unsloth-training
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF.
npx skills add majiayu000/claude-skill-registry --skill unsloth-training-skill-scientiacapital-skills-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.
<objective> Guide LLM fine-tuning using Unsloth: 1. **GRPO** - RL with reward functions (no labeled outputs needed) 2. **SFT** - Supervised fine-tuning with input/output pairs 3. **Vision** - VLM fine-tuning (Qwen3-VL, Gemma3, Llama 3.2 Vision) Key capabilities: - **FP8 Training** - 60% less VRAM, 1.4x faster (RTX 40+, H100) - **3x Packing** - Automatic 2-5x speedup for mixed-length data - **Docker** - Official `unsloth/unsloth` image - **Mobile** - QAT → ExecuTorch → iOS/Android (~40 tok/s) - **Export** - GGUF, Ollama, vLLM, LM Studio, SGLang </objective> <quick_start> **GRPO with FP8 (60% less VRAM):** ```python import os os.environ['UNSLOTH_VLLM_STANDBY'] = "1" # Shared memory from unsloth import FastLanguageModel from trl import GRPOConfig, GRPOTrainer model, tokenizer = FastLanguageModel.from_pretrained( model_name="unsloth/Qwen3-8B", max_seq_length=2048, load_in_fp8=True, fast_inference=True, ) model = FastLanguageModel.get_peft_model( model, r=64, target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], use_gradient_checkpointing="unsloth", ) def correctness_reward(completions, answer, **kwargs): return [2.0 if extract_answer(c) == a else
- When to Use GRPO vs SFT
- Model Selection
- Core Hyperparameters
- Reward Function Design
- Pattern 1: Correctness (Primary Signal)
- Pattern 2: Format Compliance
- Pattern 3: Reasoning Quality
- Pattern 4: Negative Constraints
- Typical Reward Stack
- Prompt Structure
- System Prompt with XML Tags
- Extraction Helpers
- Dataset Format
- Save and Deploy
Create Modelfile cat > Modelfile << EOF ollama create my-model -f Modelfile ollama run my-model "Solve: 15 + 27 = ?"
What does the unsloth-training skill do?
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill unsloth-training-skill-scientiacapital-skills-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.