTemplate(

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -84,7 +84,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/ollama/ollama.py

@@ -58,7 +58,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/ollama/run-with-safety.yaml

@@ -85,7 +85,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/ollama/run.yaml

@@ -80,7 +80,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -68,7 +68,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/remote-vllm/run.yaml

@@ -57,7 +57,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/remote-vllm/vllm.py

@@ -57,7 +57,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/tgi/run.yaml

@@ -80,7 +80,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/tgi/tgi.py

@@ -56,7 +56,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
     safety_model = ModelInput(

llama_stack/templates/together/run.yaml

@@ -77,46 +77,46 @@ 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_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/together/together.py

@@ -55,6 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
         ModelInput(
             model_id=core_model_to_hf_repo[m.llama_model],
             provider_model_id=m.provider_model_id,
+            provider_id="together",
         )
         for m in MODEL_ALIASES
     ]
@@ -63,7 +64,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )
 

llama_stack/templates/vllm-gpu/run.yaml

@@ -84,7 +84,7 @@ models:
   provider_model_id: null
   model_type: llm
 - metadata:
-    embedding_dim: 384
+    embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
   provider_model_id: null

llama_stack/templates/vllm-gpu/vllm.py

@@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="sentence-transformers",
         model_type=ModelType.embedding,
         metadata={
-            "embedding_dim": 384,
+            "embedding_dimension": 384,
         },
     )