 Tobi Lütke
|
d6f3688d91
Remove grpo command from default train entrypoint
|
3 mēneši atpakaļ |
|
Tobi Lütke
|
189916d6fb
Move GRPO training out of default finetune pipeline
|
3 mēneši atpakaļ |
|
Tobi Lutke
|
1d7d167b29
finetune: strict Pydantic schema, one canonical data format
|
3 mēneši atpakaļ |
|
Tobi Lutke
|
739038e1a7
docs: add explicit HuggingFace repo destinations
|
3 mēneši atpakaļ |
|
Tobi Lutke
|
38073799c0
chore: clean up finetune folder and fix training workflow
|
3 mēneši atpakaļ |
|
Tobi Lutke
|
533f0eed37
docs: add finetune CLAUDE.md and update training workflow
|
3 mēneši atpakaļ |
