minions — Shape a routing minion from Qwen3.5-0.8B — openbash
Turn Qwen3.5-0.8B into a router for your own labels with forward passes alone: one new neuron a label, fitted by least squares, scored on your held-out examples, returned as a patch.
minions
minions is a command on the openbash shell, reachable over HTTP, SSH and MCP with one key. It composes with the other programs through pipes; there is no per-program endpoint and no schema for the join.
minions shape "billing: I was charged twice || billing: why did my invoice go up || ..." --requests_text "my card was charged but the order says unpaid"
help
minions: shape a small, fast router for your own labels from Qwen3.5-0.8B, as JSON.
WHAT IT DOES
Give one-word labels and at least five examples a label. The examples are
split 3 : 1 : 1 into fit, pick and check sets. One forward pass per example
reads the model's last MLP. One new neuron a label is added there by least
squares: its gate fires where a routing answer goes and stays near zero on
other text, and its output writes the label's first token. No gradients.
The strength is picked on the pick set, keeping at least 99% of next-token
guesses unchanged on ordinary text.
RETURNS
One JSON object on stdout: `check`, the check-set accuracy of the unedited
model, the minion and random neurons of the same size; `text_unchanged`,
the share of next-token guesses on ordinary text the minion and the random
neurons leave as they were; `edit` (neurons, layer, size in KB); the forward
passes used; `routes`, each request routed by the unedited model and by the
minion; and `patch_b64`, the neurons as safetensors (rows to append to
gate_proj and up_proj, columns to down_proj, of the last layer). Also
`price_usd` and `standing`.
OPTIONS
"label: text || label: text" the examples, quoted, one per piece (the
first argument); labels come from here when --labels is
left out
--labels a,b,c the labels, one word each, 2 to 24
--requests_text "text || text" up to 20 requests to route
--patch false leave the patch out of the answer
READ THE CHECK SET AS SMALL
The check set is a fifth of your examples. With five examples a label it is
one request a label, so read the accuracy as a rough sign. The minion's
probabilities in `routes` are not calibrated; they sit near 1.
PRICE
$0.05 a run. An account that has never paid gets three runs free; after that
the run is refused until $2 of credit is added, and the `credits` tool gives
the link. A warm run takes about 6 seconds; the first after a quiet spell
waits about 90 seconds while the model loads.
Studies:
shape <examples_text>
check-set accuracy of the unedited model, the minion and random neurons, ordinary text left unchanged, each request routed, the patch, the price and how many free runs are left
JSON to stdout, so it composes: pipe to `jq` to pick a field, or `> /tmp/…` to keep it.
Run a study with no arguments — `minions shape` — to see what it takes.
What it answers
minions shape — check-set accuracy of the unedited model, the minion and random neurons, ordinary text left unchanged, each request routed, the patch, the price and how many free runs are left