lms_load_cli
Load local LLM models from the command line with granular control over GPU offload, context length, and custom instance identifiers for precise deployment.
Instructions
CLI: Advanced model loading with granular control.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model_id": "<model_id>"
},
"name": "lms_load_cli"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| gpu | No | GPU offload (e.g., 'max', '0.5', 'off'). | |
| model_id | Yes | ||
| identifier | No | Custom identifier for the loaded model instance. | |
| context_length | No | Context length override. |