Added new models and Removed the deleted ones for Groq #11455 (#11456)

Co-authored-by: crazywoola <[email protected]>
Co-authored-by: Alok Shrivastwa <[email protected]>

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

@@ -1,4 +1,5 @@
 - llama-3.1-405b-reasoning
+- llama-3.3-70b-versatile
 - llama-3.1-70b-versatile
 - llama-3.1-8b-instant
 - llama3-70b-8192

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

@@ -0,0 +1,25 @@
+model: gemma-7b-it
+label:
+  zh_Hans: Gemma 7B Instruction Tuned
+  en_US: Gemma 7B Instruction Tuned
+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: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.1'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/groq/llm/gemma2-9b-it.yaml

@@ -0,0 +1,25 @@
+model: gemma2-9b-it
+label:
+  zh_Hans: Gemma 2 9B Instruction Tuned
+  en_US: Gemma 2 9B Instruction Tuned
+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: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.1'
+  unit: '0.000001'
+  currency: USD

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

@@ -1,7 +1,8 @@
 model: llama-3.1-70b-versatile
+deprecated: true
 label:
-  zh_Hans: Llama-3.1-70b-versatile
-  en_US: Llama-3.1-70b-versatile
+  zh_Hans: Llama-3.1-70b-versatile (DEPRECATED)
+  en_US: Llama-3.1-70b-versatile (DEPRECATED)
 model_type: llm
 features:
   - agent-thought

api/core/model_runtime/model_providers/groq/llm/llama-3.2-11b-text-preview.yaml

@@ -1,4 +1,5 @@
 model: llama-3.2-11b-text-preview
+deprecated: true
 label:
   zh_Hans: Llama 3.2 11B Text (Preview)
   en_US: Llama 3.2 11B Text (Preview)

api/core/model_runtime/model_providers/groq/llm/llama-3.2-90b-text-preview.yaml

@@ -1,4 +1,5 @@
 model: llama-3.2-90b-text-preview
+depraceted: true
 label:
   zh_Hans: Llama 3.2 90B Text (Preview)
   en_US: Llama 3.2 90B Text (Preview)

api/core/model_runtime/model_providers/groq/llm/llama-3.3-70b-specdec .yaml

@@ -0,0 +1,25 @@
+model: llama-3.3-70b-specdec
+label:
+  zh_Hans: Llama 3.3 70b Speculative Decoding  (PREVIEW)
+  en_US: Llama 3.3 70b Speculative Decoding (PREVIEW)
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.1'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/groq/llm/llama3-groq-70b-8192-tool-use-preview.yaml

@@ -0,0 +1,25 @@
+model: llama3-groq-70b-8192-tool-use-preview
+label:
+  zh_Hans: Llama3-groq-70b-8192-tool-use (PREVIEW)
+  en_US: Llama3-groq-70b-8192-tool-use (PREVIEW)
+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: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.08'
+  unit: '0.000001'
+  currency: USD