Przejdź do treści
Biblioteka skilli
AI i agenci · Budowanie i kod

peft

/peft

Dopracowuje duże modele językowe metodami LoRA i QLoRA, gdy brakuje pamięci GPU i liczy się mała liczba parametrów.

Repozytorium
kheish ↗
Licencja
Apache-2.0
Ostatnia zmiana repozytorium
25.06.2026

Ocena i bezpieczeństwo

82/ 100Klasa: dobry
Format9 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena13 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
3
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
3
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.06.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co robi i kiedy

Dopracowuje duże modele językowe metodami LoRA i QLoRA, gdy brakuje pamięci GPU i liczy się mała liczba parametrów.

Oryginalny opis (EN)

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.

Jak działa

  1. Kheish Compatibility
  2. When to use PEFT
  3. Quick start
  4. LoRA parameter selection
  5. Loading and merging adapters
  6. PEFT methods comparison
  7. Integration patterns
  8. Performance benchmarks
  9. Common issues
  10. Best practices
Sekcje z nagłówków SKILL.md, w oryginale · 436 linii, 1 427 słów
Podgląd SKILL.md
---
description: 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.
version: 1.0.0
author: Orchestra Research
license: MIT
dependencies:
- peft>=0.13.0
- transformers>=4.45.0
- torch>=2.0.0
- bitsandbytes>=0.43.0
metadata:
  catalog:
    tags:
    - Fine-Tuning
    - PEFT
    - LoRA
    - QLoRA
    - Parameter-Efficient
    - Adapters
    - Low-Rank
    - Memory Optimization
    - Multi-Adapter
---

## Kheish Compatibility

This skill is repo-local and stays inactive until explicitly activated.

When the original instructions refer to legacy tool names, use these Kheish mappings:

- `terminal` => `bash`
- `web_extract` => `web_fetch`, plus `web_search` when discovery is needed
- `search_files` => `grep_search` and `glob_search`
- `browser_*` tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly

When the instructions mention local helper files, resolve them from `${KHEISH_SKILL_DIR}`.

# 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

```bash
# 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)

```python
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")
```

### QLoRA fine-tuning (memory-efficient)

```python
from transformers import AutoModelForCausalLM, BitsAndBytesConfig
from peft import get_peft_model, LoraConfig, prepare_model_for_kbit_training

# 4-bit quantization config
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",           # NormalFloat4 (best for LLMs)
    bnb_4bit_compute_dtype="bfloat16",   # Compute in bf16
    bnb_4bit_use_double_quant=True       # Nested quantization
)

# Load quantized model
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-70B",
    quantization_config=bnb_config,
    device_map="auto"
)

# Prepare for training (enables gradient checkpointing)
model = prepare_model_for_kbit_training(model)

# LoRA config for QLoRA
lora_config = LoraConfig(
    r=64,                              # Higher rank for 70B
    lora_alpha=128,
    lora_dropout=0.1,
    target_modules=["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    bias="none",
    task_type="CAUSAL_LM"
)

model = get_peft_model(model, lora_config)
# 70B model now fits on single 24GB GPU!
```

## LoRA parameter selection

### Rank (r) - capacity vs efficiency

| 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 |

### Alpha (lora_alpha) - scaling factor

```python
# Rule of thumb: alpha = 2 * rank
LoraConfig(r=16, lora_alpha=32)  # Standard
LoraConfig(r=16, lora_alpha=16)  # Conservative (lower learning rate effect)
LoraConfig(r=16, lora_alpha=64)  # Aggressive (higher learning rate effect)
```

### Target modules by architecture

```python
# Llama / Mistral / Qwen
target_modules = ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]

# GPT-2 / GPT-Neo
target_modules = ["c_attn", "c_proj", "c_fc"]

# Falcon
target_modules = ["query_key_value", "dense", "dense_h_to_4h", "dense_4h_to_h"]

# BLOOM
target_modules = ["query_key_value", "dense", "dense_h_to_4h", "dense_4h_to_h"]

# Auto-detect all linear layers
target_modules = "all-linear"  # PEFT 0.6.0+
```

## Loading and merging adapters

### Load trained adapter

```python
from peft import PeftModel, AutoPeftModelForCausalLM
from transformers import AutoModelForCausalLM

# Option 1: Load with PeftModel
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B")
model = PeftModel.from_pretrained(base_model, "./lora-llama-adapter")

# Option 2: Load directly (recommended)
model = AutoPeftModelForCausalLM.from_pretrained(
    "./lora-llama-adapter",
    device_map="auto"
)
```

### Merge adapter into base model

```python
# Merge for deployment (no adapter overhead)
merged_model = model.merge_and_unload()

# Save merged model
merged_model.save_pretrained("./llama-merged")
tokenizer.save_pretrained("./llama-merged")

# Push to Hub
merged_model.push_to_hub("username/llama-finetuned")
```

### Multi-adapter serving

```python
from peft import PeftModel

# Load base with first adapter
model = AutoPeftModelForCausalLM.from_pretrained("./adapter-task1")

# Load additional adapters
model.load_adapter("./adapter-task2", adapter_name="task2")
model.load_adapter("./adapter-task3", adapter_name="task3")

# Switch between adapters at runtime
model.set_adapter("task1")  # Use task1 adapter
output1 = model.generate(**inputs)

model.set_adapter("task2")  # Switch to task2
output2 = model.generate(**inputs)

# Disable adapters (use base model)
with model.disable_adapter():
    base_output = model.generate(**inputs)
```

## PEFT methods comparison

| 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 |

### IA3 (minimal parameters)

```python
from peft import IA3Config

ia3_config = IA3Config(
    target_modules=["q_proj", "v_proj", "k_proj", "down_proj"],
    feedforward_modules=["down_proj"]
)
model = get_peft_model(model, ia3_config)
# Trains only 0.01% of parameters!
```

### Prefix Tuning

```python
from peft import PrefixTuningConfig

prefix_config = PrefixTuningConfig(
    task_type="CAUSAL_LM",
    num_virtual_tokens=20,      # Prepended tokens
    prefix_projection=True       # Use MLP projection
)
model = get_peft_model(model, prefix_config)
```

## Integration patterns

### With TRL (SFTTrainer)

```python
from trl import SFTTrainer, SFTConfig
from peft import LoraConfig

lora_config = LoraConfig(r=16, lora_alpha=32, target_modules="all-linear")

trainer = SFTTrainer(
    model=model,
    args=SFTConfig(output_dir="./output", max_seq_length=512),
    train_dataset=dataset,
    peft_config=lora_config,  # Pass LoRA config directly
)
trainer.train()
```

### With Axolotl (YAML config)

```yaml
# axolotl config.yaml
adapter: lora
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_target_linear: true  # Target all linear layers
```

### With vLLM (inference)

```python
from vllm import LLM
from vllm.lora.request import LoRARequest

# Load base model with LoRA support
llm = LLM(model="meta-llama/Llama-3.1-8B", enable_lora=True)

# Serve with adapter
outputs = llm.generate(
    prompts,
    lora_request=LoRARequest("adapter1", 1, "./lora-adapter")
)
```

## Performance benchmarks

### Memory usage (Llama 3.1 8B)

| 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%) |

### Training speed (A100 80GB)

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

### Quality (MMLU benchmark)

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

## Common issues

### CUDA OOM during training

```python
# Solution 1: Enable gradient checkpointing
model.gradient_checkpointing_enable()

# Solution 2: Reduce batch size + increase accumulation
TrainingArguments(
    per_device_train_batch_size=1,
    gradient_accumulation_steps=16
)

# Solution 3: Use QLoRA
from transformers import BitsAndBytesConfig
bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4")
```

### Adapter not applying

```python
# Verify adapter is active
print(model.active_adapters)  # Should show adapter name

# Check trainable parameters
model.print_trainable_parameters()

# Ensure model in training mode
model.train()
```

### Quality degradation

```python
# Increase rank
LoraConfig(r=32, lora_alpha=64)

# Target more modules
target_modules = "all-linear"

# Use more training data and epochs
TrainingArguments(num_train_epochs=5)

# Lower learning rate
TrainingArguments(learning_rate=1e-4)
```

## Best practices

1. **Start with r=8-16**, increase if quality insufficient
2. **Use alpha = 2 * rank** as starting point
3. **Target attention + MLP layers** for best quality/efficiency
4. **Enable gradient checkpointing** for memory savings
5. **Save adapters frequently** (small files, easy rollback)
6. **Evaluate on held-out data** before merging
7. **Use QLoRA for 70B+ models** on consumer hardware

## References

- **[Advanced Usage](references/advanced-usage.md)** - DoRA, LoftQ, rank stabilization, custom modules
- **[Troubleshooting](references/troubleshooting.md)** - Common errors, debugging, optimization

## Resources

- **GitHub**: https://github.com/huggingface/peft
- **Docs**: https://huggingface.co/docs/peft
- **LoRA Paper**: arXiv:2106.09685
- **QLoRA Paper**: arXiv:2305.14314
- **Models**: https://huggingface.co/models?library=peft
Pliki w paczce (3)
  • SKILL.md 13 KB
  • references/advanced-usage.md 12 KB
  • references/troubleshooting.md 10 KB

Wersje

W bazie nie ma innych skilli o nazwie peft.

Migawka bazy z 13.11.2026 · wersja paczki 8137f161bd33 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 1 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 93peft-fine-tuning
    Pomaga dostroić duże modele językowe metodami LoRA i QLoRA przy ograniczonej pamięci GPU.
  • 98peft-fine-tuning
    Dostraja duże modele językowe metodami PEFT, takimi jak LoRA i QLoRA, przy ograniczonej pamięci GPU i z obsługą wielu adapterów.
  • 93peft-fine-tuning
    Dostraja duże modele LLM metodami LoRA, QLoRA i ponad 25 innymi przy ograniczonej pamięci GPU, trenując mniej niż 1 proc. parametrów, także z wieloma adapterami.
  • 100peft-fine-tuning
    Prowadzi dostrajanie modeli językowych metodami oszczędnymi parametrowo, w tym LoRA i QLoRA, także modeli 7B-70B na kartach konsumenckich.
  • 100fine-tuning-llms-lora-qlora
    Dostraja otwarte modele językowe na danych domenowych metodami LoRA i 4-bitowego QLoRA, oszczędnie pod względem parametrów.
  • 98fine-tuning-expert
    Pomaga dostrajać modele językowe: adaptery LoRA i QLoRA, zbiory danych JSONL, hiperparametry, DPO i wdrażanie dostrojonych modeli.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.