mark deprecated models in siliconflow #12399 (#12405)

Co-authored-by: crazywoola <427733928@qq.com>

api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml

@@ -1,4 +1,3 @@
-- Tencent/Hunyuan-A52B-Instruct
 - Qwen/QwQ-32B-Preview
 - Qwen/Qwen2.5-72B-Instruct
 - Qwen/Qwen2.5-32B-Instruct
@@ -6,11 +5,9 @@
 - Qwen/Qwen2.5-7B-Instruct
 - Qwen/Qwen2.5-Coder-32B-Instruct
 - Qwen/Qwen2.5-Coder-7B-Instruct
-- Qwen/Qwen2.5-Math-72B-Instruct
 - Qwen/Qwen2-VL-72B-Instruct
 - Qwen/Qwen2-1.5B-Instruct
 - Pro/Qwen/Qwen2-VL-7B-Instruct
-- OpenGVLab/InternVL2-Llama3-76B
 - OpenGVLab/InternVL2-26B
 - Pro/OpenGVLab/InternVL2-8B
 - deepseek-ai/DeepSeek-V2.5

api/core/model_runtime/model_providers/siliconflow/llm/hunyuan-a52b-instruct.yaml

@@ -82,3 +82,4 @@ pricing:
   output: '21'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/internvl2-llama3-76b.yaml

@@ -82,3 +82,4 @@ pricing:
   output: '21'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/qwen-qvq-72B-preview.yaml

@@ -0,0 +1,54 @@
+model: Qwen/QVQ-72B-Preview
+label:
+  en_US: Qwen/QVQ-72B-Preview
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 8192
+    min: 1
+    max: 16384
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '9.90'
+  output: '9.90'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen-qwq-32B-preview.yaml

@@ -15,9 +15,9 @@ parameter_rules:
   - name: max_tokens
     use_template: max_tokens
     type: int
-    default: 512
+    default: 4096
     min: 1
-    max: 4096
+    max: 8192
     help:
       zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-vl-72b-instruct.yaml

@@ -78,7 +78,7 @@ parameter_rules:
       - text
       - json_object
 pricing:
-  input: '21'
-  output: '21'
+  input: '4.13'
+  output: '4.13'
   unit: '0.000001'
   currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-vl-7b-Instruct.yaml

@@ -78,7 +78,7 @@ parameter_rules:
       - text
       - json_object
 pricing:
-  input: '21'
-  output: '21'
+  input: '0.35'
+  output: '0.35'
   unit: '0.000001'
   currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-math-72b-instruct.yaml

@@ -82,3 +82,4 @@ pricing:
   output: '4.13'
   unit: '0.000001'
   currency: RMB
+deprecated: true

docker/docker-compose-template.yaml

@@ -1,4 +1,4 @@
-x-shared-env: &shared-api-worker-env 
+x-shared-env: &shared-api-worker-env
 services:
   # API service
   api: