{
"data": [
{
"help": {
"zh_Hans": "自定义温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零,模型将变得确定性和重复性。较高的温度会导致更多的随机完成。",
"en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions."
},
"default": 0.0,
"min": 0.0,
"use_template": "temperature",
"max": 1.0,
"precision": 2,
"name": "temperature",
"options": [],
"label": {
"zh_Hans": "自定义温度",
"en_US": "Temperature"
},
"type": "float",
"required": false
},
{
"help": {
"zh_Hans": "通过核心采样控制多样性:0.5表示考虑了一半的所有可能性加权选项。",
"en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered."
},
"default": 1.0,
"min": 0.0,
"use_template": "top_p",
"max": 1.0,
"precision": 2,
"name": "top_p",
"options": [],
"label": {
"zh_Hans": "Top P",
"en_US": "Top P"
},
"type": "float",
"required": false
},
{
"help": {
"zh_Hans": "指定生成结果长度的上限。如果生成结果截断,可以调大该参数。",
"en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter."
},
"default": 512,
"min": 1.0,
"use_template": "max_tokens",
"max": 8192.0,
"precision": 0,
"name": "max_tokens",
"options": [],
"label": {
"zh_Hans": "最大标记",
"en_US": "Max Tokens"
},
"type": "int",
"required": false
}
],
"provider": "jiutian",
"model": "jiutian-1",
"id": "16e1b159-9510-441b-8948-624bc5df8291",
"enableFlag": 1,
"userId": 19645
}