卸载模型

POST

http://localhost:11434/api/generate

If an empty prompt is provided and the keep_alive parameter is set to 0, a model will be unloaded from memory.

请求示例

Shell

JavaScript

Java

Swift

curl --location --request POST 'http://localhost:11434/api/generate' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "llama3.2",
    "keep_alive": 0
}'

响应示例

{
  "model": "llama3.2",
  "created_at": "2024-09-12T03:54:03.516566Z",
  "response": "",
  "done": true,
  "done_reason": "unload"
}

请求参数

Body 参数application/json

model

enum<string>

必需

枚举值:

llama3.2

示例值:

llama3.2

keep_alive

integer

必需

>= 0

示例

返回响应

🟢200Success

application/json

A single JSON object is returned:

Body

model

string

必需

created_at

string

必需

response

string

必需

done

boolean

必需

done_reason

string

必需

修改于 2025-03-26 10:19:10

加载模型

概括