feat: nvidia add llama3.1 model (#6844)

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

@@ -2,6 +2,9 @@
 - google/codegemma-7b
 - google/recurrentgemma-2b
 - meta/llama2-70b
+- meta/llama-3.1-8b-instruct
+- meta/llama-3.1-70b-instruct
+- meta/llama-3.1-405b-instruct
 - meta/llama3-8b-instruct
 - meta/llama3-70b-instruct
 - mistralai/mistral-large

api/core/model_runtime/model_providers/nvidia/llm/llama-3.1-405b.yaml

@@ -0,0 +1,36 @@
+model: meta/llama-3.1-405b-instruct
+label:
+  zh_Hans: meta/llama-3.1-405b-instruct
+  en_US: meta/llama-3.1-405b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 4096
+    default: 1024
+  - name: frequency_penalt
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0

api/core/model_runtime/model_providers/nvidia/llm/llama-3.1-70b.yaml

@@ -0,0 +1,36 @@
+model: meta/llama-3.1-70b-instruct
+label:
+  zh_Hans: meta/llama-3.1-70b-instruct
+  en_US: meta/llama-3.1-70b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 4096
+    default: 1024
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0

api/core/model_runtime/model_providers/nvidia/llm/llama-3.1-8b.yaml

@@ -0,0 +1,36 @@
+model: meta/llama-3.1-8b-instruct
+label:
+  zh_Hans: meta/llama-3.1-8b-instruct
+  en_US: meta/llama-3.1-8b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 4096
+    default: 1024
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0

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

@@ -31,6 +31,9 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
         'meta/llama2-70b': '',
         'meta/llama3-8b-instruct': '',
         'meta/llama3-70b-instruct': '',
+        'meta/llama-3.1-8b-instruct': '',
+        'meta/llama-3.1-70b-instruct': '',
+        'meta/llama-3.1-405b-instruct': '',
         'google/recurrentgemma-2b': ''
         
     }