如何使用Unsloth和QLoRA在本地数据集上微调Mistral或Llama 3模型

!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git" !pip install --no-deps xformers trl peft accelerate bitsandbytes print("Unsloth installed successfully!")

from unsloth import FastLanguageModel
import torch
from trl import SFTTrainer
from transformers import TrainingArguments
from datasets import Dataset
import pandas as pd
import numpy as np

print("Unsloth loaded successfully!")
print(f"PyTorch: {torch.__version__}")
print(f"CUDA: {torch.cuda.is_available()}")
print(f"GPU: {torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'None'}")

print("Creating customer support Q&A dataset...")
# Create realistic customer support data
customer_support_data = [
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "How do I reset my password?",
        "output": "To reset your password: 1) Click 'Forgot Password' on the login page 2) Enter your registered email 3) Check your inbox for the reset link 4) Click the link and create a new password. Check your spam folder if not received within 5 minutes."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "My payment was declined, what should I do?",
        "output": "Common solutions: 1) Check that the card has sufficient funds 2) Ensure the card is not expired 3) Contact your bank to unblock the transaction 4) Try an alternative payment method like PayPal 5) Wait 24 hours before retrying."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "How do I cancel my subscription?",
        "output": "To cancel: 1) Log in to your account 2) Go to 'Billing & Subscriptions' 3) Click 'Cancel Subscription' 4) Confirm cancellation. Your access continues until the end of the billing period. No partial refunds."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "The app keeps crashing on startup",
        "output": "Troubleshooting steps: 1) Update the app to the latest version 2) Restart your device 3) Clear the app cache/data 4) Reinstall the app 5) Ensure 500MB free storage 6) Update your device OS. If it persists, contact support with error logs."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "Where is my order tracking information?",
        "output": "You can find tracking: 1) Check the confirmation email 2) Log into your account > Orders 3) Click the tracking number. Standard shipping: 3-5 business days. Contact the carrier with the tracking number for the exact location."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "How do I contact customer support?",
        "output": "Support options: 1) Live chat: Mon–Fri 9AM–6PM EST 2) Email: support@company.com (response within 24h) 3) Phone: 1-800-123-4567 4) Twitter: @CompanySupport. Please have your account email ready."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "Can I get a refund?",
        "output": "Refund policy: 1) Digital products: Refund within 14 days if not used 2) Subscriptions: No refunds for partial months 3) Physical goods: Return within 30 days with receipt. Contact billing@company.com with your order ID."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "How do I change my email address?",
        "output": "To change your email: 1) Log in to your account 2) Go to Account Settings 3) Click 'Change Email' 4) Enter the new email 5) Verify via the confirmation email sent to the new address. The update takes effect immediately."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "Is my data secure?",
        "output": "Yes, we use: 1) AES-256 encryption 2) SSL/TLS for all connections 3) Regular security audits 4) GDPR compliance 5) Data is never sold to third parties. Read our privacy policy for details."
    },
    {
        "instruction": "You are a helpful customer support agent. Answer clearly and professionally.",
        "input": "Do you offer student discounts?",
        "output": "Yes! Student discount: 50% off. Requirements: 1) Valid .edu email OR 2) Student ID photo. Apply: Email student@company.com with proof. The discount is applied after verification."
    },
]

expanded_data = []
for item in customer_support_data * 30: # Creates 300 samples
    expanded_data.append(item.copy())

# Convert to dataset
dataset = Dataset.from_pandas(pd.DataFrame(expanded_data))
print(f"Dataset created: {len(dataset)} samples")
print(f"Sample:\n{dataset[0]}")

model_name = "unsloth/mistral-7b"
print(f"Selected: {model_name}")
print("Loading model (takes 2-5 minutes)...")

max_seq_length = 1024
dtype = torch.float16
load_in_4bit = True

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=model_name,
    max_seq_length=max_seq_length,
    dtype=dtype,
    load_in_4bit=load_in_4bit,
)

print("Model loaded successfully!")
if torch.cuda.is_available():
    print(f"Memory used: {torch.cuda.memory_allocated() / 1e9:.2f} GB")

model = FastLanguageModel.get_peft_model(
    model,
    r=16,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    lora_alpha=16,
    lora_dropout=0,
    bias="none",
    use_gradient_checkpointing="unsloth",
    random_state=3407,
    use_rslora=False,
    loftq_config=None,
)
print("LoRA adapters added!")
print("Trainable parameters added: Only ~1% of total parameters!")