@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: `windowDays` (how many days of ledger
228
- history to train on; default all history), `epochs` (1-10, default 3), `rank` (LoRA
229
- rank, 4-64, default 16), `learningRate` (default 5e-5). It requires `jewel`, and it
230
- rides the release: changing a knob is a commit + deploy before the next training run.
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
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mindstudio-ai/remy",
3
- "version": "0.1.285",
3
+ "version": "0.1.286",
4
4
  "description": "Remy coding agent",
5
5
  "repository": {
6
6
  "type": "git",