feat: add GroqCloud llama3.1 series models support (#6596)

2024-11-16 11:42:29 +08:00 · 2024-07-24 00:41:58 +08:00 · 2024-07-24 00:41:58 +08:00 · 4c85393a1d
commit 4c85393a1d
parent d5c2680fde
4 changed files with 82 additions and 0 deletions
--- a/api/core/model_runtime/model_providers/groq/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/_position.yaml
@ -0,0 +1,7 @@
+- llama-3.1-405b-reasoning
+- llama-3.1-70b-versatile
+- llama-3.1-8b-instant
+- llama3-70b-8192
+- llama3-8b-8192
+- mixtral-8x7b-32768
+- llama2-70b-4096
--- a/api/core/model_runtime/model_providers/groq/llm/llama-3.1-405b-reasoning.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-405b-reasoning.yaml
@ -0,0 +1,25 @@
+model: llama-3.1-405b-reasoning
+label:
+  zh_Hans: Llama-3.1-405b-reasoning
+  en_US: Llama-3.1-405b-reasoning
+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
--- a/api/core/model_runtime/model_providers/groq/llm/llama-3.1-70b-versatile.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-70b-versatile.yaml
@ -0,0 +1,25 @@
+model: llama-3.1-70b-versatile
+label:
+  zh_Hans: Llama-3.1-70b-versatile
+  en_US: Llama-3.1-70b-versatile
+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
--- a/api/core/model_runtime/model_providers/groq/llm/llama-3.1-8b-instant.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-8b-instant.yaml
@ -0,0 +1,25 @@
+model: llama-3.1-8b-instant
+label:
+  zh_Hans: Llama-3.1-8b-instant
+  en_US: Llama-3.1-8b-instant
+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