gemma-trainer
google-gemma/gemma-skillsSkill
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.
Why this score
This repo hosts 2 skills, so its 1,029 stars are split between them (about 515 each) for scoring.
Popularity score: 72/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 21, 2026 at commit b10b80b3f36d, with Cisco's open-source skill-scanner.
What its code does:
- Makes network requestsSKILL.md, assets/distill_dataset.py:179 and 1 more
Web addresses in its code:
- developers.google.comSKILL.md:167
- unsloth.aiSKILL.md:159
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onegemma-trainer google-gemma/gemma-skills · Skill | 72 | ★ 1.0k | ≈59 always | 17d ago |
| gentleman-trainer Gentleman-Programming/Gentleman.Dots · Skill Both about trainer | 75 | ★ 2.0k | ≈17 always | 24d ago |
| ai-toolkit-trainer artokun/comfyui-mcp · Skill Both about trainer and train | 69 | ★ 843 | ≈79 always | 16d ago |