generate
Builtin index · Statistics & ML
result = model.generate(prompt, [max_tokens=64])
Input: prompt, max_tokens · Output: result
What it is
Runs greedy (argmax, no sampling knobs, no temperature) text completion on a model handle model from llm_load, given a string prompt and an integer cap max_tokens (default 64) on how many tokens to generate.
Overloads
One call shape — this function is not overloaded.
| Code | Input | Output | Description |
result = model.generate(prompt, [max_tokens=64]) | prompt stringnot documented yetmax_tokens string, optional (default 64)not documented yet | result string | Returns the completion as a plain string. There is no streaming and no hidden conversation state — each call is independent, so a multi-turn chat has to concatenate prior turns into prompt itself. |
Examples
No documentation example calls this form yet. The Statistics & ML chapter is where one belongs.