Individual skill
unsloth
Use when fine-tuning an open-weight LLM fast on ONE GPU with low VRAM — Unsloth's fast model loaders with 4-bit QLoRA and the trl trainer, response-only loss masking so the prompt is not trained on, GRPO reasoning fine-tunes, and export to merged 16-bit, GGUF or the Hub. NOT whether, why or which method to fine-tune (that is `finetuning`), NOT running the exported GGUF locally (that is `ollama`), NOT serving-engine flags and throughput (that is `vllm`), NOT building the JSONL dataset (that is `training-data`).
skills/unsloth/SKILL.md
Source commit d9d6bb338f66cc1e23998585e580a0ea45bbcb82
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 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)
- 561
- Repository last updated
- Nov 4, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- ai-coding Repository topic
- claude-code Repository topic
- cli Repository topic
- cline Repository topic
- codex Repository topic
- coding-assistant Repository topic
- cursor Repository topic
- unsloth Declared skill tag
- qlora Declared skill tag
- lora Declared skill tag
- single-gpu Declared skill tag
- gguf Declared skill tag
- fine-tuning Declared skill tag
- data 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 · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesSKILL.mdcore · 14,310 bytesevals/README.mddoc · 756 bytesevals/cases.yamlasset · 3,858 bytesreferences/export.mddoc · 3,554 bytesreferences/grpo.mddoc · 3,742 bytesreferences/masking-and-templates.mddoc · 4,281 bytes
Read excerpt
# Unsloth — fast, low-VRAM fine-tuning on one GPU
Unsloth is a fine-tuning *backend*: hand-written Triton kernels + a patched LoRA/QLoRA path that make
`transformers` + `trl` training run faster and fit a much bigger model on a single consumer GPU. You
reach for it when the *decision to fine-tune is already made* and the problem is now "make this run on
the one GPU I have." This skill owns the backend + the export mechanics. It does **not** decide
whether fine-tuning is even the right move (`finetuning`), and it does **not** run the model you
export (`ollama` / `vllm`).
## Read this first (the two things that bite everyone)
1. **Single-GPU is the free-tier assumption.** The open (Apache-2.0) core is built for one GPU.
Multi-GPU / multi-node "works but a better version is coming" per the docs, and the polished
multi-GPU + full-finetuning path is gated behind the paid Pro/Enterprise tiers — **verify the