feat: add siliconflow qwq and llama3.3 model

- qwq-32B-preview-instruct - llama3.3-70b
langgenius · Dec 9, 2024 · a2310c8 · a2310c8
1 parent 5c166b3
commit a2310c8
Show file tree

Hide file tree

Showing 3 changed files with 108 additions and 0 deletions.
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml
@@ -1,4 +1,5 @@
 - Tencent/Hunyuan-A52B-Instruct
+- Qwen/QwQ-32B-Preview
 - Qwen/Qwen2.5-72B-Instruct
 - Qwen/Qwen2.5-32B-Instruct
 - Qwen/Qwen2.5-14B-Instruct
@@ -19,6 +20,7 @@
 - 01-ai/Yi-1.5-6B-Chat
 - internlm/internlm2_5-20b-chat
 - internlm/internlm2_5-7b-chat
+- meta-llama/Llama-3.3-70B-Instruct
 - meta-llama/Meta-Llama-3.1-405B-Instruct
 - meta-llama/Meta-Llama-3.1-70B-Instruct
 - meta-llama/Meta-Llama-3.1-8B-Instruct

diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/meta-llama-3.3-70b-instruct.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/meta-llama-3.3-70b-instruct.yaml
@@ -0,0 +1,53 @@
+model: meta-llama/Llama-3.3-70B-Instruct
+label:
+  en_US: meta-llama/Llama-3.3-70B-Instruct
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    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: '4.13'
+  output: '4.13'
+  unit: '0.000001'
+  currency: RMB
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/qwen-qwq-32B-preview.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/qwen-qwq-32B-preview.yaml
@@ -0,0 +1,53 @@
+model: Qwen/QwQ-32B-Preview
+label:
+  en_US: Qwen/QwQ-32B-Preview
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    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: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB