| title | llm-helper new |
|---|---|
| description | Pull a new HuggingFace model, save it as a profile, and start it |
llm-helper new <org/model-repo> [flags]| Type | bool |
return as soon as the server is started instead of watching the boot
| Type | string |
which quantization to serve, for repos that ship several (see 'llm-helper inspect')
| Type | string |
on or off: whether a thinking model reasons before it answers (default: the model's own)
| Type | duration |
give up waiting after this long (default: wait forever)
| Type | bool |
block until the endpoint is healthy, without streaming logs