Skip to main content

gen_qwen38_filled_lg

Function gen_qwen38_filled_lg 

Source
pub fn gen_qwen38_filled_lg(cfg: &Qwen38Cfg, dir: &str) -> String
Expand description

The authored forward (gen_qwen38_lg) with every declared tensor filled DETERMINISTICALLY right after its declaration (a hash of the element index salted by the tensor’s name, in (-0.2, 0.2)) and the first and last logit shown — the self-contained program the demo corpus (examples/rdu_demo/qwen38_tiny.lg) and the tier-agreement locks run without a weight file. Fills follow declarations because the weights are declared per block, interleaved with the compute that reads them.