What would be the current best method to fine-tune it for my own specific agentic tasks? LoRA + DPO? GRPO? Something else?
LoRA + SFT, but it'll be big - better to wait for a finetuning API from one of the providers, I wouldn't jump straight to RL or off-policy pseudo-RL like DPO.
alt Hacker News
LoRA + SFT, but it'll be big - better to wait for a finetuning API from one of the providers, I wouldn't jump straight to RL or off-policy pseudo-RL like DPO.