BigHugger
sk Skill · hiyouga

llamafactory-sft

One-stop guided LlamaFactory SFT workflow — data prep, model prep, fine-tuning config/method selection, background training, loss visualization, effect validation and model export. TRIGGER when the user wants to fine-tune / SFT a model with LlamaFactory, run a full LlamaFactory training pipeline, or asks to "微调" / "用 llamafactory 做 sft" / "train a LoRA". SKIP for general questions about the codebase or non-training…

installs 8w
0
30-day movement
starts with the next reading
Related entries
1
Connections
0
pythonjsonbashPython

A SKILL.md that guides an AI coding agent through a complete LlamaFactory SFT run, from data and model preparation through config generation, background training, loss visualization, optional validation, and export. It structures the workflow into stages with user questions at each decision point and a progress board.

Reach for it when you want a guided, step-by-step LlamaFactory fine-tuning pipeline instead of assembling the commands yourself.

Use it to

  • Fine-tune a model with LlamaFactory SFT
  • Train a LoRA adapter end to end
  • Prepare and validate custom training data
  • Visualize training loss after a run
  • Export a fine-tuned checkpoint

For Developers fine-tuning LLMs with LlamaFactory

Host repository
hiyouga/LlamaFactory
Host stars
75k
Host language
Python
topicsllamafactorysftfine-tuningloratraining-pipelineagent-skill