CohereLabs/tiny-aya-global β€” GRPO Schema-Conditioned Extraction Adapter

GRPO post-trained LoRA adapter trained with AlignTune (Lexsi-Labs/aligntune). Related SFT warm-up repo: sujalgawas/tiny-aya-global-sft-schema-adapter.

Downloads last month
66
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for sujalgawas/tiny-aya-global-grpo-schema-model

Adapter
(395)
this model