25 min
Lesson 4 of 7
Hands-On Tutorial: End-to-End Fine-Tuning
From the course AI Fine-Tuning Pipelines
Build a complete fine-tuning pipeline from scratch with runnable code.
Project: Customer Support Model
We'll fine-tune Llama-2-7b to answer customer support questions for an e-commerce store.
Step 1: Install Dependencies
pip install transformers peft datasets trl accelerate bitsandbytes
pip install wandb # for experiment tracking
Step 2: Prepare Your Dataset
from datasets import Dataset
import json
# Load your JSONL training data
def load_support_dataset(filepath):
examples = []
with open(filepath) as f:
for line in f:
item = json.loads(line)
examples.append({
"messages": [
{"role": "system", "content": "You are a helpful customer support agent for ShopEasy."},
{"role": "user", "content": item["question"]},
{"role": "assistant", "content": item["answer"]}
]
})
return Dataset.from_list(examples)
dataset = load_support_dataset("support_data.jsonl")
dataset = dataset.train_test_split(test_size=0.1)
Step 3: Load Base Model with QLoRA
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import LoraConfig, get_peft_model
import torch
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
model = AutoModelForCausalLM.from_pretrained(
"meta-llama/Llama-2-7b-hf",
quantization_config=bnb_config,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
tokenizer.pad_token = tokenizer.eos_token
lora_config = LoraConfig(r=16, lora_alpha=32, lora_dropout=0.05, bias="none", task_type="CAUSAL_LM")
model = get_peft_model(model, lora_config)
Step 4: Train with TRL's SFTTrainer
from trl import SFTTrainer
from transformers import TrainingArguments
training_args = TrainingArguments(
output_dir="./results",
num_train_epochs=3,
per_device_train_batch_size=4,
gradient_accumulation_steps=4,
learning_rate=2e-4,
fp16=True,
save_steps=100,
logging_steps=25,
report_to="wandb"
)
trainer = SFTTrainer(
model=model,
args=training_args,
train_dataset=dataset["train"],
eval_dataset=dataset["test"],
tokenizer=tokenizer,
max_seq_length=2048
)
trainer.train()
trainer.save_model("./fine-tuned-support-model")
Step 5: Run Inference
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf", device_map="auto")
model = PeftModel.from_pretrained(base, "./fine-tuned-support-model")
def answer_question(question: str) -> str:
prompt = f"[INST] <<SYS>>You are a helpful customer support agent.<</SYS>>
{question} [/INST]"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
print(answer_question("Where is my order #12345?"))
Key Takeaways
- •QLoRA with 4-bit quantization lets you fine-tune a 7B model on a single 24GB GPU
- •TRL's SFTTrainer handles chat-format datasets natively — no custom data collator needed
- •Gradient accumulation (steps=4) simulates larger batch sizes on limited hardware
- •Always split 10% of data for evaluation and log metrics to Weights & Biases
0 of 7 lessons marked complete
Progress is kept in this browser only.