llm_load

Builtin index · Statistics & ML

result = llm_load(name)

Input: name · Output: result

What it is

Loads a chat model, identified by name: a string, either a bundled name like "tinyllama" or a local filesystem path to a .gguf weights file with a tokenizer.json beside it.

Overloads

One call shape — this function is not overloaded.

Code	Input	Output	Description
`result = llm_load(name)`	`name` stringnot documented yet	`result` Record	Returns a model handle Record with a `.generate` method; loading is eager, so the call blocks until the whole model is read into memory.

Examples

No documentation example calls this form yet. The Statistics & ML chapter is where one belongs.