|
@@ -1,25 +0,0 @@
|
|
|
-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
|