Marketplaces / wshobson/agents / llm-finetuning/finetuning-method-selection

llm-finetuning/finetuning-method-selection

Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.

skill · safety 97/100 (warn) · @ 367cb6a

Install in kendex: kendex add --skill llm-finetuning/finetuning-method-selection after subscribing to wshobson/agents.