peft-fine-tuning

•

6.6k5133 months ago

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Quick Install

npxskills add orchestra-research/ai-research-skills--skill peft-fine-tuning

Instructions

PEFT (Parameter-Efficient Fine-Tuning)

Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods.

When to use PEFT

Use PEFT/LoRA when:

Fine-tuning 7B-70B models on consumer GPUs (RTX 4090, A100)
Need to train <1% parameters (6MB adapters vs 14GB full model)
Want fast iteration with multiple task-specific adapters
Deploying multiple fine-tuned variants from one base model

Use QLoRA (PEFT + quantization) when:

Fine-tuning 70B models on single 24GB GPU
Memory is the primary constraint
Can accept ~5% quality trade-off vs full fine-tuning

Use full fine-tuning instead when:

Training small models (<1B parameters)
Need maximum quality and have compute budget
Significant domain shift requires updating all weights

Quick start

Installation

# Basic installation
pip install peft

# With quantization support (recommended)
pip install peft bitsandbytes

# Full stack
pip install peft transformers accelerate bitsandbytes datasets

LoRA fine-tuning (standard)

from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer
from peft import get_peft_model, LoraConfig, TaskType
from datasets import load_dataset

# Load base model
model_name = "meta-llama/Llama-3.1-8B"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token

# LoRA configuration
lora_config = LoraConfig(
    task_type=TaskType.CAUSAL_LM,
    r=16,                          # Rank (8-64, higher = more capacity)
    lora_alpha=32,                 # Scaling factor (typically 2*r)
    lora_dropout=0.05,             # Dropout for regularization
    target_modules=["q_proj", "v_proj", "k_proj", "o_proj"],  # Attention layers
    bias="none"                    # Don't train biases
)

# Apply LoRA
model = get_peft_model(model, lora_config)
model.print_trainable_parameters()
# Output: trainable params: 13,631,488 || all params: 8,043,307,008 || trainable%: 0.17%

# Prepare dataset
dataset = load_dataset("databricks/databricks-dolly-15k", split="train")

def tokenize(example):
    text = f"### Instruction:\n{example['instruction']}\n\n### Response:\n{example['response']}"
    return tokenizer(text, truncation=True, max_length=512, padding="max_length")

tokenized = dataset.map(tokenize, remove_columns=dataset.column_names)

# Training
training_args = TrainingArguments(
    output_dir="./lora-llama",
    num_train_epochs=3,
    per_device_train_batch_size=4,
    gradient_accumulation_steps=4,
    learning_rate=2e-4,
    fp16=True,
    logging_steps=10,
    save_strategy="epoch"
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized,
    data_collator=lambda data: {"input_ids": torch.stack([f["input_ids"] for f in data]),
                                 "attention_mask": torch.stack([f["attention_mask"] for f in data]),
                                 "labels": torch.stack([f["input_ids"] for f in data])}
)

trainer.train()

# Save adapter only (6MB vs 16GB)
model.save_pretrained("./lora-llama-adapter")

Loading…

Related Skills

skill-creator

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

367,360

skill-creator

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

367,309

1password

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

365,915

himalaya

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

365,885

Tags & Topics

aiai-researchclaudeclaude-codeclaude-skillscodex

When to use PEFT

Use PEFT/LoRA when:

Fine-tuning 7B-70B models on consumer GPUs (RTX 4090, A100)

Need to train <1% parameters (6MB adapters vs 14GB full model)

Want fast iteration with multiple task-specific adapters

Deploying multiple fine-tuned variants from one base model

Use QLoRA (PEFT + quantization) when:

Fine-tuning 70B models on single 24GB GPU

Memory is the primary constraint

Can accept ~5% quality trade-off vs full fine-tuning

Use full fine-tuning instead when:

Training small models (<1B parameters)

Need maximum quality and have compute budget

Significant domain shift requires updating all weights

Quick start

Installation

# Basic installation pip install peft # With quantization support (recommended) pip install peft bitsandbytes # Full stack pip install peft transformers accelerate bitsandbytes datasets

LoRA fine-tuning (standard)

from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer from peft import get_peft_model, LoraConfig, TaskType from datasets import load_dataset # Load base model model_name = "meta-llama/Llama-3.1-8B" model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") tokenizer = AutoTokenizer.from_pretrained(model_name) tokenizer.pad_token = tokenizer.eos_token # LoRA configuration lora_config = LoraConfig( task_type=TaskType.CAUSAL_LM, r=16, # Rank (8-64, higher = more capacity) lora_alpha=32, # Scaling factor (typically 2*r) lora_dropout=0.05, # Dropout for regularization target_modules=["q_proj", "v_proj", "k_proj", "o_proj"], # Attention layers bias="none" # Don't train biases ) # Apply LoRA model = get_peft_model(model, lora_config) model.print_trainable_parameters() # Output: trainable params: 13,631,488 || all params: 8,043,307,008 || trainable%: 0.17% # Prepare dataset dataset = load_dataset("databricks/databricks-dolly-15k", split="train") def tokenize(example): text = f"### Instruction:\n{example['instruction']}\n\n### Response:\n{example['response']}" return tokenizer(text, truncation=True, max_length=512, padding="max_length") tokenized = dataset.map(tokenize, remove_columns=dataset.column_names) # Training training_args = TrainingArguments( output_dir="./lora-llama", num_train_epochs=3, per_device_train_batch_size=4, gradient_accumulation_steps=4, learning_rate=2e-4, fp16=True, logging_steps=10, save_strategy="epoch" ) trainer = Trainer( model=model, args=training_args, train_dataset=tokenized, data_collator=lambda data: {"input_ids": torch.stack([f["input_ids"] for f in data]), "attention_mask": torch.stack([f["attention_mask"] for f in data]), "labels": torch.stack([f["input_ids"] for f in data])} ) trainer.train() # Save adapter only (6MB vs 16GB) model.save_pretrained("./lora-llama-adapter")

Rank	Trainable Params	Memory	Quality	Use Case
4	~3M	Minimal	Lower	Simple tasks, prototyping
8	~7M	Low	Good	Recommended starting point
16	~14M	Medium	Better	General fine-tuning
32	~27M	Higher	High	Complex tasks
64	~54M	High	Highest	Domain adaptation, 70B models

Method	Trainable %	Memory	Speed	Best For
LoRA	0.1-1%	Low	Fast	General fine-tuning
QLoRA	0.1-1%	Very Low	Medium	Memory-constrained
AdaLoRA	0.1-1%	Low	Medium	Automatic rank selection
IA3	0.01%	Minimal	Fastest	Few-shot adaptation
Prefix Tuning	0.1%	Low	Medium	Generation control
Prompt Tuning	0.001%	Minimal	Fast	Simple task adaptation
P-Tuning v2	0.1%	Low	Medium	NLU tasks

Method	GPU Memory	Trainable Params
Full fine-tuning	60+ GB	8B (100%)
LoRA r=16	18 GB	14M (0.17%)
QLoRA r=16	6 GB	14M (0.17%)
IA3	16 GB	800K (0.01%)

Method	Tokens/sec	vs Full FT
Full FT	2,500	1x
LoRA	3,200	1.3x
QLoRA	2,100	0.84x

Model	Full FT	LoRA	QLoRA
Llama 2-7B	45.3	44.8	44.1
Llama 2-13B	54.8	54.2	53.5

peft-fine-tuning

PEFT (Parameter-Efficient Fine-Tuning)

When to use PEFT

Quick start

Installation

LoRA fine-tuning (standard)

Related Skills

skill-creator

skill-creator

1password

himalaya

PEFT (Parameter-Efficient Fine-Tuning)

When to use PEFT

Quick start

Installation

LoRA fine-tuning (standard)

QLoRA fine-tuning (memory-efficient)

LoRA parameter selection

Rank (r) - capacity vs efficiency

Alpha (lora_alpha) - scaling factor

Target modules by architecture

Loading and merging adapters

Load trained adapter

Merge adapter into base model

Multi-adapter serving

PEFT methods comparison

IA3 (minimal parameters)

Prefix Tuning

Integration patterns

With TRL (SFTTrainer)

With Axolotl (YAML config)

With vLLM (inference)

Performance benchmarks

Memory usage (Llama 3.1 8B)

Training speed (A100 80GB)

Quality (MMLU benchmark)

Common issues

CUDA OOM during training

Adapter not applying

Quality degradation

Best practices

References

Resources

Related Skills

skill-creator

skill-creator

1password

himalaya

Related Skills

skill-creator

skill-creator

1password

himalaya