unsloth-qlora
Unsloth-qlora enables the fine-tuning of large-scale models (up to 70B parameters) on consumer-grade hardware. It utilizes dynamic 4-bit quantization which selectively preserves critical weights to maintain higher accuracy than standard quantization methods.
Profile →npx skills add majiayu000/claude-skill-registry --skill unsloth-qlora --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.
--- name: unsloth-qlora description: Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bit, load_in_4bit, bnb-4bit, VRAM optimization, dynamic quantization). --- ## Overview Unsloth-qlora enables the fine-tuning of large-scale models (up to 70B parameters) on consumer-grade hardware. It utilizes dynamic 4-bit quantization which selectively preserves critical weights to maintain higher accuracy than standard quantization methods. ## When to Use - When training on limited VRAM hardware (e.g., 24GB or 48GB cards). - When seeking to match full fine-tuning performance while using 4-bit precision. - When accuracy loss from standard BitsAndBytes quantization is unacceptable. ## Decision Tree 1. Do you need maximum VRAM savings? - Yes: Set `load_in_4bit = True`. 2. Is accuracy the priority over VRAM? - Yes: Use LoRA (16-bit) if VRAM permits; otherwise use `unsloth-bnb-4bit` models. 3. Are you training on all layers? - Yes: Target `q, k, v, o, gate, up, down` modules for optimal performance. ## Workflows 1. **Setting Up QLoRA**: Load models with the `-unsloth-bnb-4bit` suffix and initialize with `load_in_4bit = True`. 2. **
- Overview
- When to Use
- Decision Tree
- Workflows
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the unsloth-qlora skill do?
Unsloth-qlora enables the fine-tuning of large-scale models (up to 70B parameters) on consumer-grade hardware. It utilizes dynamic 4-bit quantization which selectively preserves critical weights to maintain higher accuracy than standard quantization methods.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill unsloth-qlora --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.