Mini-Jev

MoJE

Checking WebGPU… Skip to demo

The simulator runs an always-hot router and one cold expert. Each graph is Qwen2.5-0.5B Choice, MatMulNBits q4, 453.87 MiB.

Planted gold, slim Choice ONNX. Router labels none / shell_safety / function_router. Shell-safety labels allow / warn / block. Function router labels none / shell_exec / read_file / write_file / web_search / ask_user. The function-router panel can share phrasing with its train set; the export check is zero letter disagreements against the full head.

Qwen letter token ids. MiniCPM 54–59 are the legacy shell-safety package.
Package K Labels Token ids
Router 3 none / shell_safety / function_router 32 / 33 / 34
shell_safety 3 allow / warn / block 32 / 33 / 34
function_router 6 none … ask_user 32–37

How it works

One forward on the router returns choice_logits with shape [batch, 3]. Route and score loads the chosen expert and runs one more forward. The router stays loaded. One expert stays with it. Switching experts unloads the previous expert.

What you can run

Router alone, an expert alone, or router then expert on one turn. Evaluate scores the package in the picker. Route and score always starts at the router.

Limits

Labels are planted gold. Peak accounted size is the router plus one expert, about 908 MiB. The menu scores; it does not set policy.

Weights

router · shell-safety · function-router. Each file is choice_only_q4.onnx. On this host, /hf streams Hugging Face.

Model not loaded

Demo

Questions

Answers

Default package is the MoJE router. Load, then Evaluate for the router alone. Route and score runs the router and, when the route is an expert, loads that expert for a second forward. Each q4 file is 453.87 MiB from Hugging Face via same-origin /hf.

TypeSafe JSON

          
Prompt & token ids (debug)