From 6a7718722fa58e52639e8172dca1bac423ee3cb9 Mon Sep 17 00:00:00 2001
From: wehub-resource-sync <resource-sync@wehub.local>
Date: Mon, 13 Jul 2026 10:25:31 +0000
Subject: [PATCH] docs: make Chinese README the default

---
 README.md | 308 ++++++++++++++++++++++++++++--------------------------
 1 file changed, 157 insertions(+), 151 deletions(-)

diff --git a/README.md b/README.md
index 6510b8a..3fc176f 100644
--- a/README.md
+++ b/README.md
@@ -1,82 +1,88 @@
+<!-- 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/lm-sys/FastChat) · [上游 README](https://github.com/lm-sys/FastChat/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。
+
 # FastChat
 | [**Demo**](https://lmarena.ai/) | [**Discord**](https://discord.gg/6GXcFg3TH8) | [**X**](https://x.com/lmsysorg) |
 
-FastChat is an open platform for training, serving, and evaluating large language model based chatbots.
-- FastChat powers Chatbot Arena ([lmarena.ai](https://lmarena.ai)), serving over 10 million chat requests for 70+ LLMs.
-- Chatbot Arena has collected over 1.5M human votes from side-by-side LLM battles to compile an online [LLM Elo leaderboard](https://lmarena.ai/?leaderboard).
+FastChat 是一个用于训练、部署和评估基于大语言模型（LLM）的聊天机器人的开放平台。
+- FastChat 为 Chatbot Arena（[lmarena.ai](https://lmarena.ai)), 提供支持，已为 70 多款 LLM 处理超过 1000 万次聊天请求。
+- Chatbot Arena 已通过并排 LLM 对战收集了超过 150 万条人工投票，并据此编制了在线 [LLM Elo 排行榜](https://lmarena.ai/?leaderboard).
 
-FastChat's core features include:
-- The training and evaluation code for state-of-the-art models (e.g., Vicuna, MT-Bench).
-- A distributed multi-model serving system with web UI and OpenAI-compatible RESTful APIs.
+FastChat 的核心功能包括：
+- 最先进模型（例如 Vicuna、MT-Bench）的训练与评估代码。
+- 带 Web UI 且兼容 OpenAI 的 RESTful API 的分布式多模型服务系统。
 
 ## News
-- [2024/03] 🔥 We released Chatbot Arena technical [report](https://arxiv.org/abs/2403.04132).
-- [2023/09] We released **LMSYS-Chat-1M**, a large-scale real-world LLM conversation dataset. Read the [report](https://arxiv.org/abs/2309.11998).
-- [2023/08] We released **Vicuna v1.5** based on Llama 2 with 4K and 16K context lengths. Download [weights](#vicuna-weights).
-- [2023/07] We released **Chatbot Arena Conversations**, a dataset containing 33k conversations with human preferences. Download it [here](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations).
+- [2024/03] 🔥 我们发布了 Chatbot Arena 技术[报告](https://arxiv.org/abs/2403.04132).
+- [2023/09] 我们发布了 **LMSYS-Chat-1M**，一个大规模真实世界 LLM 对话数据集。阅读[报告](https://arxiv.org/abs/2309.11998).
+- [2023/08] 我们基于 Llama 2 发布了 **Vicuna v1.5**，支持 4K 和 16K 上下文长度。下载[权重](#vicuna-weights)。
+- [2023/07] 我们发布了 **Chatbot Arena Conversations**，一个包含 3.3 万条带有人类偏好标注的对话数据集。在[此处](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations). 下载。
 
 <details>
-<summary>More</summary>
+<summary>更多</summary>
 
-- [2023/08] We released **LongChat v1.5** based on Llama 2 with 32K context lengths. Download [weights](#longchat).
-- [2023/06] We introduced **MT-bench**, a challenging multi-turn question set for evaluating chatbots. Check out the blog [post](https://lmsys.org/blog/2023-06-22-leaderboard/).
-- [2023/06] We introduced **LongChat**, our long-context chatbots and evaluation tools. Check out the blog [post](https://lmsys.org/blog/2023-06-29-longchat/).
-- [2023/05] We introduced **Chatbot Arena** for battles among LLMs. Check out the blog [post](https://lmsys.org/blog/2023-05-03-arena).
-- [2023/03] We released **Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality**. Check out the blog [post](https://vicuna.lmsys.org).
+- [2023/08] 我们基于 Llama 2 发布了 **LongChat v1.5**，支持 32K 上下文长度。下载[权重](#longchat)。
+- [2023/06] 我们推出了 **MT-bench**，一套用于评估聊天机器人的挑战性多轮问答集。查看博客[文章](https://lmsys.org/blog/2023-06-22-leaderboard/).
+- [2023/06] 我们推出了 **LongChat**，即我们的长上下文聊天机器人及评估工具。查看博客[文章](https://lmsys.org/blog/2023-06-29-longchat/).
+- [2023/05] 我们推出了 **Chatbot Arena**，用于 LLM 之间的对战。查看博客[文章](https://lmsys.org/blog/2023-05-03-arena).
+- [2023/03] 我们发布了 **Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality**。查看博客[文章](https://vicuna.lmsys.org).
 
 </details>
 
 <a href="https://lmarena.ai"><img src="assets/demo_narrow.gif" width="70%"></a>
 
 ## Contents
-- [Install](#install)
-- [Model Weights](#model-weights)
-- [Inference with Command Line Interface](#inference-with-command-line-interface)
-- [Serving with Web GUI](#serving-with-web-gui)
+- [安装](#install)
+- [模型权重](#model-weights)
+- [使用命令行界面进行推理](#inference-with-command-line-interface)
+- [使用 Web GUI 部署服务](#serving-with-web-gui)
 - [API](#api)
-- [Evaluation](#evaluation)
-- [Fine-tuning](#fine-tuning)
-- [Citation](#citation)
+- [评估](#evaluation)
+- [微调](#fine-tuning)
+- [引用](#citation)
 
-## Install
+## 安装
 
-### Method 1: With pip
+### 方法 1：使用 pip
 
 ```bash
 pip3 install "fschat[model_worker,webui]"
 ```
 
-### Method 2: From source
+### 方法 2：从源码安装
 
-1. Clone this repository and navigate to the FastChat folder
+1. 克隆本仓库并进入 FastChat 文件夹
 ```bash
 git clone https://github.com/lm-sys/FastChat.git
 cd FastChat
 ```
 
-If you are running on Mac:
+如果你在 Mac 上运行：
 ```bash
 brew install rust cmake
 ```
 
-2. Install Package
+2. 安装软件包
 ```bash
 pip3 install --upgrade pip  # enable PEP 660 support
 pip3 install -e ".[model_worker,webui]"
 ```
 
-## Model Weights
-### Vicuna Weights
-[Vicuna](https://lmsys.org/blog/2023-03-30-vicuna/) is based on Llama 2 and should be used under Llama's [model license](https://github.com/facebookresearch/llama/blob/main/LICENSE).
+## 模型权重
+### Vicuna 权重
+[Vicuna](https://lmsys.org/blog/2023-03-30-vicuna/) 基于 Llama 2，使用时应遵守 Llama 的[模型许可证](https://github.com/facebookresearch/llama/blob/main/LICENSE).
 
-You can use the commands below to start chatting. It will automatically download the weights from Hugging Face repos.
-Downloaded weights are stored in a `.cache` folder in the user's home folder (e.g., `~/.cache/huggingface/hub/<model_name>`).
+你可以使用下面的命令开始聊天。权重将自动从 Hugging Face 仓库下载。
+下载的权重保存在用户主目录下的 `.cache` 文件夹中（例如 `~/.cache/huggingface/hub/<model_name>`）。
 
-See more command options and how to handle out-of-memory in the "Inference with Command Line Interface" section below.
+有关更多命令选项以及如何处理内存不足问题，请参阅下文「使用命令行界面进行推理」一节。
 
-**NOTE: `transformers>=4.31` is required for 16K versions.**
+**注意：16K 版本需要 `transformers>=4.31`。**
 
-| Size | Chat Command | Hugging Face Repo |
+| 规模 | 聊天命令 | Hugging Face 仓库 |
 | ---  | --- | --- |
 | 7B   | `python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5`  | [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)   |
 | 7B-16k   | `python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5-16k`  | [lmsys/vicuna-7b-v1.5-16k](https://huggingface.co/lmsys/vicuna-7b-v1.5-16k)   |
@@ -84,166 +90,166 @@ See more command options and how to handle out-of-memory in the "Inference with
 | 13B-16k  | `python3 -m fastchat.serve.cli --model-path lmsys/vicuna-13b-v1.5-16k` | [lmsys/vicuna-13b-v1.5-16k](https://huggingface.co/lmsys/vicuna-13b-v1.5-16k) |
 | 33B  | `python3 -m fastchat.serve.cli --model-path lmsys/vicuna-33b-v1.3` | [lmsys/vicuna-33b-v1.3](https://huggingface.co/lmsys/vicuna-33b-v1.3) |
 
-**Old weights**: see [docs/vicuna_weights_version.md](docs/vicuna_weights_version.md) for all versions of weights and their differences.
+**旧版权重**：有关所有权重的版本及其差异，请参阅 [docs/vicuna_weights_version.md](docs/vicuna_weights_version.md)。
 
-### Other Models
-Besides Vicuna, we also released two additional models: [LongChat](https://lmsys.org/blog/2023-06-29-longchat/) and FastChat-T5.
-You can use the commands below to chat with them. They will automatically download the weights from Hugging Face repos.
+### 其他模型
+除 Vicuna 外，我们还发布了另外两款模型：[LongChat](https://lmsys.org/blog/2023-06-29-longchat/) 和 FastChat-T5。
+你可以使用下面的命令与它们聊天。权重将自动从 Hugging Face 仓库下载。
 
-| Model | Chat Command | Hugging Face Repo |
+| 模型 | 聊天命令 | Hugging Face 仓库 |
 | ---  | --- | --- |
 | LongChat-7B   | `python3 -m fastchat.serve.cli --model-path lmsys/longchat-7b-32k-v1.5`  | [lmsys/longchat-7b-32k](https://huggingface.co/lmsys/longchat-7b-32k-v1.5)   |
 | FastChat-T5-3B   | `python3 -m fastchat.serve.cli --model-path lmsys/fastchat-t5-3b-v1.0`  | [lmsys/fastchat-t5-3b-v1.0](https://huggingface.co/lmsys/fastchat-t5-3b-v1.0) |
 
-## Inference with Command Line Interface
+## 使用命令行界面进行推理
 
 <a href="https://lmarena.ai"><img src="assets/screenshot_cli.png" width="70%"></a>
 
-(Experimental Feature: You can specify `--style rich` to enable rich text output and better text streaming quality for some non-ASCII content. This may not work properly on certain terminals.)
+（实验性功能：你可以指定 `--style rich` 以启用富文本输出，并改善部分非 ASCII 内容的文本流式输出质量。某些终端上可能无法正常工作。）
 
-#### Supported Models
-FastChat supports a wide range of models, including
-LLama 2, Vicuna, Alpaca, Baize, ChatGLM, Dolly, Falcon, FastChat-T5, GPT4ALL, Guanaco, MTP, OpenAssistant, OpenChat, RedPajama, StableLM, WizardLM, xDAN-AI and more.
+#### 支持的模型
+FastChat 支持多种模型，包括
+LLama 2、Vicuna、Alpaca、Baize、ChatGLM、Dolly、Falcon、FastChat-T5、GPT4ALL、Guanaco、MTP、OpenAssistant、OpenChat、RedPajama、StableLM、WizardLM、xDAN-AI 等。
 
-See a complete list of supported models and instructions to add a new model [here](docs/model_support.md).
+完整支持的模型列表及添加新模型的说明请见[此处](docs/model_support.md)。
 
-#### Single GPU
-The command below requires around 14GB of GPU memory for Vicuna-7B and 28GB of GPU memory for Vicuna-13B.
-See the ["Not Enough Memory" section](#not-enough-memory) below if you do not have enough memory.
-`--model-path` can be a local folder or a Hugging Face repo name.
+#### 单 GPU
+下面的命令大约需要 14GB GPU 显存（Vicuna-7B）和 28GB GPU 显存（Vicuna-13B）。
+如果显存不足，请参阅下文[「内存不足」](#not-enough-memory)一节。
+`--model-path` 可以是本地文件夹或 Hugging Face 仓库名称。
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5
 ```
 
-#### Multiple GPUs
-You can use model parallelism to aggregate GPU memory from multiple GPUs on the same machine. 
+#### 多 GPU
+你可以使用模型并行，聚合同一台机器上多块 GPU 的显存。
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --num-gpus 2
 ```
 
-Tips:
-Sometimes the "auto" device mapping strategy in huggingface/transformers does not perfectly balance the memory allocation across multiple GPUs.
-You can use `--max-gpu-memory` to specify the maximum memory per GPU for storing model weights.
-This allows it to allocate more memory for activations, so you can use longer context lengths or larger batch sizes. For example,
+提示：
+有时 huggingface/transformers 中的「auto」设备映射策略无法在多块 GPU 之间完美平衡内存分配。
+你可以使用 `--max-gpu-memory` 指定每块 GPU 用于存储模型权重的最大内存。
+这样可为激活值分配更多内存，从而使用更长的上下文长度或更大的批大小。例如，
 
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --num-gpus 2 --max-gpu-memory 8GiB
 ```
 
-#### CPU Only
-This runs on the CPU only and does not require GPU. It requires around 30GB of CPU memory for Vicuna-7B and around 60GB of CPU memory for Vicuna-13B.
+#### 仅 CPU
+这仅在 CPU 上运行，不需要 GPU。Vicuna-7B 大约需要 30GB CPU 内存，Vicuna-13B 大约需要 60GB CPU 内存。
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device cpu
 ```
 
-Use Intel AI Accelerator AVX512_BF16/AMX to accelerate CPU inference.
+使用 Intel AI Accelerator AVX512_BF16/AMX 加速 CPU 推理。
 ```
 CPU_ISA=amx python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device cpu
 ```
 
-#### Metal Backend (Mac Computers with Apple Silicon or AMD GPUs)
-Use `--device mps` to enable GPU acceleration on Mac computers (requires torch >= 2.0).
-Use `--load-8bit` to turn on 8-bit compression.
+#### Metal 后端（搭载 Apple Silicon 或 AMD GPU 的 Mac 电脑）
+使用 `--device mps` 在 Mac 电脑上启用 GPU 加速（需要 torch >= 2.0）。
+使用 `--load-8bit` 开启 8 位压缩。
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device mps --load-8bit
 ```
-Vicuna-7B can run on a 32GB M1 Macbook with 1 - 2 words / second.
+Vicuna-7B 可在 32GB 内存的 M1 Macbook 上运行，速度约为每秒 1–2 个词。
 
-#### Intel XPU (Intel Data Center and Arc A-Series GPUs)
-Install the [Intel Extension for PyTorch](https://intel.github.io/intel-extension-for-pytorch/xpu/latest/tutorials/installation.html). Set the OneAPI environment variables:
+#### Intel XPU（Intel 数据中心 GPU 与 Arc A 系列 GPU）
+安装 [Intel Extension for PyTorch](https://intel.github.io/intel-extension-for-pytorch/xpu/latest/tutorials/installation.html). 并设置 OneAPI 环境变量：
 ```
 source /opt/intel/oneapi/setvars.sh
 ```
 
-Use `--device xpu` to enable XPU/GPU acceleration.
+使用 `--device xpu` 启用 XPU/GPU 加速。
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device xpu
 ```
-Vicuna-7B can run on an Intel Arc A770 16GB.
+Vicuna-7B 可在 Intel Arc A770 16GB 上运行。
 
 #### Ascend NPU
-Install the [Ascend PyTorch Adapter](https://github.com/Ascend/pytorch). Set the CANN environment variables:
+安装 [Ascend PyTorch Adapter](https://github.com/Ascend/pytorch). 并设置 CANN 环境变量：
 ```
 source /usr/local/Ascend/ascend-toolkit/set_env.sh
 ```
 
-Use `--device npu` to enable NPU acceleration.
+使用 `--device npu` 启用 NPU 加速。
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device npu
 ```
-Vicuna-7B/13B can run on an Ascend NPU.
+Vicuna-7B/13B 可在 Ascend NPU 上运行。
 
-#### Not Enough Memory
-If you do not have enough memory, you can enable 8-bit compression by adding `--load-8bit` to commands above.
-This can reduce memory usage by around half with slightly degraded model quality.
-It is compatible with the CPU, GPU, and Metal backend.
+#### 内存不足
+如果内存不足，你可以在上述命令中添加 `--load-8bit` 以启用 8 位压缩。
+这可将内存占用减少约一半，但模型质量会略有下降。
+它兼容 CPU、GPU 和 Metal 后端。
 
-Vicuna-13B with 8-bit compression can run on a single GPU with 16 GB of VRAM, like an Nvidia RTX 3090, RTX 4080, T4, V100 (16GB), or an AMD RX 6800 XT.
+启用 8 位压缩后，Vicuna-13B 可在单块 16 GB 显存的 GPU 上运行，例如 Nvidia RTX 3090、RTX 4080、T4、V100（16GB）或 AMD RX 6800 XT。
 
 ```
 python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --load-8bit
 ```
 
-In addition to that, you can add `--cpu-offloading` to commands above to offload weights that don't fit on your GPU onto the CPU memory.
-This requires 8-bit compression to be enabled and the bitsandbytes package to be installed, which is only available on linux operating systems.
+此外，你还可以在上述命令中添加 `--cpu-offloading`，将无法放入 GPU 显存的权重卸载到 CPU 内存。
+这需要启用 8 位压缩并安装 bitsandbytes 包，该包仅在 Linux 操作系统上可用。
 
-#### More Platforms and Quantization
-- For AMD GPU users, please install ROCm and [the ROCm version of PyTorch](https://pytorch.org/get-started/locally/) before you install FastChat. See also this [post](https://github.com/lm-sys/FastChat/issues/104#issuecomment-1613791563).
-- FastChat supports ExLlama V2. See [docs/exllama_v2.md](/docs/exllama_v2.md).
-- FastChat supports GPTQ 4bit inference with [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). See [docs/gptq.md](/docs/gptq.md).
-- FastChat supports AWQ 4bit inference with [mit-han-lab/llm-awq](https://github.com/mit-han-lab/llm-awq). See [docs/awq.md](/docs/awq.md).
-- [MLC LLM](https://mlc.ai/mlc-llm/), backed by [TVM Unity](https://github.com/apache/tvm/tree/unity) compiler, deploys Vicuna natively on phones, consumer-class GPUs and web browsers via Vulkan, Metal, CUDA and WebGPU.
+#### 更多平台与量化
+- 对于 AMD GPU 用户，请在安装 FastChat 之前安装 ROCm 和 [ROCm 版 PyTorch](https://pytorch.org/get-started/locally/)。另请参阅这篇[帖子](https://github.com/lm-sys/FastChat/issues/104#issuecomment-1613791563).
+- FastChat 支持 ExLlama V2。请参阅 [docs/exllama_v2.md](/docs/exllama_v2.md)。
+- FastChat 支持通过 [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). 进行 GPTQ 4 位推理。请参阅 [docs/gptq.md](/docs/gptq.md)。
+- FastChat 支持通过 [mit-han-lab/llm-awq](https://github.com/mit-han-lab/llm-awq). 进行 AWQ 4 位推理。请参阅 [docs/awq.md](/docs/awq.md)。
+- 由 [TVM Unity](https://github.com/apache/tvm/tree/unity) 编译器支持的 [MLC LLM](https://mlc.ai/mlc-llm/), 可通过 Vulkan、Metal、CUDA 和 WebGPU 在手机、消费级 GPU 和 Web 浏览器上原生部署 Vicuna。
 
-#### Use models from modelscope
-For Chinese users, you can use models from www.modelscope.cn via specify the following environment variables.
+#### 使用 ModelScope 模型
+中国用户可通过设置以下环境变量，使用来自 www.modelscope.cn 的模型。
 ```bash
 export FASTCHAT_USE_MODELSCOPE=True
 ```
 
-## Serving with Web GUI
+## 使用 Web GUI 提供服务
 
 <a href="https://lmarena.ai"><img src="assets/screenshot_gui.png" width="70%"></a>
 
-To serve using the web UI, you need three main components: web servers that interface with users, model workers that host one or more models, and a controller to coordinate the webserver and model workers. You can learn more about the architecture [here](docs/server_arch.md).
+要通过 Web UI 提供服务，你需要三个主要组件：与用户交互的 Web 服务器、托管一个或多个模型的模型 worker，以及用于协调 Web 服务器和模型 worker 的控制器。你可以在[此处](docs/server_arch.md)了解更多架构信息。
 
-Here are the commands to follow in your terminal:
+请在终端中执行以下命令：
 
-#### Launch the controller
+#### 启动控制器
 ```bash
 python3 -m fastchat.serve.controller
 ```
 
-This controller manages the distributed workers.
+该控制器负责管理分布式 worker。
 
-#### Launch the model worker(s)
+#### 启动模型 worker
 ```bash
 python3 -m fastchat.serve.model_worker --model-path lmsys/vicuna-7b-v1.5
 ```
-Wait until the process finishes loading the model and you see "Uvicorn running on ...". The model worker will register itself to the controller .
+等待进程完成模型加载，并看到 "Uvicorn running on ..."。模型 worker 会自动向控制器注册。
 
-To ensure that your model worker is connected to your controller properly, send a test message using the following command:
+为确保模型 worker 已正确连接到控制器，请使用以下命令发送测试消息：
 ```bash
 python3 -m fastchat.serve.test_message --model-name vicuna-7b-v1.5
 ```
-You will see a short output.
+你将看到简短输出。
 
-#### Launch the Gradio web server
+#### 启动 Gradio Web 服务器
 ```bash
 python3 -m fastchat.serve.gradio_web_server
 ```
 
-This is the user interface that users will interact with.
+这是用户将与之交互的界面。
 
-By following these steps, you will be able to serve your models using the web UI. You can open your browser and chat with a model now.
-If the models do not show up, try to reboot the gradio web server.
+按照这些步骤，你就可以通过 Web UI 提供模型服务。你现在可以打开浏览器与模型对话。
+如果模型未显示，请尝试重启 gradio web 服务器。
 
-## Launch Chatbot Arena (side-by-side battle UI)
+## 启动 Chatbot Arena（并排对战 UI）
 
-Currently, Chatbot Arena is powered by FastChat. Here is how you can launch an instance of Chatbot Arena locally.
+目前，Chatbot Arena 由 FastChat 驱动。以下介绍如何在本地启动 Chatbot Arena 实例。
 
-FastChat supports popular API-based models such as OpenAI, Anthropic, Gemini, Mistral and more. To add a custom API, please refer to the model support [doc](./docs/model_support.md). Below we take OpenAI models as an example.
+FastChat 支持 OpenAI、Anthropic、Gemini、Mistral 等主流基于 API 的模型。要添加自定义 API，请参阅模型支持[文档](./docs/model_support.md)。以下以 OpenAI 模型为例。
 
-Create a JSON configuration file `api_endpoint.json` with the api endpoints of the models you want to serve, for example:
+创建 JSON 配置文件 `api_endpoint.json`，填写你想提供的模型的 API 端点，例如：
 ```
 {
     "gpt-4o-2024-05-13": {
@@ -255,73 +261,73 @@ Create a JSON configuration file `api_endpoint.json` with the api endpoints of t
     }
 }
 ```
-For Anthropic models, specify `"api_type": "anthropic_message"` with your Anthropic key. Similarly, for gemini model, specify `"api_type": "gemini"`. More details can be found in [api_provider.py](https://github.com/lm-sys/FastChat/blob/main/fastchat/serve/api_provider.py).
+对于 Anthropic 模型，请使用你的 Anthropic 密钥指定 `"api_type": "anthropic_message"`。同样地，对于 Gemini 模型，请指定 `"api_type": "gemini"`。更多细节请参阅 [api_provider.py](https://github.com/lm-sys/FastChat/blob/main/fastchat/serve/api_provider.py).
 
-To serve your own model using local gpus, follow the instructions in [Serving with Web GUI](#serving-with-web-gui).
+要使用本地 GPU 提供你自己的模型服务，请遵循[使用 Web GUI 提供服务](#serving-with-web-gui)中的说明。
 
-Now you're ready to launch the server:
+现在你可以启动服务器了：
 ```
 python3 -m fastchat.serve.gradio_web_server_multi --register-api-endpoint-file api_endpoint.json
 ```
 
-#### (Optional): Advanced Features, Scalability, Third Party UI
-- You can register multiple model workers to a single controller, which can be used for serving a single model with higher throughput or serving multiple models at the same time. When doing so, please allocate different GPUs and ports for different model workers.
+#### （可选）高级功能、可扩展性与第三方 UI
+- 你可以将多个模型 worker 注册到单个控制器，用于以更高吞吐量提供单个模型服务，或同时提供多个模型。这样做时，请为不同的模型 worker 分配不同的 GPU 和端口。
 ```
 # worker 0
 CUDA_VISIBLE_DEVICES=0 python3 -m fastchat.serve.model_worker --model-path lmsys/vicuna-7b-v1.5 --controller http://localhost:21001 --port 31000 --worker http://localhost:31000
 # worker 1
 CUDA_VISIBLE_DEVICES=1 python3 -m fastchat.serve.model_worker --model-path lmsys/fastchat-t5-3b-v1.0 --controller http://localhost:21001 --port 31001 --worker http://localhost:31001
 ```
-- You can also launch a multi-tab gradio server, which includes the Chatbot Arena tabs.
+- 你也可以启动包含 Chatbot Arena 标签页的多标签 Gradio 服务器。
 ```bash
 python3 -m fastchat.serve.gradio_web_server_multi
 ```
-- The default model worker based on huggingface/transformers has great compatibility but can be slow. If you want high-throughput batched serving, you can try [vLLM integration](docs/vllm_integration.md).
-- If you want to host it on your own UI or third party UI, see [Third Party UI](docs/third_party_ui.md).
+- 基于 huggingface/transformers 的默认模型 worker 兼容性很好，但可能较慢。如果你需要高吞吐量的批处理服务，可以尝试 [vLLM integration](docs/vllm_integration.md)。
+- 如果你想在自己的 UI 或第三方 UI 上托管，请参阅 [Third Party UI](docs/third_party_ui.md)。
 
 ## API
-### OpenAI-Compatible RESTful APIs & SDK
-FastChat provides OpenAI-compatible APIs for its supported models, so you can use FastChat as a local drop-in replacement for OpenAI APIs.
-The FastChat server is compatible with both [openai-python](https://github.com/openai/openai-python) library and cURL commands.
-The REST API is capable of being executed from Google Colab free tier, as demonstrated in the [FastChat_API_GoogleColab.ipynb](https://github.com/lm-sys/FastChat/blob/main/playground/FastChat_API_GoogleColab.ipynb) notebook, available in our repository.
-See [docs/openai_api.md](docs/openai_api.md).
+### 兼容 OpenAI 的 RESTful API 与 SDK
+FastChat 为其支持的模型提供兼容 OpenAI 的 API，因此你可以将 FastChat 用作 OpenAI API 的本地替代方案。
+FastChat 服务器同时兼容 [openai-python](https://github.com/openai/openai-python) 库和 cURL 命令。
+REST API 可在 Google Colab 免费版中运行，如仓库中的 [FastChat_API_GoogleColab.ipynb](https://github.com/lm-sys/FastChat/blob/main/playground/FastChat_API_GoogleColab.ipynb) 笔记本所示。
+请参阅 [docs/openai_api.md](docs/openai_api.md)。
 
-### Hugging Face Generation APIs
-See [fastchat/serve/huggingface_api.py](fastchat/serve/huggingface_api.py).
+### Hugging Face 生成 API
+请参阅 [fastchat/serve/huggingface_api.py](fastchat/serve/huggingface_api.py)。
 
-### LangChain Integration
-See [docs/langchain_integration](docs/langchain_integration.md).
+### LangChain 集成
+请参阅 [docs/langchain_integration](docs/langchain_integration.md)。
 
-## Evaluation
-We use MT-bench, a set of challenging multi-turn open-ended questions to evaluate models. 
-To automate the evaluation process, we prompt strong LLMs like GPT-4 to act as judges and assess the quality of the models' responses.
-See instructions for running MT-bench at [fastchat/llm_judge](fastchat/llm_judge).
+## 评估
+我们使用 MT-bench，这是一组具有挑战性的多轮开放式问题，用于评估模型。
+为自动化评估流程，我们提示 GPT-4 等强大的 LLM 担任评委，评估模型回答的质量。
+有关运行 MT-bench 的说明，请参阅 [fastchat/llm_judge](fastchat/llm_judge)。
 
-MT-bench is the new recommended way to benchmark your models. If you are still looking for the old 80 questions used in the vicuna blog post, please go to [vicuna-blog-eval](https://github.com/lm-sys/vicuna-blog-eval).
+MT-bench 是评测模型的新推荐方式。如果你仍在寻找 vicuna 博客文章中使用的旧版 80 个问题，请前往 [vicuna-blog-eval](https://github.com/lm-sys/vicuna-blog-eval).
 
-## Fine-tuning
-### Data
+## 微调
+### 数据
 
-Vicuna is created by fine-tuning a Llama base model using approximately 125K user-shared conversations gathered from ShareGPT.com with public APIs. To ensure data quality, we convert the HTML back to markdown and filter out some inappropriate or low-quality samples. Additionally, we divide lengthy conversations into smaller segments that fit the model's maximum context length. For detailed instructions to clean the ShareGPT data, check out [here](docs/commands/data_cleaning.md).
+Vicuna 通过对 Llama 基础模型进行微调创建，使用了从 ShareGPT.com 通过公开 API 收集的约 125K 条用户共享对话。为确保数据质量，我们将 HTML 转换回 markdown，并过滤掉部分不当或低质量样本。此外，我们将冗长对话拆分为符合模型最大上下文长度的小段。有关清洗 ShareGPT 数据的详细说明，请查看[此处](docs/commands/data_cleaning.md)。
 
-We will not release the ShareGPT dataset. If you would like to try the fine-tuning code, you can run it with some dummy conversations in [dummy_conversation.json](data/dummy_conversation.json). You can follow the same format and plug in your own data.
+我们不会发布 ShareGPT 数据集。如果你想试用微调代码，可以使用 [dummy_conversation.json](data/dummy_conversation.json) 中的一些虚拟对话来运行。你可以遵循相同格式并填入自己的数据。
 
-### Code and Hyperparameters
-Our code is based on [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) with additional support for multi-turn conversations.
-We use similar hyperparameters as the Stanford Alpaca.
+### 代码与超参数
+我们的代码基于 [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca)，并额外支持多轮对话（multi-turn conversations）。
+我们使用的超参数与 Stanford Alpaca 类似。
 
-| Hyperparameter | Global Batch Size | Learning rate | Epochs | Max length | Weight decay |
+| 超参数 | 全局批次大小 | 学习率 | 训练轮数 | 最大长度 | 权重衰减 |
 | --- | ---: | ---: | ---: | ---: | ---: |
 | Vicuna-13B | 128 | 2e-5 | 3 | 2048 | 0 |
 
-### Fine-tuning Vicuna-7B with Local GPUs
+### 使用本地 GPU 微调 Vicuna-7B
 
-- Install dependency
+- 安装依赖
 ```bash
 pip3 install -e ".[train]"
 ```
 
-- You can use the following command to train Vicuna-7B with 4 x A100 (40GB). Update `--model_name_or_path` with the actual path to Llama weights and `--data_path` with the actual path to data.
+- 你可以使用以下命令，在 4 x A100 (40GB) 上训练 Vicuna-7B。请将 `--model_name_or_path` 更新为 Llama 权重的实际路径，并将 `--data_path` 更新为数据的实际路径。
 ```bash
 torchrun --nproc_per_node=4 --master_port=20001 fastchat/train/train_mem.py \
     --model_name_or_path meta-llama/Llama-2-7b-hf \
@@ -349,22 +355,22 @@ torchrun --nproc_per_node=4 --master_port=20001 fastchat/train/train_mem.py \
     --lazy_preprocess True
 ```
 
-Tips:
-- If you are using V100 which is not supported by FlashAttention, you can use the [memory-efficient attention](https://arxiv.org/abs/2112.05682) implemented in [xFormers](https://github.com/facebookresearch/xformers). Install xformers and replace `fastchat/train/train_mem.py` above with [fastchat/train/train_xformers.py](fastchat/train/train_xformers.py).
-- If you meet out-of-memory due to "FSDP Warning: When using FSDP, it is efficient and recommended... ", see solutions [here](https://github.com/huggingface/transformers/issues/24724#issuecomment-1645189539).
-- If you meet out-of-memory during model saving, see solutions [here](https://github.com/pytorch/pytorch/issues/98823).
-- To turn on logging to popular experiment tracking tools such as Tensorboard, MLFlow or Weights & Biases, use the `report_to` argument, e.g. pass `--report_to wandb` to turn on logging to Weights & Biases.
+提示：
+- 如果你使用的是不受 FlashAttention 支持的 V100，可以使用 [memory-efficient attention](https://arxiv.org/abs/2112.05682) implemented in [xFormers](https://github.com/facebookresearch/xformers). 安装 xformers，并将上文中的 `fastchat/train/train_mem.py` 替换为 [fastchat/train/train_xformers.py](fastchat/train/train_xformers.py)。
+- 如果因 "FSDP Warning: When using FSDP, it is efficient and recommended... " 而出现显存不足，请参阅[此处](https://github.com/huggingface/transformers/issues/24724#issuecomment-1645189539). 的解决方案。
+- 如果在模型保存过程中遇到显存不足，请参阅[此处](https://github.com/pytorch/pytorch/issues/98823). 的解决方案。
+- 若要开启 Tensorboard、MLFlow 或 Weights & Biases 等常用实验跟踪工具的日志记录，请使用 `report_to` 参数，例如传入 `--report_to wandb` 以开启 Weights & Biases 日志记录。
 
-### Other models, platforms and LoRA support
-More instructions to train other models (e.g., FastChat-T5) and use LoRA are in [docs/training.md](docs/training.md).
+### 其他模型、平台与 LoRA 支持
+关于训练其他模型（例如 FastChat-T5）和使用 LoRA 的更多说明，请参阅 [docs/training.md](docs/training.md)。
 
-### Fine-tuning on Any Cloud with SkyPilot
-[SkyPilot](https://github.com/skypilot-org/skypilot) is a framework built by UC Berkeley for easily and cost effectively running ML workloads on any cloud (AWS, GCP, Azure, Lambda, etc.).
-Find SkyPilot documentation [here](https://github.com/skypilot-org/skypilot/tree/master/llm/vicuna) on using managed spot instances to train Vicuna and save on your cloud costs.
+### 使用 SkyPilot 在任意云上微调
+[SkyPilot](https://github.com/skypilot-org/skypilot) 是由 UC Berkeley 构建的框架，用于在任意云（AWS、GCP、Azure、Lambda 等）上轻松且经济高效地运行机器学习工作负载。
+请在[此处](https://github.com/skypilot-org/skypilot/tree/master/llm/vicuna) 查阅 SkyPilot 文档，了解如何使用 managed spot 实例（managed spot instances）训练 Vicuna 并节省云成本。
 
-## Citation
-The code (training, serving, and evaluation) in this repository is mostly developed for or derived from the paper below.
-Please cite it if you find the repository helpful.
+## 引用
+本仓库中的代码（训练、serving 和评估）大多是为下文论文开发或衍生而来。
+如果你觉得本仓库有帮助，请引用该论文。
 
 ```
 @misc{zheng2023judging,
@@ -377,4 +383,4 @@ Please cite it if you find the repository helpful.
 }
 ```
 
-We are also planning to add more of our research to this repository.
+我们也计划将更多研究成果添加到本仓库。