AutoDL 远程连接 VS Code Remote-SSH 完整指南 AutoDL 远程连接 VS Code Remote-SSH 完整指南前置准备1. 安装 VS Code 插件在 VS Code 中安装 Remote - SSH 插件：打开 VS Code按 Ctrl+Shift+X 打开扩展商店搜索 Remote - SSH点击安装（作者：Microsoft）2. 获取 AutoDL SSH 连接信息登录 AutoDL 控制台找到你的实例，点击进入详情页在「SSH 登录指令」处获取连接信息，格式如下：ssh -p 端口号 root@区域.autodl.pro例如：ssh -p 12345 root@region-1.autodl.pro记录以下信息：主机地址：如 region-1.autodl.pro端口号：如 12345用户名：通常为 root密码：在实例页面可查看或重置方法一：直接连接（推荐新手）步骤 1：打开 Remote-SSH按 Ctrl+Shift+P 打开命令面板输入 Remote-SSH: Connect to Host...选择该选项步骤 2：输入连接信息在弹出的输入框中输入：ssh -p 端口号 root@主机地址例如：ssh -p 12345 root@region-1.autodl.pro步骤 3：选择配置文件首次连接会提示选择 SSH 配置文件保存位置，选择：Windows: C:\Users\你的用户名\.ssh\configLinux/Mac: ~/.ssh/config步骤 4：选择操作系统选择远程服务器的操作系统类型：Linux步骤 5：输入密码在弹出的密码框中输入 AutoDL 实例的密码，等待连接完成。方法二：配置 SSH Config（推荐长期使用）步骤 1：打开 SSH 配置文件按 Ctrl+Shift+P 打开命令面板输入 Remote-SSH: Open SSH Configuration File...选择配置文件路径步骤 2：添加配置在配置文件中添加以下内容：Host autodl HostName region-1.autodl.pro Port 12345 User root将 HostName 和 Port 替换为你的实际信息步骤 3：保存并连接保存配置文件按 Ctrl+Shift+P，输入 Remote-SSH: Connect to Host...选择刚才配置的 autodl输入密码即可连接方法三：配置 SSH 密钥免密登录（推荐）步骤 1：生成 SSH 密钥（如已有可跳过）在本地终端执行：ssh-keygen -t rsa -b 4096 -C "your_email@example.com"一路回车使用默认配置，密钥会生成在：Windows: C:\Users\你的用户名\.ssh\id_rsaLinux/Mac: ~/.ssh/id_rsa步骤 2：上传公钥到 AutoDL方法 A：使用 ssh-copy-id（Linux/Mac）ssh-copy-id -p 端口号 root@主机地址方法 B：手动上传（Windows/通用）查看本地公钥内容：# Windows PowerShell cat C:\Users\你的用户名\.ssh\id_rsa.pub # Linux/Mac cat ~/.ssh/id_rsa.pub复制公钥内容SSH 登录到 AutoDL 服务器：ssh -p 端口号 root@主机地址在服务器上执行：mkdir -p ~/.ssh echo "你复制的公钥内容" >> ~/.ssh/authorized_keys chmod 700 ~/.ssh chmod 600 ~/.ssh/authorized_keys步骤 3：更新 SSH ConfigHost autodl HostName region-1.autodl.pro Port 12345 User root IdentityFile ~/.ssh/id_rsa现在连接时无需输入密码。常见问题排查1. 连接超时检查 AutoDL 实例是否已开机检查网络是否正常确认端口号是否正确2. 密码错误在 AutoDL 控制台重置密码注意密码区分大小写3. Host key verification failed删除旧的主机密钥记录：# Windows ssh-keygen -R "[主机地址]:端口号" # 例如 ssh-keygen -R "[region-1.autodl.pro]:12345"4. VS Code 一直提示输入密码检查密钥配置是否正确确认服务器上 ~/.ssh/authorized_keys 权限为 600确认 ~/.ssh 目录权限为 7005. 连接后无法打开文件夹等待 VS Code Server 安装完成，首次连接可能需要几分钟。实用技巧1. 端口转发在 SSH Config 中添加端口转发，方便访问远程服务：Host autodl HostName region-1.autodl.pro Port 12345 User root LocalForward 8888 localhost:8888 LocalForward 6006 localhost:6006这样可以通过本地 localhost:8888 访问远程的 Jupyter Notebook。2. 保持连接防止连接断开，添加心跳配置：Host autodl HostName region-1.autodl.pro Port 12345 User root ServerAliveInterval 60 ServerAliveCountMax 33. 多实例管理为不同实例配置不同名称：Host autodl-train HostName region-1.autodl.pro Port 12345 User root Host autodl-dev HostName region-2.autodl.pro Port 54321 User root快速检查清单[ ] VS Code 已安装 Remote-SSH 插件[ ] AutoDL 实例已开机[ ] 已获取正确的主机地址、端口、密码[ ] SSH Config 配置正确[ ] （可选）SSH 密钥已配置连接成功后，你可以像操作本地文件一样编辑远程服务器上的代码！AutoDL 目录选择指南AutoDL 实例有两个主要存储位置：目录名称速度说明/root系统盘一般实例关机数据不会丢失，会随保存镜像一起保存/root/autodl-tmp数据盘快实例关机数据不会丢失，不会随保存镜像一起保存推荐存放方案存放内容推荐目录原因代码、配置文件、环境/root (系统盘)会随镜像保存，换机器不用重新配置数据集、模型权重、checkpoint/root/autodl-tmp (数据盘)IO 速度快，训练/推理时读写效率高典型项目结构/root/ ├── projects/ # 代码项目（系统盘，保存镜像） │ └── your-project/ │ ├── src/ │ └── configs/ /root/autodl-tmp/ ├── datasets/ # 数据集（数据盘，IO快） ├── models/ # 预训练模型权重 └── outputs/ # 训练输出、checkpoint简单原则需要保存到镜像的 → 系统盘 /root大文件、频繁读写的 → 数据盘 /root/autodl-tmp💡 提示：如果使用 vLLM 等推理框架，建议把模型权重放 /root/autodl-tmp，代码放 /root。

Excel模板批量文本替换工具 Excel模板批量文本替换工具功能说明批量替换 .xlsm Excel模板文件中的指定文本，包括：自定义功能区/菜单栏名称工作表中的文本内容实现原理.xlsm 文件本质是 ZIP 压缩包，内含多个 XML 文件：customUI/customUI.xml - 自定义功能区配置xl/sharedStrings.xml - 工作表共享文本脚本通过解压→替换XML内容→重新打包的方式实现批量修改。使用方法编辑 replace_text.py，修改配置区的变量：old_text = '原文本' # 要替换的文本 new_text = '新文本' # 替换后的文本运行脚本：python replace_text.py# -*- coding: utf-8 -*- """ Excel模板批量文本替换工具 用法：修改下方的 old_text 和 new_text，然后运行脚本 """ import zipfile import os import shutil import sys sys.stdout.reconfigure(encoding='utf-8') # ========== 配置区 ========== files = [ '1001银行模板（划线注销11项）.xlsm', '1001银行模板（填无注销11项）.xlsm', '2001往来模板.xlsm', '3001其他模板.xlsm' ] old_text = '中兴财光华' # 要替换的原文本 new_text = '审计五组' # 替换后的新文本 # ============================ for file in files: if not os.path.exists(file): print(f'文件不存在: {file}') continue print(f'处理文件: {file}') temp_dir = f'temp_{file}' # 解压xlsm文件（本质是zip包） with zipfile.ZipFile(file, 'r') as zip_ref: zip_ref.extractall(temp_dir) # 遍历所有xml文件进行文本替换 replaced_count = 0 for root, dirs, filenames in os.walk(temp_dir): for filename in filenames: if filename.endswith(('.xml', '.rels')): filepath = os.path.join(root, filename) try: with open(filepath, 'r', encoding='utf-8') as f: content = f.read() if old_text in content: new_content = content.replace(old_text, new_text) with open(filepath, 'w', encoding='utf-8') as f: f.write(new_content) replaced_count += 1 print(f' 替换: {os.path.relpath(filepath, temp_dir)}') except: pass # 重新打包为xlsm backup_file = file + '.bak' shutil.move(file, backup_file) with zipfile.ZipFile(file, 'w', zipfile.ZIP_DEFLATED) as zipf: for root, dirs, filenames in os.walk(temp_dir): for filename in filenames: filepath = os.path.join(root, filename) arcname = os.path.relpath(filepath, temp_dir) zipf.write(filepath, arcname) shutil.rmtree(temp_dir) os.remove(backup_file) print(f' 完成，替换了 {replaced_count} 处\n') print('全部处理完成！')依赖Python 3.x无需额外安装库（使用标准库 zipfile）

WSL2 备份与导入指南 WSL2 备份与导入指南查看已安装的发行版wsl --list --verbose备份 WSL2 发行版将指定发行版导出为 .tar 文件：wsl --export <发行版名称> <导出路径>示例：wsl --export Ubuntu D:\backup\ubuntu-backup.tar导入 WSL2 发行版从备份文件导入：wsl --import <新发行版名称> <安装路径> <tar文件路径>示例：wsl --import Ubuntu-New D:\wsl\Ubuntu-New D:\backup\ubuntu-backup.tar设置默认用户（导入后）导入的发行版默认以 root 登录，需要手动设置默认用户：<发行版名称> config --default-user <用户名>或在发行版内创建 /etc/wsl.conf：[user] default=你的用户名常用命令操作命令关闭所有发行版wsl --shutdown关闭指定发行版wsl --terminate <名称>删除发行版wsl --unregister <名称>设置默认发行版wsl --set-default <名称>注意事项备份前建议先关闭 WSL：wsl --shutdown导出文件可能较大，确保目标磁盘有足够空间导入时安装路径会创建一个 ext4.vhdx 虚拟磁盘文件

如何使用 LoRA 微调 DeepSeek R1 How to Fine-Tune DeepSeek R1 Using LoRA如何使用 LoRA 微调 DeepSeek R1This guide walks through fine-tuning DeepSeek R1 using LoRA, a Parameter-Efficient Fine-Tuning (PEFT) method that updates only a small portion of model parameters to improve function calling. It covers dataset preparation, model configuration, and training using Hugging Face tools, making fine-tuning efficient and resource-friendly. The result is a model that performs function calls accurately following the dataset design. 本指南介绍如何使用 LoRA 对 DeepSeek R1 进行微调，LoRA 是一种参数高效微调 （PEFT） 方法，仅更新一小部分模型参数以改进函数调用。它涵盖了数据集准备、模型配置和使用 Hugging Face 工具进行训练，使微调变得高效且资源友好。结果是一个按照数据集设计准确执行函数调用的模型。DeepSeek is quickly gaining attention for its impressive performance and cost efficiency, so I decided to write about fine-tuning it. In this post, we’ll work with a smaller DeepSeek model and demonstrate how to apply supervised fine-tuning (SFT) using a Parameter-Efficient Fine-Tuning (PEFT) approach via Low-Rank Adaptation (LoRA). We’ll be fine-tuning the model on a function calling dataset, showing how you can quickly and efficiently adapt large language models (LLMs) to improve their function calling capabilities. With this pipeline, you can easily swap out the dataset or model to fine-tune models on specific domains. DeepSeek 因其令人印象深刻的性能和成本效益而迅速受到关注，因此我决定写一篇关于微调它的文章。在本文中，我们将使用一个较小的 DeepSeek 模型，并演示如何通过低秩自适应 （LoRA） 使用参数高效微调 （PEFT） 方法应用监督微调 （SFT）。我们将在函数调用数据集上微调模型，展示如何快速有效地调整大型语言模型 （LLM） 以改进其函数调用功能。使用此管道，您可以轻松换出数据集或模型，以微调特定域上的模型。What is Parameter-Efficient Fine-Tuning (PEFT) and LoRA?什么是参数高效微调 （PEFT） 和 LoRA？Full fine-tuning of LLMs can be resource intensive. PEFT techniques, such as LoRA, offer an elegant solution by adjusting only a small subset of parameters. LoRA works by freezing the model’s weights and injecting trainable, low-rank matrices into key layers. 对 LLM 进行全面微调可能会占用大量资源。PEFT 技术（如 LoRA）通过仅调整一小部分参数来提供优雅的解决方案。LoRA 的工作原理是冻结模型的权重，并将可训练的低秩矩阵注入关键层。Consider a weight matrix ( W ) in a Transformer layer. Instead of updating ( W ) directly, we update it as: 考虑 Transformer 层中的权重矩阵 （ W ）。我们不是直接更新 （ W ），而是将其更新为：Here, ( A ) and ( B ) are low-rank matrices which are the trainable weights being injected. In practice, you define a rank r so that ( A ) has shape (N, r) and ( B ) has shape (r, M), the multiplication results in a matrix with the same shape a (W) (N, M). Experiments have shown that values such as r=8, r=16, or r=32 often achieve excellent performance comparable to a full fine-tuning, while only training ~1% of the total parameters. 这里，（ A ） 和 （ B ） 是低秩矩阵，它们是要注入的可训练权重。在实践中，您定义一个秩，即 （ A ） 具有形状 （N， r） 和 （ B ） 具有形状 （r， M），乘法得到具有相同形状 a （W）（N， M） 的矩阵。实验表明，诸如 r=8、r=16、orr=32 等值通常可以获得与完全微调相当的出色性能，而仅训练总参数的 ~1%。Hands-On: Fine-Tuning DeepSeek with LoRA 动手实践：使用 LoRA 微调 DeepSeekIn this section, we’ll walk through the process of fine-tuning a DeepSeek model on a function calling dataset using LoRA. 在本节中，我们将演练使用 LoRA 在函数调用数据集上微调 DeepSeek 模型的过程。1. Setting Up Your Environment 1. 设置您的环境I’ve been using the official Hugging Face Docker image (huggingface/transformers-pytorch-gpu) with Jupyter Notebook locally. You’ll need to install the necessary libraries with: 我一直在本地将官方的 Hugging Face Docker 镜像 （）huggingface/transformers-pytorch-gpu 与 Jupyter Notebook 一起使用。您需要使用以下命令安装必要的库：pip install transformers datasets accelerate evaluate bitsandbytes peft trl wandb optimum**2. Preparing the Function Calling Dataset 2. 准备函数调用 dataset**We will use the glaiveai/glaive-function-calling-v2 dataset. Since the raw dataset contains chat interactions not leading to function calling, we first filter the data and later we’ll balance the samples. 我们将使用数据集glaiveai/glaive-function-calling-v2。由于原始数据集包含不会导致函数调用的聊天交互，因此我们首先筛选数据，然后平衡样本。**2.1. Load and Filter the Dataset 2.1. 加载和过滤数据集**import multiprocessing from datasets import load_dataset max_seq_length = 512 dataset_size = 'small' train_eval_split = 0.1 train_test_split = 0.01 seed = 42 dataset_path = 'glaiveai/glaive-function-calling-v2' fn_calling_dataset = load_dataset( dataset_path, split='train', num_proc=multiprocessing.cpu_count() ) # Select samples that contain either a function call or a message indicating inability to call a function. dataset_reduced = fn_calling_dataset.filter( lambda x: "I'm sorry" in x["chat"] or "functioncall" in x["chat"] ).shuffle(seed=seed) dataset_reduced>>> Dataset({ >>> features: ['system', 'chat'], >>> num_rows: 78392 >>> })We now “balance” the dataset to include both cases — when a function call is found and not — and then split it into training and testing sets. This will help us balance the dataset between the scenarios we want the model to improve: 现在，我们“平衡”数据集以包括这两种情况（当找到函数调用时，未找到函数调用时），然后将其拆分为训练集和测试集。这将帮助我们在希望模型改进的场景之间平衡数据集：Knowing when it can’t do a function call; 知道何时无法执行函数调用;How to perform a function call when it can. 如何在可以执行函数调用时执行函数调用。from datasets import concatenate_datasets def get_dataset_size(dataset_size): if dataset_size == "small": missed_amount = 200 found_amount = 600 elif dataset_size == "medium": missed_amount = 350 found_amount = 750 elif dataset_size == "large": missed_amount = 375 found_amount = 825 return missed_amount, found_amount # Reserve a portion of the data for testing. test_amount = max(int(train_test_split * dataset_reduced.num_rows), 25) dataset_reduced_train = dataset_reduced.select(range(dataset_reduced.num_rows - test_amount)) # Determine the number of samples for each scenario. missed_amount, found_amount = get_dataset_size(dataset_size) dataset_train_missed = dataset_reduced_train.filter( lambda x: "I'm sorry" in x["chat"] and not ("functioncall" in x["chat"]) ).select(range(missed_amount)) dataset_train_found = dataset_reduced_train.filter( lambda x: not ("I'm sorry" in x["chat"]) and "functioncall" in x["chat"] ).select(range(found_amount)) # Concatenate the two balanced datasets. dataset_final_train = concatenate_datasets([dataset_train_missed, dataset_train_found]) # The reduced dataset now contains a small balanced mix of samples dataset_final_train>>> Filter: 100%|██████████| 77609/77609 [00:00<00:00, 95166.57 examples/s] >>> Filter: 100%|██████████| 77609/77609 [00:00<00:00, 105422.00 examples/s] >>> Dataset({ >>> features: ['system', 'chat'], >>> num_rows: 800 >>> })2.2. Converting the Dataset Format 2.2. 转换数据集格式We’ll be using the TRL library to handle a couple of steps, such as input tokenization, so we need to transform the dataset samples into a format the TRL trainer class expects. 我们将使用 来处理TRL library几个步骤，例如输入标记化，因此我们需要将数据集样本转换为 TRL trainer 类所需的格式。The dataset contains system and chat entries. For example, a sample from the dataset looks like: 数据集包含 systemandchatentries。例如，数据集中的样本如下所示：>>> SYSTEM: You are a helpful assistant with access to the following functions. Use them if required - { "name": "convert_currency", "description": "Convert the amount from one currency to another", ... } ----- USER: Hi, I need to convert 500 US dollars to Euros. Can you help me with that? ASSISTANT: {"name": "convert_currency", "arguments": '{"amount": 500, "from_currency": "USD", "to_currency": "EUR"}'} FUNCTION RESPONSE: {"converted_amount": 425.50, ...} ASSISTANT: Sure, 500 US dollars is approximately 425.50 Euros.We convert the original format (with system and chat fields) into a list messages: 我们将原始格式 （withsystemandchatfields） 转换为 listmessages：import re from typing import List, Any, Dict, Tuple def chat_str_to_messages(chat_str: str) -> Dict[str, Tuple[str, str]]: try: # Limit the chat to the point before the first function response. chat_until_function_call = chat_str[: next(re.finditer(r"FUNCTION\sRESPONSE\:", chat_str)).start()].strip() except StopIteration: chat_until_function_call = chat_str.strip() # use regex to find all user and assistant messages. matches = re.findall( r"(USER|ASSISTANT):\s(.*?)(?=\n\n|$)", chat_until_function_call, re.DOTALL ) chat_interaction = [ (matchh[0], matchh[1].replace(" <|endoftext|>", "").strip()) for matchh in matches ] return chat_interaction def transform_dataset_format(data_from_sample: List[Any]) -> Dict[str, List[Dict[str, str]]]: texts = [] system_prompts = list(map(lambda x: re.split(r"SYSTEM\:\s", x)[1].strip(), data_from_sample["system"])) chats = list(map(chat_str_to_messages, data_from_sample["chat"])) for systemprompt, chatnow in zip(system_prompts, chats): messages = [{"role": "system", "content": systemprompt}] + [ {"role": role.lower(), "content": msg} for role, msg in chatnow ] texts.append(messages) return {"messages": texts} dataset_train = dataset_final_train.map( transform_dataset_format, batched=True, remove_columns=dataset_final_train.column_names, ) dataset_train>>> Map: 100%|██████████| 800/800 [00:00<00:00, 24218.98 examples/s] >>> Dataset({ >>> features: ['messages'], >>> num_rows: 800 >>> })Now, we inspect a sample to ensure the format is correct: 现在，我们检查样本以确保格式正确：>>> {'messages': [{'content': 'You are a helpful assistant with access to the following functions. Use them if required -\n{\n "name": "calculate_distance",\n "description": "Calculate the distance between two locations",\n "parameters": {\n "type": "object",\n "properties": {\n "start_location": {\n "type": "string",\n "description": "The starting location"\n },\n "end_location": {\n "type": "string",\n "description": "The ending location"\n }\n },\n "required": [\n "start_location",\n "end_location"\n ]\n }\n}', 'role': 'system'}, {'content': 'Can you please book a flight for me from New York to Los Angeles?', 'role': 'user'}, {'content': "I'm sorry, but as an AI, I don't have the capability to book flights. My current function allows me to calculate the distance between two locations. If you need to know the distance between New York and Los Angeles, I can certainly help with that.", 'role': 'assistant'}]}Finally, we split the dataset between training and validation: 最后，我们将数据集分为训练和验证：dataset_train_eval= dataset_train.train_test_split(test_size=train_eval_split) dataset_train_eval>>> DatasetDict({ >>> train: Dataset({ >>> features: ['messages'], >>> num_rows: 720 >>> }) >>> test: Dataset({ >>> features: ['messages'], >>> num_rows: 80 >>> }) >>> })**3. Loading the Pre-Trained DeepSeek Model and Configuring LoRA 3. 加载预先训练的 DeepSeek 模型并配置 LoRA**Now that the dataset is ready, we load the DeepSeek model, set up the LoRA configuration, and let the GPU burn! Let’s check the amount of trainable parameters. 现在数据集已经准备好了，我们加载 DeepSeek 模型，设置 LoRA 配置，然后让 GPU 刻录！我们来检查一下可训练参数的数量。from peft import LoraConfig, get_peft_model from transformers import AutoModelForCausalLM, AutoTokenizer model_name = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B' model_size = '1.5B' lora_r = 4 # this will vary the amount of trainable parameters - it's correlated with the performance gains. lora_alpha = 16 # according to the paper, this is the best value for most tasks. target_modules = ["q_proj", "k_proj", "v_proj", "o_proj"] # Modules to apply LoRA - it's correlated with the amount of trainable parameters. # Load model and tokenizer. model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto") tokenizer = AutoTokenizer.from_pretrained( model_name, padding=True, truncation=True, max_length=max_seq_length ) # Set up the LoRA configuration. lora_config = LoraConfig( r=lora_r, lora_alpha=lora_alpha, lora_dropout=0.1, target_modules=target_modules, init_lora_weights="gaussian", task_type="CAUSAL_LM", inference_mode=False ) # Wrap the model with LoRA and check the amount of trainable parameters peft_model = get_peft_model(model, lora_config) peft_model.print_trainable_parameters()>>> trainable params: 1,189,888 || all params: 1,778,277,888 || trainable%: 0.06694. Configuring and Running the Fine-Tuning Process4. 配置并运行微调过程**4.1. Customizing Trainer Class 4.1. 自定义 Trainer 类**Using the TRL library, we set up a simple supervised fine-tuning trainer. I extended the original SFTTrainer class to ensure that the tokenizer properly handles padding to the specified max_seq_length. Not sure if there’s an issue when tokenizing with padding, but the SFTTrainer class seems to ignore the configuration to add max_seq_length padding to input. 使用 TRL 库，我们设置了一个简单的监督式微调训练器。我扩展了 originalSFTTrainer类，以确保分词器正确处理specifiedmax\_seq\_length的填充。不确定使用填充进行标记化时是否存在问题，但是SFTTrainer类似乎忽略了addmax\_seq\_lengthpadding输入的配置。import warnings from datasets import Dataset from typing import Optional, Callable from trl import SFTTrainer class CustomSFTTrainer(SFTTrainer): def _prepare_non_packed_dataloader( self, processing_class, dataset, dataset_text_field: str, max_seq_length, formatting_func: Optional[Callable] = None, add_special_tokens=True, remove_unused_columns=True, ): # Inspired from: https://huggingface.co/learn/nlp-course/chapter7/6?fw=pt def tokenize(element): outputs = processing_class( element[dataset_text_field] if formatting_func is None else formatting_func(element), add_special_tokens=add_special_tokens, truncation=True, padding="max_length", max_length=max_seq_length, return_overflowing_tokens=False, return_length=False, ) if formatting_func is not None and not isinstance(formatting_func(element), list): raise ValueError( "The `formatting_func` should return a list of processed strings since it can lead to silent bugs." ) return {"input_ids": outputs["input_ids"], "attention_mask": outputs["attention_mask"]} signature_columns = ["input_ids", "labels", "attention_mask"] if dataset.column_names is not None: # None for IterableDataset extra_columns = list(set(dataset.column_names) - set(signature_columns)) else: extra_columns = [] if not remove_unused_columns and len(extra_columns) > 0: warnings.warn( "You passed `remove_unused_columns=False` on a non-packed dataset. This might create some issues with " "the default collator and yield to errors. If you want to inspect dataset other columns (in this " f"case {extra_columns}), you can subclass `DataCollatorForLanguageModeling` in case you used the " "default collator and create your own data collator in order to inspect the unused dataset columns.", UserWarning, ) map_kwargs = { "batched": True, "remove_columns": dataset.column_names if remove_unused_columns else None, "batch_size": self.dataset_batch_size, } if isinstance(dataset, Dataset): map_kwargs["num_proc"] = self.dataset_num_proc # this arg is not available for IterableDataset tokenized_dataset = dataset.map(tokenize, **map_kwargs) return tokenized_dataset4.2. Running the Trainer 4.2. 运行 TrainerThere are a couple of parameters that have an impact on time/resources used during training, and it will depend on the type of hardware you are running. Newer GPUs would allow you to cast the model to torch.bfloat16, use tf32 dtype during training, etc, which would greatly improve training speed and GPU usage. This setup allows you to run with Google Colab’s free T4 GPU. You can also control the memory usage by configuring per_device_train_batch_size and gradient_accumulation_steps as the batch size is given by per_device_train_batch_size * gradient_accumulation_steps. 有几个参数会影响训练期间使用的时间 / 资源，具体取决于您运行的硬件类型。较新的 GPU 将允许您在训练期间将模型转换为 torch.bfloat16、usetf32dtype 等，这将大大提高训练速度和 GPU 使用率。此设置允许您使用 Google Colab 的免费 T4 GPU 运行。您还可以通过configuringper\_device\_train\_batch\_sizeandgradient\_accumulation\_stepsas批处理大小指定为 byper\_device\_train\_batch\_size * gradient\_accumulation\_steps来控制内存使用。import pathlib import wandb import os from trl import SFTConfig num_train_epochs = 1 max_steps = 200 bf16 = False output_dir = 'results' run_name = f"{model_name.split('/')[-1]}-fncall_peft-ds_{dataset_size}-lora_r_{lora_r}-use_qlora_False" output_dir_final = os.path.join(output_dir, run_name) # Adjust tokenizer settings as warned by the trainer tokenizer.padding_side = 'right' # Log into wandb. wandb.login(os.environ.get("WANDB_API_KEY")) print("Creating trainer...") pathlib.Path(output_dir_final).mkdir(parents=True, exist_ok=True) training_args = SFTConfig( dataset_text_field="messages", num_train_epochs=num_train_epochs, per_device_train_batch_size=2, per_device_eval_batch_size=2, gradient_accumulation_steps=8, gradient_checkpointing=True, # Saves memory at the cost of additional training time. bf16=bf16, tf32=False, # use tf32 for faster training on Ampere GPUs or newer. dataloader_pin_memory=False, # pin data to memory. torch_compile=False, # compile to create graphs from existing PyTorch programs. warmup_steps=50, max_steps=max_steps, learning_rate=1e-4, lr_scheduler_type="cosine", weight_decay=0.01, logging_strategy="steps", save_strategy="steps", save_steps=50, save_total_limit=3, eval_strategy="steps", logging_steps=10, output_dir=output_dir_final, optim="paged_adamw_8bit", remove_unused_columns=True, seed=seed, run_name=run_name, report_to="wandb", push_to_hub=False, eval_steps=25, ) trainer = CustomSFTTrainer( model=model, args=training_args, train_dataset=dataset_train_eval["train"], eval_dataset=dataset_train_eval["test"], processing_class=tokenizer, peft_config=lora_config ) print("Training...") trainer.train()>>> Training... >>> wandb: Using wandb-core as the SDK backend. Please refer to https://wandb.me/wandb-core for more information. >>> Tracking run with wandb version 0.19.5 >>> Run data is saved locally in /content/wandb/run-20250131_170132-q9qabdfm >>> Syncing run DeepSeek-R1-Distill-Qwen-1.5B-fncall_peft-ds_small-lora_r_4-use_qlora_False to Weights & Biases (docs) >>> [200/200 2:55:15, Epoch 4/5] >>> TrainOutput(global_step=200, training_loss=0.5143453764915467, metrics={'train_runtime': 10568.7869, 'train_samples_per_second': 0.303, 'train_steps_per_second': 0.019, 'total_flos': 3.03740523380736e+16, 'train_loss': 0.5143453764915467, 'epoch': 4.444444444444445})With the fine-tuning session done, we can check the results on the Wandb platform and assess how well the system performed during training by checking the validation loss. We can see the model was able to be trained by measuring how validation loss (orange line) decreased over time: 完成微调会话后，我们可以在 Wandb 平台上检查结果，并通过检查验证损失来评估系统在训练期间的表现。我们可以看到，通过测量验证损失（橙线）如何随时间减少，可以训练模型：**5. Running Inference with the Fine-Tuned Model 5. 使用微调模型运行推理**After training, load the fine-tune adapters to generate responses from the model. 训练后，加载微调适配器以从模型生成响应。from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel # Helper function for chat generation. def run_inout_pipe(chat_interaction, tokenizer, model): prompt = tokenizer.apply_chat_template(chat_interaction, tokenize=False, add_generation_prompt=True) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=512, pad_token_id=tokenizer.eos_token_id) outputs = outputs[:, inputs['input_ids'].shape[-1]:] return tokenizer.decode(outputs[0], skip_special_tokens=True) # define the model and max_seq_length max_seq_length = 512 model_name = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B' # get latest checkpoint from the training sessions checkpoint_lora_path = 'results/DeepSeek-R1-Distill-Qwen-1.5B-fncall_peft-ds_small-lora_r_4-use_qlora_False/checkpoint-200' # Load base model and tokenizer. model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cuda") tokenizer = AutoTokenizer.from_pretrained( model_name, padding=True, truncation=True, max_length=max_seq_length ) offload_dir = "/temp/offload_dir" # In case the model needs to offload weights. peft_model = PeftModel.from_pretrained(model, checkpoint_lora_path, offload_dir=offload_dir) chat_interaction = [ { "role": "system", "content": '''You are a helpful assistant with access to the following functions. Use them if required - { "name": "convert_currency", "description": "Convert the amount from one currency to another", "parameters": { "type": "object", "properties": { "amount": { "type": "number", "description": "The amount to convert" }, "from_currency": { "type": "string", "description": "The currency to convert from" }, "to_currency": { "type": "string", "description": "The currency to convert to" } }, "required": [ "amount", "from_currency", "to_currency" ] } }''' }, { "role": "user", "content": "Hi, I need to convert 500 US dollars to Euros. Can you help me with that?" } ] print(run_inout_pipe(chat_interaction, tokenizer, peft_model))>>> <functioncall> {"name": "convert_currency", "arguments": '{"amount": 500, "from_currency": "USD", "to_currency": "EUR"}'}</functioncall>Conclusion 结论In this post, we explored how Parameter-Efficient Fine-Tuning via LoRA dramatically reduces the resources needed to adapt LLMs for specific tasks. By injecting low-rank matrices into key layers, only a fraction of the model’s parameters are adjusted while still retaining robust performance. 在这篇文章中，我们探讨了通过 LoRA 的 Parameter-Efficient Fine-Tuning 如何显著减少为特定任务调整 LLM 所需的资源。通过将低秩矩阵注入关键层，只需调整模型参数的一小部分，同时仍保持稳健的性能。

搭建开发环境 Revit二次开发环境搭建Visual studio下载Visual studio，可以通过百度，在官网 https://visualstudio.microsoft.com/zh-hans/下载社区版