train.py

# ✅ Final train.py with ZIP logic added
import unsloth  # must be first
import pandas as pd
import torch
from datasets import Dataset
from transformers import TrainingArguments
from unsloth import FastLanguageModel
from trl import SFTTrainer
import os
import shutil
import zipfile

# Load and format your dataset
df = pd.read_csv("data.csv")
df["text"] = df.apply(lambda row: f"### Instruction:\n{row['instruction']}\n\n### Response:\n{row['response']}\n", axis=1)
dataset = Dataset.from_pandas(df[["text"]])

# Load Unsloth model
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/Llama-3.2-3B-Instruct",
    max_seq_length = 2048,
    dtype = torch.float16,
    load_in_4bit = True,
)

# Apply LoRA without task_type
model = FastLanguageModel.get_peft_model(
    model,
    r = 8,
    lora_alpha = 32,
    lora_dropout = 0.05,
    bias = "none",
)

# Tokenize text
def tokenize(example):
    return tokenizer(example["text"], truncation=True, padding="max_length", max_length=512)

tokenized_dataset = dataset.map(tokenize, batched=True)

# Set up training
training_args = TrainingArguments(
    output_dir = "./output_model",
    per_device_train_batch_size = 2,
    num_train_epochs = 3,
    learning_rate = 2e-4,
    logging_steps = 10,
    save_steps = 100,
    fp16 = True,
)

# Train
trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    args = training_args,
    train_dataset = tokenized_dataset,
)

trainer.train()

# Save the fine-tuned LoRA adapter
output_dir = "./output_model"
os.makedirs(output_dir, exist_ok=True)
model.save_pretrained(output_dir)

# ✅ Zip it for download
zip_path = "/home/user/app/model.zip"
try:
    with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
        for root, _, files in os.walk(output_dir):
            for file in files:
                full_path = os.path.join(root, file)
                rel_path = os.path.relpath(full_path, output_dir)
                zipf.write(full_path, rel_path)
    print(f"✅ Zipped model to {zip_path}")
except Exception as e:
    print(f"❌ Failed to zip model: {e}")