unsloth-sft
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like sft, instruction tuning, chat templates, sharegpt, alpaca, conversation_extension, and SFTTrainer.
npx skills add majiayu000/claude-skill-registry --skill unsloth-sft-cuba6112-skillfactory-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Overview Supervised Fine-Tuning (SFT) in Unsloth focuses on training models to follow instructions using specific formats. It provides tools for chat template mapping, multi-turn conversation synthesis via `conversation_extension`, and optimized dataset processing. ## When to Use - When training models on instruction-response datasets (e.g., Alpaca). - When developing multi-turn conversational agents. - When you need to standardize various dataset formats (ShareGPT, OpenAI) for training. ## Decision Tree 1. Is your dataset single-turn? - Yes: Use `conversation_extension` to synthetically create multi-turn samples. - No: Map columns using `standardize_sharegpt`. 2. Are you training on Windows? - Yes: Set `dataset_num_proc = 1` in SFTConfig. - No: Use multiple processes for faster mapping. 3. Want to increase multi-turn accuracy? - Yes: Enable masking of inputs to train on completions only. ## Workflows ### Chat Template Implementation 1. Select a template (e.g., 'chatml', 'llama-3.1') using `get_chat_template(tokenizer, chat_template='...')`. 2. Map dataset columns using the mapping parameter (e.g., `mapping = {'role' : 'from', 'content' : 'value'}`). 3. Apply the formatting func
- Overview
- When to Use
- Decision Tree
- Workflows
- Chat Template Implementation
- Multi-turn Data Preparation
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the unsloth-sft skill do?
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like sft, instruction tuning, chat templates, sharegpt, alpaca, conversation_extension, and SFTTrainer.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill unsloth-sft-cuba6112-skillfactory-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.