feat: support moonshot and glm base models for volcengine provider (#…

…6029)
langgenius · Jul 6, 2024 · 85744b7 · 85744b7
1 parent f0b7051
commit 85744b7
Show file tree

Hide file tree

Showing 2 changed files with 104 additions and 8 deletions.
diff --git a/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py b/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py
@@ -111,5 +111,71 @@
             'mode': 'chat',
         },
         'features': [],
+    },
+    'Moonshot-v1-8k': {
+        'req_params': {
+            'max_prompt_tokens': 8192,
+            'max_new_tokens': 4096,
+        },
+        'model_properties': {
+            'context_size': 8192,
+            'mode': 'chat',
+        },
+        'features': [],
+    },
+    'Moonshot-v1-32k': {
+        'req_params': {
+            'max_prompt_tokens': 32768,
+            'max_new_tokens': 16384,
+        },
+        'model_properties': {
+            'context_size': 32768,
+            'mode': 'chat',
+        },
+        'features': [],
+    },
+    'Moonshot-v1-128k': {
+        'req_params': {
+            'max_prompt_tokens': 131072,
+            'max_new_tokens': 65536,
+        },
+        'model_properties': {
+            'context_size': 131072,
+            'mode': 'chat',
+        },
+        'features': [],
+    },
+    'GLM3-130B': {
+        'req_params': {
+            'max_prompt_tokens': 8192,
+            'max_new_tokens': 4096,
+        },
+        'model_properties': {
+            'context_size': 8192,
+            'mode': 'chat',
+        },
+        'features': [],
+    },
+    'GLM3-130B-Fin': {
+        'req_params': {
+            'max_prompt_tokens': 8192,
+            'max_new_tokens': 4096,
+        },
+        'model_properties': {
+            'context_size': 8192,
+            'mode': 'chat',
+        },
+        'features': [],
+    },
+    'Mistral-7B': {
+        'req_params': {
+            'max_prompt_tokens': 8192,
+            'max_new_tokens': 2048,
+        },
+        'model_properties': {
+            'context_size': 8192,
+            'mode': 'chat',
+        },
+        'features': [],
     }
 }
diff --git a/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml b/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml
@@ -120,12 +120,6 @@ model_credential_schema:
           show_on:
             - variable: __model_type
               value: llm
-        - label:
-            en_US: Skylark2-pro-4k
-          value: Skylark2-pro-4k
-          show_on:
-            - variable: __model_type
-              value: llm
         - label:
             en_US: Llama3-8B
           value: Llama3-8B
@@ -138,6 +132,42 @@ model_credential_schema:
           show_on:
             - variable: __model_type
               value: llm
+        - label:
+            en_US: Moonshot-v1-8k
+          value: Moonshot-v1-8k
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: Moonshot-v1-32k
+          value: Moonshot-v1-32k
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: Moonshot-v1-128k
+          value: Moonshot-v1-128k
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: GLM3-130B
+          value: GLM3-130B
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: GLM3-130B-Fin
+          value: GLM3-130B-Fin
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: Mistral-7B
+          value: Mistral-7B
+          show_on:
+            - variable: __model_type
+              value: llm
         - label:
             en_US: Doubao-embedding
           value: Doubao-embedding
@@ -181,7 +211,7 @@ model_credential_schema:
         zh_Hans: 模型上下文长度
         en_US: Model Context Size
       type: text-input
-      default: '4096'
+      default: "4096"
       placeholder:
         zh_Hans: 输入您的模型上下文长度
         en_US: Enter your Model Context Size
@@ -195,7 +225,7 @@ model_credential_schema:
       label:
         zh_Hans: 最大 token 上限
         en_US: Upper Bound for Max Tokens
-      default: '4096'
+      default: "4096"
       type: text-input
       placeholder:
         zh_Hans: 输入您的模型最大 token 上限