# 训练后使用模型

使用 SFTTrainer 或 DPOTrainer 训练模型后，你将获得一个可用于文本生成的微调模型。在本节中，我们将介绍加载微调模型并生成文本的流程。如果你需要使用训练好的模型运行推理服务器，可以探索 [`text-generation-inference`](https://github.com/huggingface/text-generation-inference) 等库。

## 加载和生成

如果您已对模型进行了完全微调，即未使用 PEFT，则可以像加载 transformers 中的任何其他语言模型一样直接加载它：

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name_or_path = "Qwen/Qwen3-0.6B" #path/to/your/model/or/name/on/hub
device = torch.accelerator.current_accelerator() if torch.accelerator.is_available() else "cpu"

model = AutoModelForCausalLM.from_pretrained(model_name_or_path).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)

inputs = tokenizer.encode("This movie was really", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```

或者，您也可以使用 pipeline：

```python
from transformers import pipeline

model_name_or_path = "Qwen/Qwen3-0.6B" #path/to/your/model/or/name/on/hub
pipe = pipeline("text-generation", model=model_name_or_path)
print(pipe("This movie was really")[0]["generated_text"])
```

## 使用 Adapters PEFT

```python
from peft import PeftConfig, PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model_name = "Qwen/Qwen3-0.6B" #path/to/your/model/or/name/on/hub
adapter_model_name = "path/to/my/adapter"

model = AutoModelForCausalLM.from_pretrained(base_model_name)
model = PeftModel.from_pretrained(model, adapter_model_name)

tokenizer = AutoTokenizer.from_pretrained(base_model_name)
```

您还可以将适配器合并到基础模型中，从而像使用普通的 Transformers 模型一样使用该模型，但检查点文件会显著增大：

```python
model = AutoModelForCausalLM.from_pretrained(base_model_name)
model = PeftModel.from_pretrained(model, adapter_model_name)

model = model.merge_and_unload()
model.save_pretrained("merged_adapters")
```

加载模型后，无论您是将适配器合并还是将其单独保留在模型之上，都可以按照上文所述，像运行普通模型一样执行生成。

