Individual skill

gemma-trainer

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.

skills/gemma-trainer/SKILL.md

Read pinned source

Source commit 5aee63beeed3d5591f7c5393519d7af1026b8a5c

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 10, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,039
Repository last updated: Oct 28, 2026
License: Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

gemma Repository topic
skills Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 8,767 bytes
SKILL.mdcore · 8,767 bytes
assets/dataset_prep.pyruns · 17,746 bytes
assets/distill_dataset.pyruns · 18,430 bytes
assets/dpo_train.pyruns · 9,984 bytes
assets/reward_train.pyruns · 6,041 bytes
assets/sft_train.pyruns · 14,692 bytes

Read excerpt


# Gemma Training and Fine-Tuning Skill

## 1. Core Principles: Local Fine-Tuning Setup

When training locally, memory efficiency and execution speed are huge. Always
guide the user to follow these best practices:

*   **Prioritize Unsloth**: For local single-GPU training, always recommend
    **Unsloth**. It supports Gemma 4 natively, uses up to 70% less memory, and
    is up to 2x faster than standard Hugging Face PEFT training.
*   **Fall Back to TRL**: For multi-GPU environments (using DDP/FSDP) or when
    Unsloth is unavailable, use Hugging Face **TRL** (`SFTTrainer`,
    `DPOTrainer`) coupled with **PEFT** and **bitsandbytes** (for QLoRA).
*   **Always use QLoRA (4-bit Quantization)**: Crucial for fitting Gemma models