Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: Alok Shrivastwa <Alok.Shrivastwa@microland.com>
@@ -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
@@ -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
+model: gemma2-9b-it
+ zh_Hans: Gemma 2 9B Instruction Tuned
+ en_US: Gemma 2 9B Instruction Tuned
@@ -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
model: llama-3.2-11b-text-preview
zh_Hans: Llama 3.2 11B Text (Preview)
en_US: Llama 3.2 11B Text (Preview)
model: llama-3.2-90b-text-preview
+depraceted: true
zh_Hans: Llama 3.2 90B Text (Preview)
en_US: Llama 3.2 90B Text (Preview)
+model: llama-3.3-70b-specdec
+ zh_Hans: Llama 3.3 70b Speculative Decoding (PREVIEW)
+ en_US: Llama 3.3 70b Speculative Decoding (PREVIEW)
+ context_size: 131072
+model: llama3-groq-70b-8192-tool-use-preview
+ zh_Hans: Llama3-groq-70b-8192-tool-use (PREVIEW)
+ en_US: Llama3-groq-70b-8192-tool-use (PREVIEW)
+ output: '0.08'