From 06de7fb9cc6e72301a647cc21bb307ae930120f7 Mon Sep 17 00:00:00 2001
From: wehub-resource-sync <resource-sync@wehub.local>
Date: Mon, 13 Jul 2026 10:36:39 +0000
Subject: [PATCH] docs: make Chinese README the default

---
 README.md | 84 +++++++++++++++++++++++++++++--------------------------
 1 file changed, 45 insertions(+), 39 deletions(-)

diff --git a/README.md b/README.md
index aaa9e7e..c7b2a50 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,9 @@
+<!-- WEHUB_ZH_README -->
+> [!NOTE]
+> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。  
+> [English](./README.en.md) · [原始项目](https://github.com/huggingface/peft) · [上游 README](https://github.com/huggingface/peft/blob/HEAD/README.md)  
+> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
+
 <!---
 Copyright 2023 The HuggingFace Team. All rights reserved.
 
@@ -16,27 +22,27 @@ limitations under the License.
 
 <h1 align="center"> <p>🤗 PEFT</p></h1>
 <h3 align="center">
-    <p>State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods</p>
+    <p>先进的参数高效微调（Parameter-Efficient Fine-Tuning，PEFT）方法</p>
 </h3>
 
-Fine-tuning large pretrained models is often prohibitively costly due to their scale. Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of large pretrained models to various downstream applications by only fine-tuning a small number of (extra) model parameters instead of all the model's parameters. This significantly decreases the computational and storage costs. Recent state-of-the-art PEFT techniques achieve performance comparable to fully fine-tuned models.
+微调大型预训练模型往往因其规模而成本过高。参数高效微调（PEFT）方法通过只微调少量（额外）模型参数，而非全部模型参数，使大型预训练模型能够高效适应各种下游应用。这显著降低了计算和存储成本。近期最先进的 PEFT 技术可达到与全量微调模型相当的性能。
 
-PEFT is integrated with Transformers for easy model training and inference, Diffusers for conveniently managing different adapters, and Accelerate for distributed training and inference for really big models.
+PEFT 已与 Transformers 集成，便于模型训练与推理；与 Diffusers 集成，便于管理不同的适配器；与 Accelerate 集成，支持超大模型的分布式训练与推理。
 
 > [!TIP]
-> Visit the [PEFT](https://huggingface.co/PEFT) organization to read about the PEFT methods implemented in the library and to see notebooks demonstrating how to apply these methods to a variety of downstream tasks. Click the "Watch repos" button on the organization page to be notified of newly implemented methods and notebooks!
+> 访问 [PEFT](https://huggingface.co/PEFT) 组织页面，了解库中实现的 PEFT 方法，并查看演示如何将这些方法应用于各类下游任务的 notebook。点击组织页面的「Watch repos」按钮，以便在新方法和新 notebook 发布时收到通知！
 
-Check the PEFT Adapters API Reference section for a list of supported PEFT methods, and read the [Adapters](https://huggingface.co/docs/peft/en/conceptual_guides/adapter), [Soft prompts](https://huggingface.co/docs/peft/en/conceptual_guides/prompting), and [IA3](https://huggingface.co/docs/peft/en/conceptual_guides/ia3) conceptual guides to learn more about how these methods work.
+查看 PEFT Adapters API Reference 部分以获取支持的 PEFT 方法列表，并阅读 [Adapters](https://huggingface.co/docs/peft/en/conceptual_guides/adapter),、[Soft prompts](https://huggingface.co/docs/peft/en/conceptual_guides/prompting), 和 [IA3](https://huggingface.co/docs/peft/en/conceptual_guides/ia3) 概念指南，进一步了解这些方法的工作原理。
 
-## Quickstart
+## 快速入门
 
-Install PEFT from pip:
+通过 pip 安装 PEFT：
 
 ```bash
 pip install peft
 ```
 
-Prepare a model for training with a PEFT method such as LoRA by wrapping the base model and PEFT configuration with `get_peft_model`. For the bigscience/mt0-large model, you're only training 0.19% of the parameters!
+使用 `get_peft_model` 将基础模型与 PEFT 配置包装起来，即可用 LoRA 等 PEFT 方法为训练准备模型。对于 bigscience/mt0-large 模型，你只需训练 0.19% 的参数！
 
 ```python
 import torch
@@ -60,7 +66,7 @@ model.print_trainable_parameters()
 model.save_pretrained("qwen2.5-3b-lora")
 ```
 
-To load a PEFT model for inference:
+加载 PEFT 模型进行推理：
 
 ```python
 import torch
@@ -80,60 +86,60 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 # prints something like: Preheat the oven to 350 degrees and place the cookie dough in a baking dish [...]
 ```
 
-## Why you should use PEFT
+## 为何应使用 PEFT
 
-There are many benefits of using PEFT but the main one is the huge savings in compute and storage, making PEFT applicable to many different use cases.
+使用 PEFT 有许多优势，但最主要的是在计算和存储方面的大幅节省，使 PEFT 适用于许多不同的用例。
 
-### High performance on consumer hardware
+### 在消费级硬件上实现高性能
 
-Consider the memory requirements for training the following models on the [ought/raft/twitter_complaints](https://huggingface.co/datasets/ought/raft/viewer/twitter_complaints) dataset with an A100 80GB GPU with more than 64GB of CPU RAM.
+以下是在 [ought/raft/twitter_complaints](https://huggingface.co/datasets/ought/raft/viewer/twitter_complaints) 数据集上、使用配备 80GB 显存的 A100 GPU 且 CPU RAM 超过 64GB 时，训练下列模型的内存需求。
 
-|   Model         | Full Finetuning | PEFT-LoRA PyTorch  | PEFT-LoRA DeepSpeed with CPU Offloading |
+|   模型         | 全量微调 | PEFT-LoRA PyTorch  | 带 CPU Offloading 的 PEFT-LoRA DeepSpeed |
 | --------- | ---- | ---- | ---- |
 | bigscience/T0_3B (3B params) | 47.14GB GPU / 2.96GB CPU  | 14.4GB GPU / 2.96GB CPU | 9.8GB GPU / 17.8GB CPU |
 | bigscience/mt0-xxl (12B params) | OOM GPU | 56GB GPU / 3GB CPU | 22GB GPU / 52GB CPU |
 | bigscience/bloomz-7b1 (7B params) | OOM GPU | 32GB GPU / 3.8GB CPU | 18.1GB GPU / 35GB CPU |
 
-With LoRA you can fully finetune a 12B parameter model that would've otherwise run out of memory on the 80GB GPU, and comfortably fit and train a 3B parameter model. When you look at the 3B parameter model's performance, it is comparable to a fully finetuned model at a fraction of the GPU memory.
+借助 LoRA，你可以全量微调一个 12B 参数模型——否则在 80GB GPU 上会显存不足（OOM）——并能舒适地容纳并训练 3B 参数模型。若观察 3B 参数模型的性能，其在仅占全量微调模型一小部分 GPU 显存的情况下，表现与之相当。
 
-|   Submission Name        | Accuracy |
+|   提交名称        | 准确率 |
 | --------- | ---- |
 | Human baseline (crowdsourced) |	0.897 |
 | Flan-T5 | 0.892 |
 | lora-t0-3b | 0.863 |
 
 > [!TIP]
-> The bigscience/T0_3B model performance isn't optimized in the table above. You can squeeze even more performance out of it by playing around with the input instruction templates, LoRA hyperparameters, and other training related hyperparameters. The final checkpoint size of this model is just 19MB compared to 11GB of the full bigscience/T0_3B model. Learn more about the advantages of finetuning with PEFT in this [blog post](https://www.philschmid.de/fine-tune-flan-t5-peft).
+> 上表中 bigscience/T0_3B 模型的性能尚未优化。你可以通过调整输入指令模板、LoRA 超参数及其他训练相关超参数，进一步榨取性能。该模型的最终 checkpoint 大小仅为 19MB，而完整的 bigscience/T0_3B 模型为 11GB。在这篇[博客文章](https://www.philschmid.de/fine-tune-flan-t5-peft). 中了解更多使用 PEFT 进行微调的优势。
 
-### Quantization
+### 量化
 
-Quantization is another method for reducing the memory requirements of a model by representing the data in a lower precision. It can be combined with PEFT methods to make it even easier to train and load LLMs for inference.
+量化是另一种通过以较低精度表示数据来降低模型内存需求的方法。它可以与 PEFT 方法结合使用，使训练和加载 LLM 进行推理更加容易。
 
-* Learn how to finetune [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) with QLoRA and the [TRL](https://huggingface.co/docs/trl/index) library on a 16GB GPU in the [Finetune LLMs on your own consumer hardware using tools from PyTorch and Hugging Face ecosystem](https://pytorch.org/blog/finetune-llms/) blog post.
-* Learn how to finetune a [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) model for multilingual automatic speech recognition with LoRA and 8-bit quantization in this [notebook](https://colab.research.google.com/drive/1DOkD_5OUjFa0r5Ik3SgywJLJtEo2qLxO?usp=sharing) (see this [notebook](https://colab.research.google.com/drive/1vhF8yueFqha3Y3CpTHN6q9EVcII9EYzs?usp=sharing) instead for an example of streaming a dataset).
+* 在这篇[博客文章](https://pytorch.org/blog/finetune-llms/) 中学习如何在 16GB GPU 上使用 QLoRA 和 [TRL](https://huggingface.co/docs/trl/index) 库微调 [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)——参见《使用 PyTorch 和 Hugging Face 生态工具在你自己的消费级硬件上微调 LLM》。
+* 在这份 [notebook](https://colab.research.google.com/drive/1DOkD_5OUjFa0r5Ik3SgywJLJtEo2qLxO?usp=sharing) 中学习如何使用 LoRA 和 8-bit 量化微调 [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) 模型以实现多语言自动语音识别（若要查看流式传输数据集的示例，请参阅这份 [notebook](https://colab.research.google.com/drive/1vhF8yueFqha3Y3CpTHN6q9EVcII9EYzs?usp=sharing)）。
 
-### Save compute and storage
+### 节省计算与存储
 
-PEFT can help you save storage by avoiding full finetuning of models on each of downstream task or dataset. In many cases, you're only finetuning a very small fraction of a model's parameters and each checkpoint is only a few MBs in size (instead of GBs). These smaller PEFT adapters demonstrate performance comparable to a fully finetuned model. If you have many datasets, you can save a lot of storage with a PEFT model and not have to worry about catastrophic forgetting or overfitting the backbone or base model.
+PEFT 可帮助你在每个下游任务或数据集上避免全量微调模型，从而节省存储空间。在许多情况下，你只需微调模型参数的极小一部分，每个 checkpoint 仅几 MB（而非 GB）。这些更小的 PEFT 适配器可达到与全量微调模型相当的性能。若你有许多数据集，使用 PEFT 模型可节省大量存储，且无需担心灾难性遗忘或对骨干/基础模型过拟合。
 
-## PEFT integrations
+## PEFT 集成
 
-PEFT is widely supported across the Hugging Face ecosystem because of the massive efficiency it brings to training and inference.
+PEFT 在 Hugging Face 生态系统中得到广泛支持，因为它为训练与推理带来了巨大的效率提升。
 
 ### Diffusers
 
-The iterative diffusion process consumes a lot of memory which can make it difficult to train. PEFT can help reduce the memory requirements and reduce the storage size of the final model checkpoint. For example, consider the memory required for training a Stable Diffusion model with LoRA on an A100 80GB GPU with more than 64GB of CPU RAM. The final model checkpoint size is only 8.8MB!
+迭代扩散过程会消耗大量内存，使训练变得困难。PEFT 可帮助降低内存需求并减小最终模型 checkpoint 的存储体积。例如，在配备 80GB 显存的 A100 GPU 且 CPU RAM 超过 64GB 的条件下，考虑使用 LoRA 训练 Stable Diffusion 模型所需的内存。最终模型 checkpoint 大小仅为 8.8MB！
 
 |   Model         | Full Finetuning | PEFT-LoRA  | PEFT-LoRA with Gradient Checkpointing  |
 | --------- | ---- | ---- | ---- |
 | CompVis/stable-diffusion-v1-4 | 27.5GB GPU / 3.97GB CPU | 15.5GB GPU / 3.84GB CPU | 8.12GB GPU / 3.77GB CPU | 
 
 > [!TIP]
-> Take a look at the [examples/lora_dreambooth/train_dreambooth.py](examples/lora_dreambooth/train_dreambooth.py) training script to try training your own Stable Diffusion model with LoRA, and play around with the [smangrul/peft-lora-sd-dreambooth](https://huggingface.co/spaces/smangrul/peft-lora-sd-dreambooth) Space which is running on a T4 instance. Learn more about the PEFT integration in Diffusers in this [tutorial](https://huggingface.co/docs/peft/main/en/tutorial/peft_integrations#diffusers).
+> 查看 [examples/lora_dreambooth/train_dreambooth.py](examples/lora_dreambooth/train_dreambooth.py) 训练脚本，尝试使用 LoRA 训练你自己的 Stable Diffusion 模型，还可以在运行在 T4 实例上的 [smangrul/peft-lora-sd-dreambooth](https://huggingface.co/spaces/smangrul/peft-lora-sd-dreambooth) Space 中进行体验。阅读这篇 [tutorial](https://huggingface.co/docs/peft/main/en/tutorial/peft_integrations#diffusers). 了解更多关于 Diffusers 中 PEFT 集成的内容。
 
 ### Transformers
 
-PEFT is directly integrated with [Transformers](https://huggingface.co/docs/transformers/main/en/peft). After loading a model, call `add_adapter` to add a new PEFT adapter to the model:
+PEFT 已与 [Transformers](https://huggingface.co/docs/transformers/main/en/peft). 直接集成。加载模型后，调用 `add_adapter` 可为模型添加新的 PEFT 适配器：
 
 ```python
 from peft import LoraConfig
@@ -142,44 +148,44 @@ peft_config = LoraConfig(...)
 model.add_adapter(peft_config, adapter_name="lora_1")
 ```
 
-To load a trained PEFT adapter, call `load_adapter`:
+要加载已训练的 PEFT 适配器，请调用 `load_adapter`：
 
 ```python
 model = ...  # transformers model
 model.load_adapter(<path-to-adapter>, adapter_name="lora_1")
 ```
 
-And to switch between different adapters, call `set_adapter`:
+要在不同适配器之间切换，请调用 `set_adapter`：
 
 ```python
 model.set_adapter("lora_2")
 ```
 
-The Transformers integration doesn't include all the functionalities offered in PEFT, such as methods for merging the adapter into the base model.
+Transformers 集成并未包含 PEFT 提供的全部功能，例如将适配器合并到基础模型中的方法。
 
 ### Accelerate
 
-[Accelerate](https://huggingface.co/docs/accelerate/index) is a library for distributed training and inference on various training setups and hardware (GPUs, TPUs, Apple Silicon, etc.). PEFT models work with Accelerate out of the box, making it really convenient to train really large models or use them for inference on consumer hardware with limited resources.
+[Accelerate](https://huggingface.co/docs/accelerate/index) 是一个用于在各种训练配置和硬件（GPU、TPU、Apple Silicon 等）上进行分布式训练与推理的库。PEFT 模型可与 Accelerate 开箱即用（out of the box）协同工作，让你能够非常方便地训练超大规模模型，或在资源有限的消费级硬件上进行推理。
 
 ### TRL
 
-PEFT can also be applied to training LLMs with RLHF components such as the ranker and policy. Get started by reading:
+PEFT 也可用于训练包含 RLHF 组件（如 ranker 和 policy）的 LLM。可通过阅读以下内容入门：
 
-* [Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) with PEFT and the [TRL](https://huggingface.co/docs/trl/index) library to learn more about the Direct Preference Optimization (DPO) method and how to apply it to a LLM.
-* [Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU](https://huggingface.co/blog/trl-peft) with PEFT and the [TRL](https://huggingface.co/docs/trl/index) library, and then try out the [gpt2-sentiment_peft.ipynb](https://github.com/huggingface/trl/blob/main/examples/notebooks/gpt2-sentiment.ipynb) notebook to optimize GPT2 to generate positive movie reviews.
-* [StackLLaMA: A hands-on guide to train LLaMA with RLHF](https://huggingface.co/blog/stackllama) with PEFT, and then try out the [stack_llama/scripts](https://github.com/huggingface/trl/tree/main/examples/research_projects/stack_llama/scripts) for supervised finetuning, reward modeling, and RL finetuning.
+* [使用直接偏好优化（Direct Preference Optimization，DPO）微调 Mistral-7b 模型](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) 结合 PEFT 与 [TRL](https://huggingface.co/docs/trl/index) 库，了解更多关于 DPO 方法及其在 LLM 上的应用。
+* [在 24GB 消费级 GPU 上使用 RLHF 微调 20B LLM](https://huggingface.co/blog/trl-peft) 结合 PEFT 与 [TRL](https://huggingface.co/docs/trl/index) 库，然后试用 [gpt2-sentiment_peft.ipynb](https://github.com/huggingface/trl/blob/main/examples/notebooks/gpt2-sentiment.ipynb) 笔记本，优化 GPT2 以生成正面的电影评论。
+* [StackLLaMA：使用 RLHF 训练 LLaMA 的实战指南](https://huggingface.co/blog/stackllama) 结合 PEFT，然后试用 [stack_llama/scripts](https://github.com/huggingface/trl/tree/main/examples/research_projects/stack_llama/scripts) 进行监督微调、奖励建模和 RL 微调。
 
 ## Model support
 
-Use this [Space](https://stevhliu-peft-methods.hf.space) or check out the [docs](https://huggingface.co/docs/peft/main/en/index) to find which models officially support a PEFT method out of the box. Even if you don't see a model listed below, you can manually configure the model config to enable PEFT for a model. Read the [New transformers architecture](https://huggingface.co/docs/peft/main/en/developer_guides/custom_models#new-transformers-architectures) guide to learn how.
+使用此 [Space](https://stevhliu-peft-methods.hf.space) 或查看 [docs](https://huggingface.co/docs/peft/main/en/index)，了解哪些模型开箱即支持 PEFT 方法。即使下方列表中没有某个模型，你也可以手动配置模型 config 以为其启用 PEFT。阅读 [New transformers architecture](https://huggingface.co/docs/peft/main/en/developer_guides/custom_models#new-transformers-architectures) 指南了解具体做法。
 
 ## Contribute
 
-If you would like to contribute to PEFT, please check out our [contribution guide](https://huggingface.co/docs/peft/developer_guides/contributing).
+如果你想为 PEFT 做出贡献，请查看我们的 [contribution guide](https://huggingface.co/docs/peft/developer_guides/contributing).
 
 ## Citing 🤗 PEFT
 
-To use 🤗 PEFT in your publication, please cite it by using the following BibTeX entry.
+若要在出版物中使用 🤗 PEFT，请使用以下 BibTeX 条目进行引用。
 
 ```bibtex
 @Misc{peft,