model = FastLanguageModel.get_peft_model(
    model,
    use_gradient_checkpointing = "unsloth", # <<<<<<<
)

conda create --name unsloth_env python=3.10
conda activate unsloth_env
conda install pytorch-cuda=<12.1/11.8> pytorch cudatoolkit xformers -c pytorch -c nvidia -c xformers
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps trl peft accelerate bitsandbytes

import torch; torch.version.cuda

pip install --upgrade --force-reinstall --no-cache-dir torch==2.1.0 triton \
  --index-url https://download.pytorch.org/whl/cu121

pip install "unsloth[cu118] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere] @ git+https://github.com/unslothai/unsloth.git"

pip install --upgrade --force-reinstall --no-cache-dir torch==2.1.1 triton \
  --index-url https://download.pytorch.org/whl/cu121

pip install "unsloth[cu118-torch211] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-torch211] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere-torch211] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere-torch211] @ git+https://github.com/unslothai/unsloth.git"

pip install --upgrade --force-reinstall --no-cache-dir torch==2.2.0 triton \
  --index-url https://download.pytorch.org/whl/cu121

pip install "unsloth[cu118-torch220] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-torch220] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere-torch220] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere-torch220] @ git+https://github.com/unslothai/unsloth.git"

pip install --upgrade pip

# RTX 3090, 4090 Ampere GPUs:
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes
# Pre Ampere RTX 2080, T4, GTX 1080 GPUs:
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps xformers trl peft accelerate bitsandbytes

nvcc
python -m xformers.info
python -m bitsandbytes

from unsloth import FastLanguageModel
import torch
from trl import SFTTrainer
from transformers import TrainingArguments
from datasets import load_dataset
max_seq_length = 2048 # Supports RoPE Scaling interally, so choose any!
# Get LAION dataset
url = "https://huggingface.co/datasets/laion/OIG/resolve/main/unified_chip2.jsonl"
dataset = load_dataset("json", data_files = {"train" : url}, split = "train")
# 4bit pre quantized models we support - 4x faster downloading!
fourbit_models = [
"unsloth/mistral-7b-bnb-4bit",
"unsloth/llama-2-7b-bnb-4bit",
"unsloth/llama-2-13b-bnb-4bit",
"unsloth/codellama-34b-bnb-4bit",
"unsloth/tinyllama-bnb-4bit",
] # Go to https://huggingface.co/unsloth for more 4-bit models!
# Load Llama model
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/mistral-7b-bnb-4bit", # Supports Llama, Mistral - replace this!
max_seq_length = max_seq_length,
dtype = None,
load_in_4bit = True,
)
# Do model patching and add fast LoRA weights
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, # Supports any, but = 0 is optimized
bias = "none",    # Supports any, but = "none" is optimized
use_gradient_checkpointing = True,
random_state = 3407,
max_seq_length = max_seq_length,
use_rslora = False,  # We support rank stabilized LoRA
loftq_config = None, # And LoftQ
)
trainer = SFTTrainer(
model = model,
train_dataset = dataset,
dataset_text_field = "text",
max_seq_length = max_seq_length,
tokenizer = tokenizer,
args = TrainingArguments(
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4,
warmup_steps = 10,
max_steps = 60,
fp16 = not torch.cuda.is_bf16_supported(),
bf16 = torch.cuda.is_bf16_supported(),
logging_steps = 1,
output_dir = "outputs",
optim = "adamw_8bit",
seed = 3407,
),
)
trainer.train()
# Go to https://github.com/unslothai/unsloth/wiki for advanced tips like
# (1) Saving to GGUF / merging to 16bit for vLLM
# (2) Continued training from a saved LoRA adapter
# (3) Adding an evaluation loop / OOMs
# (4) Cutomized chat templates

from unsloth import FastLanguageModel, PatchDPOTrainer
PatchDPOTrainer()
import torch
from transformers import TrainingArguments
from trl import DPOTrainer
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/zephyr-sft-bnb-4bit",
max_seq_length = max_seq_length,
dtype = None,
load_in_4bit = True,
)
# Do model patching and add fast LoRA weights
model = FastLanguageModel.get_peft_model(
model,
r = 64,
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",],
lora_alpha = 64,
lora_dropout = 0, # Supports any, but = 0 is optimized
bias = "none",    # Supports any, but = "none" is optimized
use_gradient_checkpointing = True,
random_state = 3407,
max_seq_length = max_seq_length,
)
dpo_trainer = DPOTrainer(
model = model,
ref_model = None,
args = TrainingArguments(
per_device_train_batch_size = 4,
gradient_accumulation_steps = 8,
warmup_ratio = 0.1,
num_train_epochs = 3,
fp16 = not torch.cuda.is_bf16_supported(),
bf16 = torch.cuda.is_bf16_supported(),
logging_steps = 1,
optim = "adamw_8bit",
seed = 42,
output_dir = "outputs",
),
beta = 0.1,
train_dataset = YOUR_DATASET_HERE,
# eval_dataset = YOUR_DATASET_HERE,
tokenizer = tokenizer,
max_length = 1024,
max_prompt_length = 512,
)
dpo_trainer.train()