@mindstudio-ai/remy 0.1.285 → 0.1.286
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -224,10 +224,13 @@ The wiring itself is two manifest lines on the method's entry:
|
|
|
224
224
|
```
|
|
225
225
|
|
|
226
226
|
`tuning` (optional) is the training recipe for the jewel's own model. Every knob has a
|
|
227
|
-
platform default and most jewels never set any: `
|
|
228
|
-
|
|
229
|
-
|
|
230
|
-
|
|
227
|
+
platform default and most jewels never set any: `base` (which model to train — a slug
|
|
228
|
+
from the platform's small menu; `qwen3.5-4b` is the default, `qwen3.5-9b` and
|
|
229
|
+
`ministral-3-8b` are the larger options, and the default is the right choice unless a
|
|
230
|
+
report shows it falling short), `windowDays` (how many days of ledger history to train
|
|
231
|
+
on; default all history), `epochs` (1-10, default 3), `rank` (LoRA rank, 4-64, default
|
|
232
|
+
16), `learningRate` (default 5e-5). It requires `jewel`, and it rides the release:
|
|
233
|
+
changing a knob is a commit + deploy before the next training run.
|
|
231
234
|
|
|
232
235
|
Once a method has accumulated graded pairs, train from the prod CLI:
|
|
233
236
|
`mindstudio-prod jewels train <methodId>` (see `--help`). The dataset report says
|