add-leptonai

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

@@ -0,0 +1,7 @@
+- gemma-7b
+- mistral-7b
+- mixtral-8x7b
+- llama2-7b
+- llama2-13b
+- llama3-70b
+- 

api/core/model_runtime/model_providers/leptonai/llm/gemma-7b.yaml

@@ -0,0 +1,20 @@
+model: gemma-7b
+label:
+  zh_Hans: gemma-7b
+  en_US: gemma-7b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 1024

api/core/model_runtime/model_providers/leptonai/llm/llama2-13b.yaml

@@ -0,0 +1,20 @@
+model: llama2-13b
+label:
+  zh_Hans: llama2-13b
+  en_US: llama2-13b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 1024

api/core/model_runtime/model_providers/leptonai/llm/llama-7b.yaml → api/core/model_runtime/model_providers/leptonai/llm/llama2-7b.yaml

@@ -15,11 +15,6 @@ parameter_rules:
     use_template: top_p
   - name: max_tokens
     use_template: max_tokens
-    default: 512
+    default: 1024
     min: 1
-    max: 4096
-pricing:
-  input: '0.01'
-  output: '0.01'
-  unit: '0.000001'
-  currency: USD
+    max: 1024

api/core/model_runtime/model_providers/leptonai/llm/llama3-70b.yaml

@@ -0,0 +1,20 @@
+model: llama3-70b
+label:
+  zh_Hans: llama3-70b
+  en_US: llama3-70b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 1024

api/core/model_runtime/model_providers/leptonai/llm/llm.py

@@ -7,8 +7,13 @@
 
 
 class LeptonAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
-    MODEL_SUFFIX_MAP = {
+    MODEL_PREFIX_MAP = {
         'llama2-7b': 'llama2-7b',
+        'gemma-7b': 'gemma-7b',
+        'mistral-7b': 'mistral-7b',
+        'mixtral-8x7b': 'mixtral-8x7b',
+        'llama3-70b': 'llama3-70b',
+        'llama2-13b': 'llama2-13b',
     } 
     def _invoke(self, model: str, credentials: dict,
                 prompt_messages: list[PromptMessage], model_parameters: dict,
@@ -25,5 +30,5 @@ def validate_credentials(self, model: str, credentials: dict) -> None:
     @classmethod
     def _add_custom_parameters(cls, credentials: dict, model: str) -> None:
         credentials['mode'] = 'chat'
-        credentials['endpoint_url'] = f'https://{cls.MODEL_SUFFIX_MAP[model]}.lepton.run/api/v1'
+        credentials['endpoint_url'] = f'https://{cls.MODEL_PREFIX_MAP[model]}.lepton.run/api/v1'
 

api/core/model_runtime/model_providers/leptonai/llm/mistral-7b.yaml

@@ -0,0 +1,20 @@
+model: mistral-7b
+label:
+  zh_Hans: mistral-7b
+  en_US: mistral-7b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 1024

api/core/model_runtime/model_providers/leptonai/llm/mixtral-8x7b.yaml

@@ -0,0 +1,20 @@
+model: mixtral-8x7b
+label:
+  zh_Hans: mixtral-8x7b
+  en_US: mixtral-8x7b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 1024