[helm] Sync values.yaml models with config/models

charts/ome-serving/values.yaml

@@ -204,15 +204,6 @@ models:
     runtime:
       gpus: 1
 
-  deepseek-rdma:
-    enabled: false
-    createRuntime: true
-    vendor: other
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: deepseek-rdma
-    runtime:
-      gpus: 1
-
   deepseek-v2-lite-chat:
     enabled: false
     createRuntime: true
@@ -420,24 +411,6 @@ models:
     runtime:
       gpus: 4
 
-  gpt-oss-120b-bf16:
-    enabled: false
-    createRuntime: true
-    vendor: lmsys
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: lmsys/gpt-oss-120b-bf16
-    runtime:
-      gpus: 8
-
-  gpt-oss-120b-grpc:
-    enabled: false
-    createRuntime: true
-    vendor: openai
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: openai/gpt-oss-120b
-    runtime:
-      gpus: 2
-
   gpt-oss-20b:
     enabled: false
     createRuntime: true
@@ -447,24 +420,6 @@ models:
     runtime:
       gpus: 2
 
-  gpt-oss-20b-bf16:
-    enabled: false
-    createRuntime: true
-    vendor: lmsys
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: lmsys/gpt-oss-20b-bf16
-    runtime:
-      gpus: 2
-
-  gpt-oss-20b-grpc:
-    enabled: false
-    createRuntime: true
-    vendor: openai
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: openai/gpt-oss-20b
-    runtime:
-      gpus: 1
-
   granite-3-0-3b-a800m-instruct:
     enabled: false
     createRuntime: true
@@ -609,7 +564,7 @@ models:
     runtime:
       gpus: 4
 
-  llama-2-13b:
+  llama-2-13b-hf:
     enabled: false
     createRuntime: true
     vendor: meta
@@ -627,7 +582,7 @@ models:
     runtime:
       gpus: 1
 
-  llama-2-70b:
+  llama-2-70b-hf:
     enabled: false
     createRuntime: true
     vendor: meta
@@ -690,15 +645,6 @@ models:
     runtime:
       gpus: 1
 
-  llama-3-1-8b-instruct-grpc:
-    enabled: false
-    createRuntime: true
-    vendor: meta
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: meta-llama/Llama-3.1-8B-Instruct
-    runtime:
-      gpus: 1
-
   llama-3-1-nemotron-70b-instruct-hf:
     enabled: false
     createRuntime: true
@@ -834,24 +780,6 @@ models:
     runtime:
       gpus: 8
 
-  llama-4-maverick-17b-128e-instruct-fp8-grpc:
-    enabled: false
-    createRuntime: true
-    vendor: meta
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-    runtime:
-      gpus: 8
-
-  llama-4-maverick-17b-128e-instruct-fp8-pd-grpc:
-    enabled: false
-    createRuntime: true
-    vendor: meta
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-    runtime:
-      gpus: 8
-
   llama-4-scout-17b-16e-instruct:
     enabled: false
     createRuntime: true
@@ -951,23 +879,14 @@ models:
     runtime:
       gpus: 4
 
-  mistral-7b-instruct:
-    enabled: false
-    createRuntime: true
-    vendor: mistral
-    capabilities: [TEXT_TO_TEXT]
-    hfModelId: mistralai/Mistral-7B-Instruct-v0.2
-    runtime:
-      gpus: 2
-
   mistral-7b-instruct-v0-2:
     enabled: false
     createRuntime: true
     vendor: mistral
     capabilities: [TEXT_TO_TEXT]
     hfModelId: mistralai/Mistral-7B-Instruct-v0.2
     runtime:
-      gpus: 1
+      gpus: 2
 
   mistral-7b-instruct-v0-3:
     enabled: false
@@ -996,7 +915,7 @@ models:
     runtime:
       gpus: 2
 
-  mixtral-8x22b:
+  mixtral-8x22b-v0-1:
     enabled: false
     createRuntime: true
     vendor: mistral
@@ -1005,7 +924,7 @@ models:
     runtime:
       gpus: 8
 
-  mixtral-8x7b:
+  mixtral-8x7b-v0-1:
     enabled: false
     createRuntime: true
     vendor: mistral
@@ -1014,7 +933,7 @@ models:
     runtime:
       gpus: 4
 
-  mixtral-8x7b-instruct:
+  mixtral-8x7b-instruct-v0-1:
     enabled: false
     createRuntime: true
     vendor: mistral

config/models/Qwen/Qwen1.5-110B-Chat.yaml

@@ -0,0 +1,23 @@
+apiVersion: ome.io/v1beta1
+kind: ClusterBaseModel
+metadata:
+  name: qwen1-5-110b-chat
+spec:
+  modelCapabilities:
+    - TEXT_TO_TEXT
+  vendor: Qwen
+  displayName: qwen.qwen1-5-110b-chat
+  disabled: false
+  version: "1.0.0"
+  modelArchitecture: Qwen2ForCausalLM
+  modelFormat:
+    name: safetensors
+    version: "1.0.0"
+  modelFramework:
+    name: transformers
+    version: "4.41.2"
+  modelParameterSize: 110B
+  storage:
+    storageUri: hf://Qwen/Qwen1.5-110B-Chat
+    path: /raid/models/Qwen/Qwen1.5-110B-Chat
+    key: "hf-token"

config/models/Qwen/Qwen1.5-32B-Chat.yaml

@@ -0,0 +1,23 @@
+apiVersion: ome.io/v1beta1
+kind: ClusterBaseModel
+metadata:
+  name: qwen1-5-32b-chat
+spec:
+  modelCapabilities:
+    - TEXT_TO_TEXT
+  vendor: Qwen
+  displayName: qwen.qwen1-5-32b-chat
+  disabled: false
+  version: "1.0.0"
+  modelArchitecture: Qwen2ForCausalLM
+  modelFormat:
+    name: safetensors
+    version: "1.0.0"
+  modelFramework:
+    name: transformers
+    version: "4.41.2"
+  modelParameterSize: 32B
+  storage:
+    storageUri: hf://Qwen/Qwen1.5-32B-Chat
+    path: /raid/models/Qwen/Qwen1.5-32B-Chat
+    key: "hf-token"

config/models/Qwen/Qwen1.5-72B-Chat.yaml

@@ -0,0 +1,23 @@
+apiVersion: ome.io/v1beta1
+kind: ClusterBaseModel
+metadata:
+  name: qwen1-5-72b-chat
+spec:
+  modelCapabilities:
+    - TEXT_TO_TEXT
+  vendor: Qwen
+  displayName: qwen.qwen1-5-72b-chat
+  disabled: false
+  version: "1.0.0"
+  modelArchitecture: Qwen2ForCausalLM
+  modelFormat:
+    name: safetensors
+    version: "1.0.0"
+  modelFramework:
+    name: transformers
+    version: "4.41.2"
+  modelParameterSize: 72B
+  storage:
+    storageUri: hf://Qwen/Qwen1.5-72B-Chat
+    path: /raid/models/Qwen/Qwen1.5-72B-Chat
+    key: "hf-token"

config/models/Qwen/Qwen1.5-7B-Chat.yaml

@@ -0,0 +1,23 @@
+apiVersion: ome.io/v1beta1
+kind: ClusterBaseModel
+metadata:
+  name: qwen1-5-7b-chat
+spec:
+  modelCapabilities:
+    - TEXT_TO_TEXT
+  vendor: Qwen
+  displayName: qwen.qwen1-5-7b-chat
+  disabled: false
+  version: "1.0.0"
+  modelArchitecture: Qwen2ForCausalLM
+  modelFormat:
+    name: safetensors
+    version: "1.0.0"
+  modelFramework:
+    name: transformers
+    version: "4.41.2"
+  modelParameterSize: 7B
+  storage:
+    storageUri: hf://Qwen/Qwen1.5-7B-Chat
+    path: /raid/models/Qwen/Qwen1.5-7B-Chat
+    key: "hf-token"

config/models/google/gemma-2-27b-it.yaml

@@ -0,0 +1,16 @@
+# This model is gated on HuggingFace
+apiVersion: ome.io/v1beta1
+kind: ClusterBaseModel
+metadata:
+  name: gemma-2-27b-it
+spec:
+  modelCapabilities:
+    - TEXT_TO_TEXT
+  vendor: google
+  disabled: false
+  version: "1.0.0"
+  displayName: google.gemma-2-27b-it
+  storage:
+    storageUri: hf://google/gemma-2-27b-it
+    path: /raid/models/google/gemma-2-27b-it
+    key: "hf-token"