> For the complete documentation index, see [llms.txt](https://unsloth.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://unsloth.ai/docs/de/loslegen/reinforcement-learning-rl-guide/preference-dpo-orpo-and-kto.md).

# Training zur Präferenzoptimierung – DPO, ORPO & KTO

Erfahre mehr über Fine-Tuning zur Präferenzanpassung mit DPO, GRPO, ORPO oder KTO über Unsloth, befolge die folgenden Schritte:

DPO (Direct Preference Optimization), ORPO (Odds Ratio Preference Optimization), PPO, KTO Reward Modelling funktionieren alle mit Unsloth.

Wir haben Google-Colab-Notebooks zur Reproduktion von GRPO, ORPO, DPO Zephyr, KTO und SimPO:

* [GRPO-Notebooks](/docs/de/loslegen/unsloth-notebooks.md#grpo-reasoning-rl-notebooks)
* [ORPO-Notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_\(8B\)-ORPO.ipynb)
* [DPO-Zephyr-Notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Zephyr_\(7B\)-DPO.ipynb)
* [KTO-Notebook](https://colab.research.google.com/drive/1MRgGtLWuZX4ypSfGguFgC-IblTvO2ivM?usp=sharing)
* [SimPO-Notebook](https://colab.research.google.com/drive/1Hs5oQDovOay4mFA6Y9lQhVJ8TnbFLFh2?usp=sharing)

Wir sind auch in den offiziellen Dokumenten von 🤗Hugging Face! Wir sind in den [SFT-Dokumenten](https://huggingface.co/docs/trl/main/en/sft_trainer#accelerate-fine-tuning-2x-using-unsloth) und den [DPO-Dokumenten](https://huggingface.co/docs/trl/main/en/dpo_trainer#accelerate-dpo-fine-tuning-using-unsloth).

## DPO-Code

```python
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0" # Optionale Festlegung der GPU-Geräte-ID

from unsloth import FastLanguageModel, PatchDPOTrainer
from unsloth import is_bfloat16_supported
PatchDPOTrainer()
import torch
from trl import DPOTrainer, DPOConfig  # Geändert von TrainingArguments

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/zephyr-sft-bnb-4bit",
    max_seq_length = max_seq_length,
    dtype = None,
    load_in_4bit = True,
)

# Modell-Patching durchführen und schnelle LoRA-Gewichte hinzufügen
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, # Unterstützt alles, aber = 0 ist optimiert
    bias = "none",    # Unterstützt alles, aber = "none" ist optimiert
    # [NEU] "unsloth" benötigt 30 % weniger VRAM und passt in 2x größere Batchgrößen!
    use_gradient_checkpointing = "unsloth", # True oder "unsloth" für sehr lange Kontexte
    random_state = 3407,
    max_seq_length = max_seq_length,
)

dpo_trainer = DPOTrainer(
    model = model,
    ref_model = None,
    args = DPOConfig( # DPOConfig verwenden
        per_device_train_batch_size = 4,
        gradient_accumulation_steps = 8,
        warmup_ratio = 0.1,
        num_train_epochs = 3,
        fp16 = not is_bfloat16_supported(),
        bf16 = is_bfloat16_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()
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://unsloth.ai/docs/de/loslegen/reinforcement-learning-rl-guide/preference-dpo-orpo-and-kto.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.