jxjwilliam

jxjwilliam/jinyong-finetune-qlora

Cursor rule Cursor

AutoDL (autodl.com) cloud GPU workflow for QLoRA fine-tuning Jin Yong style.

jxjwilliam/jinyong-finetune-qlora

Cursor rule Cursor

HuggingFace PEFT and TRL conventions.

jxjwilliam/jinyong-finetune-qlora

Cursor rule Cursor

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

jxjwilliam/jinyong-finetune-qlora

Cursor rule Cursor

ML Python conventions for this project.

jxjwilliam/jinyong-finetune-qlora

Instructions file CodexOpenCode

AGENTS.md instructions for jxjwilliam/jinyong-finetune-qlora, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

jxjwilliam/jinyong-finetune-qlora

Instructions file

Claude Code instructions for jxjwilliam/jinyong-finetune-qlora, covering claude.md, project purpose, setup, key commands and train (all hyperparameters come from the yaml config).