> 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/zh/kuai-su-kai-shi/reinforcement-learning-rl-guide/preference-dpo-orpo-and-kto.md).

# 偏好优化训练 - DPO、ORPO 和 KTO

了解如何通过 Unsloth 使用 DPO、GRPO、ORPO 或 KTO 进行偏好对齐微调，请按照以下步骤操作：

DPO（直接偏好优化）、ORPO（赔率比偏好优化）、PPO、KTO 奖励建模都可与 Unsloth 配合使用。

我们有用于复现 GRPO、ORPO、DPO Zephyr、KTO 和 SimPO 的 Google Colab 笔记本：

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

我们也出现在 🤗Hugging Face 的官方文档中！我们在 [SFT 文档](https://huggingface.co/docs/trl/main/en/sft_trainer#accelerate-fine-tuning-2x-using-unsloth) 以及 [DPO 文档](https://huggingface.co/docs/trl/main/en/dpo_trainer#accelerate-dpo-fine-tuning-using-unsloth).

## DPO 代码

```python
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 可选设置 GPU 设备 ID

from unsloth import FastLanguageModel, PatchDPOTrainer
from unsloth import is_bfloat16_supported
PatchDPOTrainer()
import torch
from trl import DPOTrainer, DPOConfig  # 已从 TrainingArguments 更改

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

# 进行模型补丁处理并添加快速 LoRA 权重
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，# 支持任意值，但 = 0 已做优化
    bias = "none"，    # 支持任意值，但 = "none" 已做优化
    # [NEW] "unsloth" 可减少 30% VRAM 占用，适配 2 倍更大的批量大小！
    use_gradient_checkpointing = "unsloth"，# 对于超长上下文可设为 True 或 "unsloth"
    random_state = 3407,
    max_seq_length = max_seq_length,
)

dpo_trainer = DPOTrainer(
    model = model,
    ref_model = None,
    args = DPOConfig( # 使用 DPOConfig
        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/zh/kuai-su-kai-shi/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.