LLM fine-tuning and prompt-tuning techniques
Triggers when users need to fine-tune models for specific tasks or domains. Provides parameter-efficient methods like LoRA and QLoRA for resource-constrained environments, with dataset preparation templates and training configurations.
/plugin marketplace add pluginagentmarketplace/custom-plugin-prompt-engineering/plugin install prompt-engineering-assistant@pluginagentmarketplace-prompt-engineeringThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/config.yamlassets/schema.jsonreferences/GUIDE.mdreferences/PATTERNS.mdscripts/validate.pyBonded to: prompt-optimization-agent
Skill("custom-plugin-prompt-engineering:fine-tuning")
parameters:
tuning_method:
type: enum
values: [full, lora, qlora, prompt_tuning, prefix_tuning]
default: lora
dataset_size:
type: enum
values: [small, medium, large]
description: "<1k, 1k-10k, >10k examples"
compute_budget:
type: enum
values: [low, medium, high]
default: medium
| Method | Parameters | Compute | Quality | Best For |
|---|---|---|---|---|
| Full Fine-tune | All | Very High | Highest | Maximum customization |
| LoRA | ~0.1% | Low | High | Resource-constrained |
| QLoRA | ~0.1% | Very Low | Good | Consumer GPUs |
| Prompt Tuning | <0.01% | Minimal | Good | Simple tasks |
| Prefix Tuning | ~0.1% | Low | Good | Generation tasks |
formats:
instruction:
template: |
### Instruction
{instruction}
### Response
{response}
chat:
template: |
<|user|>
{user_message}
<|assistant|>
{assistant_response}
completion:
template: "{input}{output}"
quality_checklist:
- [ ] No duplicate examples
- [ ] Consistent formatting
- [ ] Diverse examples
- [ ] Balanced categories
- [ ] High-quality outputs
- [ ] No harmful content
training_config:
hyperparameters:
learning_rate: 2e-5
batch_size: 8
epochs: 3
warmup_ratio: 0.1
lora_config:
r: 16
alpha: 32
dropout: 0.05
target_modules: ["q_proj", "v_proj"]
evaluation:
eval_steps: 100
save_steps: 500
metric: loss
| Metric | Purpose | Target |
|---|---|---|
| Loss | Training progress | Decreasing |
| Accuracy | Task performance | >90% |
| Perplexity | Model confidence | <10 |
| Human eval | Quality assessment | Preferred >80% |
| Issue | Cause | Solution |
|---|---|---|
| Overfitting | Small dataset | Add regularization |
| Underfitting | Low epochs | Increase training |
| Catastrophic forgetting | Aggressive tuning | Lower learning rate |
| Poor generalization | Data bias | Diversify dataset |
See: Hugging Face PEFT, OpenAI Fine-tuning Guide
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.