alias groq models to their HF aliases

docs/source/distributions/self_hosted_distro/groq.md

@@ -37,11 +37,11 @@ The following environment variables can be configured:
 
 The following models are available by default:
 
-- `groq/llama3-8b-8192 `
+- `groq/llama3-8b-8192 (aliases: meta-llama/Llama-3.1-8B-Instruct)`
 - `groq/llama-3.1-8b-instant `
-- `groq/llama3-70b-8192 `
+- `groq/llama3-70b-8192 (aliases: meta-llama/Llama-3-70B-Instruct)`
-- `groq/llama-3.3-70b-versatile `
+- `groq/llama-3.3-70b-versatile (aliases: meta-llama/Llama-3.3-70B-Instruct)`
-- `groq/llama-3.2-3b-preview `
+- `groq/llama-3.2-3b-preview (aliases: meta-llama/Llama-3.2-3B-Instruct)`
 
 
 ### Prerequisite: API Keys

llama_stack/providers/remote/inference/groq/models.py

@@ -5,10 +5,13 @@
 # the root directory of this source tree.
 
 from llama_stack.models.llama.sku_list import CoreModelId
-from llama_stack.providers.utils.inference.model_registry import build_model_entry
+from llama_stack.providers.utils.inference.model_registry import (
+    build_hf_repo_model_entry,
+    build_model_entry,
+)
 
 MODEL_ENTRIES = [
-    build_model_entry(
+    build_hf_repo_model_entry(
         "groq/llama3-8b-8192",
         CoreModelId.llama3_1_8b_instruct.value,
     ),
@@ -16,11 +19,11 @@ MODEL_ENTRIES = [
         "groq/llama-3.1-8b-instant",
         CoreModelId.llama3_1_8b_instruct.value,
     ),
-    build_model_entry(
+    build_hf_repo_model_entry(
         "groq/llama3-70b-8192",
         CoreModelId.llama3_70b_instruct.value,
     ),
-    build_model_entry(
+    build_hf_repo_model_entry(
         "groq/llama-3.3-70b-versatile",
         CoreModelId.llama3_3_70b_instruct.value,
     ),
@@ -28,7 +31,7 @@ MODEL_ENTRIES = [
     # Preview models aren't recommended for production use, but we include this one
     # to pass the test fixture
     # TODO(aidand): Replace this with a stable model once Groq supports it
-    build_model_entry(
+    build_hf_repo_model_entry(
         "groq/llama-3.2-3b-preview",
         CoreModelId.llama3_2_3b_instruct.value,
     ),

llama_stack/templates/dev/run.yaml

@@ -301,6 +301,11 @@ models:
   provider_id: groq
   provider_model_id: groq/llama3-8b-8192
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama3-8b-8192
+  model_type: llm
 - metadata: {}
   model_id: groq/llama-3.1-8b-instant
   provider_id: groq
@@ -311,16 +316,31 @@ models:
   provider_id: groq
   provider_model_id: groq/llama3-70b-8192
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3-70B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama3-70b-8192
+  model_type: llm
 - metadata: {}
   model_id: groq/llama-3.3-70b-versatile
   provider_id: groq
   provider_model_id: groq/llama-3.3-70b-versatile
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-3.3-70b-versatile
+  model_type: llm
 - metadata: {}
   model_id: groq/llama-3.2-3b-preview
   provider_id: groq
   provider_model_id: groq/llama-3.2-3b-preview
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-3.2-3b-preview
+  model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2

llama_stack/templates/groq/run.yaml

@@ -95,6 +95,11 @@ models:
   provider_id: groq
   provider_model_id: groq/llama3-8b-8192
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama3-8b-8192
+  model_type: llm
 - metadata: {}
   model_id: groq/llama-3.1-8b-instant
   provider_id: groq
@@ -105,16 +110,31 @@ models:
   provider_id: groq
   provider_model_id: groq/llama3-70b-8192
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3-70B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama3-70b-8192
+  model_type: llm
 - metadata: {}
   model_id: groq/llama-3.3-70b-versatile
   provider_id: groq
   provider_model_id: groq/llama-3.3-70b-versatile
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-3.3-70b-versatile
+  model_type: llm
 - metadata: {}
   model_id: groq/llama-3.2-3b-preview
   provider_id: groq
   provider_model_id: groq/llama-3.2-3b-preview
   model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-3.2-3b-preview
+  model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2