Add model parameter enable_enhance for hunyuan llm model (#6847)

Co-authored-by: sun <sun@centen.cn>
This commit is contained in:
Giga Group 2024-07-31 20:04:43 +08:00 committed by GitHub
parent 13f5867a16
commit 4b410494b3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 32 additions and 1 deletions

View File

@ -21,6 +21,16 @@ parameter_rules:
default: 1024
min: 1
max: 32000
- name: enable_enhance
label:
zh_Hans: 功能增强
en_US: Enable Enhancement
type: boolean
help:
zh_Hans: 功能增强(如搜索)开关,关闭时将直接由主模型生成回复内容,可以降低响应时延(对于流式输出时的首字时延尤为明显)。但在少数场景里,回复效果可能会下降。
en_US: Allow the model to perform external search to enhance the generation results.
required: false
default: true
pricing:
input: '0.03'
output: '0.10'

View File

@ -21,6 +21,16 @@ parameter_rules:
default: 1024
min: 1
max: 256000
- name: enable_enhance
label:
zh_Hans: 功能增强
en_US: Enable Enhancement
type: boolean
help:
zh_Hans: 功能增强(如搜索)开关,关闭时将直接由主模型生成回复内容,可以降低响应时延(对于流式输出时的首字时延尤为明显)。但在少数场景里,回复效果可能会下降。
en_US: Allow the model to perform external search to enhance the generation results.
required: false
default: true
pricing:
input: '0.015'
output: '0.06'

View File

@ -21,6 +21,16 @@ parameter_rules:
default: 1024
min: 1
max: 32000
- name: enable_enhance
label:
zh_Hans: 功能增强
en_US: Enable Enhancement
type: boolean
help:
zh_Hans: 功能增强(如搜索)开关,关闭时将直接由主模型生成回复内容,可以降低响应时延(对于流式输出时的首字时延尤为明显)。但在少数场景里,回复效果可能会下降。
en_US: Allow the model to perform external search to enhance the generation results.
required: false
default: true
pricing:
input: '0.0045'
output: '0.0005'

View File

@ -36,7 +36,8 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
custom_parameters = {
'Temperature': model_parameters.get('temperature', 0.0),
'TopP': model_parameters.get('top_p', 1.0)
'TopP': model_parameters.get('top_p', 1.0),
'EnableEnhancement': model_parameters.get('enable_enhance', True)
}
params = {