Fine-tuning LLMs with LoRA and QLoRA

pip install transformers peft bitsandbytes accelerate datasets

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True
)

model = AutoModelForCausalLM.from_pretrained(
    "mistralai/Mistral-7B-v0.1",
    quantization_config=bnb_config,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")

from peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training

model = prepare_model_for_kbit_training(model)

lora_config = LoraConfig(
    r=16,                      # Rank
    lora_alpha=32,             # Scaling factor
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM"
)

model = get_peft_model(model, lora_config)
model.print_trainable_parameters()
# trainable params: 4,194,304 || all params: 3,752,071,168 || trainable%: 0.11%

from transformers import TrainingArguments, Trainer

training_args = TrainingArguments(
    output_dir="./lora-mistral",
    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=train_dataset,
    tokenizer=tokenizer
)
trainer.train()

# Save LoRA adapter
model.save_pretrained("./lora-adapter")

# Merge with base model for inference
merged_model = model.merge_and_unload()
merged_model.save_pretrained("./merged-model")