Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/peft
Parameter-Efficient Fine-Tuning (PEFT) library. LoRA, QLoRA, AdaLoRA, IA3, Prefix Tuning, P-Tuning, Prompt Tuning. Fine-tune large models with minimal memory overhead. Hugging Face ecosystem integration.
Passed 22 of 22 test cases with the skill, and 21 of 22 without it.
1 fixed21 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
When defining a standard LoRA config, I usually set rank r to 16. What is the standard matching lora_alpha value recommended for standard scaling?
| Checked | Without skill | With skill |
|---|---|---|
| sets lora_alpha to 32 | Missed | Passed |
The instructions your model reads when the skill loads.
PEFT (Parameter-Efficient Fine-Tuning) adapts large pretrained models by training only a small subset of parameters. Supports LoRA, QLoRA, AdaLoRA, IA3, Prefix Tuning, P-Tuning, and Prompt Tuning. Reduces GPU memory by 4-16x compared to full fine-tuning.
uv pip install peft
from transformers import AutoModelForCausalLM
from peft import LoraConfig, get_peft_model, TaskType
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
peft_config = LoraConfig(
r=16, lora_alpha=32,
target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
task_type=TaskType.CAUSAL_LM,
)
model = get_peft_model(model, peft_config)
model.print_trainable_parameters()
model.save_pretrained("adapter")
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
merged = PeftModel.from_pretrained(base, "adapter").merge_and_unload()
from transformers import BitsAndBytesConfig
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct",
test cases passed, vs 21 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.