MiniCPM5-1B
MiniCPM Text Series
Fine-tuning Cookbook and Agent Skills
MiniCPM5-1B uses the standard LlamaForCausalLM architecture, so mainstream inference engines can load it directly, with no custom operators and no forked model code. To help developers reproduce the fine-tuning workflow quickly, we provide single-page cookbooks, each paired one-to-one with a Cursor Agent Skill.
Cookbook: Best for running the steps manually. Agent Skills: Best for letting the agent in Cursor / Claude Code choose the execution path based on the target backend, hardware and data path.
Top-level Skill
MiniCPM5-1B Finetune Skill(automatically routes to trl · llamafactory · ms-swift · unsloth · xtuner)
After downloading this Skill and placing it in your current project directory, you can type the following in a coding agent such as Cursor / Claude Code:
@minicpm5-finetune use unsloth + LoRA on /data/my_chat.jsonl, write to ./out
The agent reads the top-level Skill, picks the matching sub-Skill and cookbook based on the target backend, hardware and data path, then runs the commands and reports back the results.
The cookbooks and sub-Skills are listed below by inference backend.