YH Hsu
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights New
    • Engagement control
    • Make a copy
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Engagement control Make a copy Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    1
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    ### [AI / ML領域相關學習筆記入口頁面](https://hackmd.io/@YungHuiHsu/BySsb5dfp) ### [Deeplearning.ai GenAI/LLM系列課程筆記](https://learn.deeplearning.ai/) - [Large Language Models with Semantic Search。大型語言模型與語義搜索 ](https://hackmd.io/@YungHuiHsu/rku-vjhZT) - [Finetuning Large Language Models。微調大型語言模型](https://hackmd.io/@YungHuiHsu/HJ6AT8XG6) - [LangChain for LLM Application Development](https://hackmd.io/1r4pzdfFRwOIRrhtF9iFKQ) --- ## [2022。AACL-IJCNLP。Recent Advances in Pre-trained Language Models: Why Do They Work and How to Use Them](https://d223302.github.io/AACL2022-Pretrain-Language-Model-Tutorial/lecture_material/AACL_2022_tutorial_PLMs.pdf) - 作者:Cheng-Han Chiang,Yung-Sung Chuang, Hung-yi Lee 李弘毅老師實驗室出品,非常棒的語言模型近期(2022年)進展的介紹,出自chatGPT問世前的世代 ### 投影片大綱: - Part 1 Introduction - Framework of Pre-training ![](https://hackmd.io/_uploads/Sky9xVIMT.png =400x) - Part 2 Why do PLMs work - Contextualized Word Representations - Context is considered! ![](https://hackmd.io/_uploads/B16rWEUz6.png =400x) - "lie" 在不同語境(Context)下的分群 ![](https://hackmd.io/_uploads/Hk-v-EIMa.png =600x) - Part 3 How to use PLMs: Contrastive Learning for PLMs - Part 4 How to use PLMs: Parameter-efficient fine-tuning - Part 5 How to use PLMs: Using PLMs with different amounts of data #### 個人補充 - 從數值分布觀點理解 提示工程(Prompt Engineering)與參數效率微調PEFT :::info - **Prompt Engineering(提示工程)** - 在數學上,Prompt Engineering可以被看作是在一個離散的搜索空間內尋找最佳解的過程。這個搜索空間由所有可能的自然語言提示組成。在這個框架下,每一個可能的提示都是一個候選解,我們的目標是找到一個能夠引導語言模型(Language Model, LM)產生我們期望輸出的最佳提示 - **離散性**:提示是用自然語言構成的,不能通過簡單的數學操作(比如加法或乘法)來調整。每一個提示都是獨立且不連續的,你不能在兩個提示之間找到一個清晰的數學路徑。 - **搜索方法**:通過試錯,或者更高級的搜索演算法,在這個離散空間中尋找最適合的提示。這通常涉及到創建多個提示變體,對它們進行評分,然後選擇最好的 - **提示策略或框架**:們不僅僅是關於找到一個單一的有效提示,而是關於如何設計提示來引導模型以一種更加結構化和一致的方式思考,方法包含Chain-of-Thought(CoT)或Tree of Thoughts(ToT)、Self-Consistency等 - PEFT(Parameter-efficient Fine-tuning,參數高效微調) * PEFT則是在一個連續的數學空間中進行的,這個空間是由模型的參數構成的。在這個框架下,微調是通過應用梯度下降(或其他優化算法)在參數空間中尋找一組參數,使得模型的性能最優化 將這兩種方法對比,可以這樣理解:Prompt Engineering是一種**直觀且更接近人類思維的方法**,而PEFT是一種更**數學化、需要計算資源進行數值優化**的方法。Prompt Engineering在概念上更簡單,但可能需要更多的創造性和人工參與。相反,PEFT雖然在計算上更複雜,但它提供了一種更細膩控制模型的方式,並且可以自動化進行 ::: ### Part 4 How to use PLMs: Parameter-efficient fine-tuning 以下摘錄PEFT的四種重要方法(2022年) - Part 4 How do PLMs work: Parameter-efficient fine-tuning - intro - PLMs are gigantic - Need a copy for each downstream task - Problem: PLMs are gigantic (in terms of numbers of parameters, model size, and the storage needed to store the model) - Solution: Reduce the number of parameters by parameter-efficient fine-tuning - Use a small amount of parameters for each downstream task ![](https://hackmd.io/_uploads/rJRnG4UMp.png =400x) 是在BERT時代的預訓練模型為了解決下游任務的模型參數量而提出的解決辦法 - What is standard fine-tuning really doing? - Modify the hidden representations ($h$) of the PLM such that it can perform well on downstream task ![](https://hackmd.io/_uploads/BybfUE8Ma.png =500x) - Fine-tuning = modifying the hidden representation based on a PLM ![](https://hackmd.io/_uploads/Sy1ULEIMa.png =500x) #### 4-1 **Adapter** - 4-1 **Adapter** - pseudo code - from [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://arxiv.org/pdf/2303.15647.pdf) ```python= def transformer_block_with_adapter(x): residual = x x = SelfAttention(x) x = FFN(x) # adapter x = LN(x + residual) residual = x x = FFN(x) # transformer FFN x = FFN(x) # adapter x = LN(x + residual) return x ``` 應該是參數效率調節的開山之作 - Use special submodules to modify hidden representations! ![](https://hackmd.io/_uploads/B1dfwE8fT.png =300x) - small trainable submodules inserted in transformers 在transformers模塊後面插入小型的可訓練運算模算 ![](https://hackmd.io/_uploads/HJPYDE8zT.png =500x) - adptters內部結構 - 使用類似resnet讀跳接設計,一個module level的殘差概念,類似小型UNET ![](https://hackmd.io/_uploads/r1n8FNLMT.png =500x) - During fine-tuning, only update the adpaters and the classifier head 梯度更新時凍結預訓練模型的部分、只更新adpaters跟橋接下游任務的分類頭 ![](https://hackmd.io/_uploads/SkLZKE8Gp.png =400x) - All downstream tasks share the PLM; the adapters in each layer and the classifier heads are the task-specific modules 所有下游任務共享預訓練的語言模型(PLM,即現代所說的LLM)、針對下游特定任務則有專屬的adapters跟分類頭 #### 4-2 **LoRA**: Low-Rank Adaptation of Large Language Models - 4-2 **LoRA**: Low-Rank Adaptation of Large Language Models - pseudo code - from [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://arxiv.org/pdf/2303.15647.pdf) $$ \delta W = W_A W_B \quad W_A \in \mathbb{R}^{in \times r}, \, W_B \in \mathbb{R}^{r \times out} $$ - scaling factor is constant : $\frac{1}{r}$ ```python= def lora_linear(x): h = x @ W # regular linear h += x @ W_A @ W_B # low-rank update return scale * h ``` ![](https://hackmd.io/_uploads/SyDZprLGT.png =500x) - 在Transformer層的上採樣與下採樣計算模塊,分別搭配一組可訓練的參數 - 這裡採用近年常見加寬的並聯設計、猜測除了增加表徵學習與表達的豐富性外,也方便將計算模快平行化做分散式運算 ![](https://hackmd.io/_uploads/r1rE6H8Gp.png =500x) ![](https://hackmd.io/_uploads/BkxjiM8IGa.png =350x) - LoRA設計概念 ![](https://hackmd.io/_uploads/B1nWQ8UM6.png =350x) 1. **動機**: Downstream fine-tunings have low intrinsic dimension - 儘管原始的大型語言模型可能有大量的參數,但實際上只需要調整其中的一小部分參數就可以達到特定的下游任務 2. **權重更新**: Weight after fine-tuning = $W_o$ (pre-trained weight) + $\Delta W$ (updates to the weight) 微調後的權重可以表示為$W_o$(**原始的預訓練權重**) + $\Delta W$(權重的更新) 3. **假設**: The updates to the weight $\Delta W$ also gave a low intrinsic rank 權重的更新$\Delta W$也具有低的固有秩,意即儘管有大量的權重可以更新,但實際上只有一小部分的權重需要被調整。 4. **微調後的權重**: Fine-tuned weight = $W_o + \Delta W = W_o + BA$ , rank $r \ll \min(d_{FFW}, d_{model})$ 微調後的權重 $W$ 可以表示為原始的權重 $W_o$ 加上某種低秩矩陣 $B$和$A$的乘積,其中$r$是這個低秩矩陣的秩,且$r$ 遠小於 $d_{FFW}$和 $d_{model}$中的較小值。 - All downstream tasks share the PLM; the LoRA in each layer and the classifier heads are the task-specific modules ![](https://hackmd.io/_uploads/SyxCI8Ifa.png =400x) #### 4-3 **Prefix tuning** - 4-3 **Prefix tuning** - pseudo code - from [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://arxiv.org/pdf/2303.15647.pdf) - trainable parameters are prepended to the hidden states of all layers - prefix $P_θ ∈ R^{l×h}$ - soft prompts are parametrized through a feed-forward network $P_θ = FFN(\hat{P}_{θ})$. ```python= def transformer_block_for_prefix_tuning(x): soft_prompt = FFN(soft_prompt) x = concat([soft_prompt, x], dim=seq) return transformer_block(x) ``` 前綴微調是一種特殊的微調技術,其中只有模型的一部分參數(即前綴)是可訓練的,而模型的其餘部分保持固定 - Insert trainable prefix in each layer 在模型的**每一層**(Prompt tuning只有在第一層)中插入一個可訓練的前綴。這些前綴參數在微調過程中會被更新,而模型的主體部分則不會 ![](https://hackmd.io/_uploads/S1fdP8LGp.png =400x) - Standard Self-Attention ![](https://hackmd.io/_uploads/SkZhwI8MT.png =400x) - Insert trainable prefix ![](https://hackmd.io/_uploads/rycTwLLfT.png =400x) - Only the prefix (key and value) are updated during finetuning ![](https://hackmd.io/_uploads/ByIMu88Ga.png =400x) - 個人想法 - 雖然可訓練參數只有前綴部分,但矩陣運算的計算量還是被增加? #### 4-4 **(Soft) Prompt tuning / Soft Prompting** - 4-4 **(Soft) Prompt tuning / Soft Prompting** - Prompt tuning:在輸入層前加入一個**可訓練的前綴嵌入(prefix embedding)**,而不是直接在輸入句子中添加固定的詞彙(即硬提示)。Prefix tuning則在每一層插入**可參數化的前綴** - 白話來說,是把提示詞編碼為數值表示(embeddingd)的參數,且這些參數是可以透過梯度下降、反向傳播來優化 - pseudo code - from [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://arxiv.org/pdf/2303.15647.pdf) - prepend the model input embeddings with a trainable tensor("soft prompt") $P ∈ R^{l × h}$ ```python= def soft_prompted_model(input_ids): x = Embed(input_ids) x = concat([soft_prompt, x], dim=seq) return model(x) ``` * Prepend the prefix embedding at the input layer ![](https://hackmd.io/_uploads/HJQ0dLUM6.png =500x) - Soft Prompting can be considered as the soften version of prompting - (Hard) prompting: add words in the input sentence ![](https://hackmd.io/_uploads/SJizt8LfT.png =500x) - **Hard Prompts**: words (that are originally in the vocabulary) 直接在輸入句子中添加固定的詞彙。這些詞彙是原始詞彙表中的詞彙 ![](https://hackmd.io/_uploads/BkeKV5LUM6.png =200x) - **Soft Prompts**: vectors (can be initialized from some word embeddings) - 在輸入層前加入向量(可以從某些詞嵌入中初始化) - 這些向量不一定直接對應於詞彙表中的詞彙,但可以被視為柔和版本的提示 - **通過反向傳播學習**(i.e. 利用梯度方法在連續空間上進行優化),並且可以調整以合併來自任意數量的標記示例的信號(tokens) ![](https://hackmd.io/_uploads/H1vPKIUz6.png =50x) - 軟提示的長度: * 軟提示的長度需要足夠長,以便模型可以從中捕獲足夠的信息。 * 當軟提示的長度足夠長時,增加提示的長度會顯示出遞減的性能增益。這意味著在某一點之後,增加更多的提示不再帶來顯著的性能提升。 * 軟提示的限制: * 詞向量的限制: 軟提示的向量可以從某些詞嵌入中初始化,但不一定要直接對應於詞彙表中的詞彙。 * 長度的限制: 雖然軟提示的長度應該足夠長,但過長的提示可能不會帶來更多的性能增益,並可能增加計算成本 #### 結論 * Benefit 1: Drastically decreases the task-specific parameters PEFT 通過專注於模型中的特定參數來減少任務特定的參數,從而減少了模型的大小和計算需求 ![](https://hackmd.io/_uploads/BJZ_i88fp.png =500x) - Benefit 2: Less easier to overfit on training data; better out-of-domain performance 於 PEFT 使用的參數較少,因此模型較不容易在訓練數據上過度擬合。這意味著模型在未見過的數據上的性能會更好,特別是在領域外的情境中 - Benefit 3: Fewer parameters to fine-tune, making them good candidates when training with small dataset PEFT 方法需要微調的參數較少,這使得它們成為在小數據集上訓練時的理想選擇。這是因為在小數據集上訓練大型模型時,過多的參數可能會導致過度擬合 - Which parameter-efficient fine-tuning should one select? - 沒有放之四海而皆準的方案 ![](https://hackmd.io/_uploads/rySl3IUGp.png) --- # 補充資料 ### Model Customization #### [2023.08。Nvidia。Selecting Large Language Model Customization Techniques](https://developer.nvidia.com/blog/selecting-large-language-model-customization-techniques/) ![image.png](https://hackmd.io/_uploads/BJHP9qd76.png) ### Parameter-efficient fine-tuning #### :pencil2:[低秩矩陣分解( Low-rank Matrix Decomposition)與 LoRA](https://hackmd.io/@YungHuiHsu/S1m3OeKPp) <div style="text-align: center;"> <figure> <img src="https://dustinstansbury.github.io/theclevermachine/assets/images/svd-data-compression/low-rank-approximation.png" alt="low-rank-approximation.png" width="250"> <figcaption> <span style="color: #3F7FBF; font-weight: bold;"> <a href="https://arxiv.org/pdf/2106.09685.pdf" target="_blank">Low-rank Matrix Decomposition</a> </figcaption> </figure> </div> ### Prompt Learning #### [2023。Nvidia。Prompt Learning - p-tuning and prompt tuning](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/nlp/nemo_megatron/prompt_learning.html#p-tuning) 提供理論說明、實做程式碼 ![image.png](https://hackmd.io/_uploads/H12O5cumT.png) > 由於原始模型參數被凍結且不會被這兩種方法所改變,p-tuning/prompt tuning也避免了常在細微調整模型時遇到的災難性遺忘問題 > p-tuning和prompt tuning不是選擇手動或自動的方式來選擇離散的文本提示,而是使用可以**通過梯度下降來優化的虛擬提示嵌入**。在NeMo-Megatron中,prompt tuning和p-tuning的唯一區別在於在訓練過程中用來**調整軟提示token的架構** > 我們將使用continuous、soft和virtual token這些術語來交替指代插入到模型提示中的嵌入,這些嵌入在模型的詞彙中沒有具體映射到字符串或字符。這些虛擬token嵌入與構成模型詞彙的離散、硬或真實token形成對比。虛擬token純粹是1D向量,其維度等於每個真實token嵌入,匹配hidden_size超參數。在訓練和推理中,連續token嵌入根據您在模型的配置中提供的模板,插入到離散token嵌入中。我們將在下面展示如何做到這一點。 * **Prompt Tuning** * [The Power of Scale for Parameter-Efficient Prompt Tuning]() ![image.png](https://hackmd.io/_uploads/H13FAqumT.png =300x) > - 左側:Model Tuning。每一個特定的任務創建一個獨立的模型副本,並對這些副本進行微調 > - 右側:在Prompt Tuning中,只需要在原始的預訓練模型前加入少量的任務特定的prompt(提示) > - 這些prompt作為輸入的一部分,引導模型生成特定任務的輸出。這樣就不需要對模型的核心參數進行改變,從而大幅減少所需的參數量和存儲空間(T5 "XXL" Model: 11B > 20K, with 5 prompt token ) 在對預訓練的GPT模型進行prompt tuning時,軟提示嵌入作為一個2D矩陣初始化,大小為total_virtual_tokens X hidden_size。每個任務都有其自己的2D嵌入矩陣與之關聯。任務在訓練或推理期間不共享任何參數。所有GPT模型參數被凍結,只有每個任務的嵌入參數在訓練期間更新(**各任務間參數獨立**)。 在prompt tuning中,您可以指定每個任務的嵌入如何初始化。您可以: - 根據某些隨機分佈初始化嵌入參數 - 從現有的詞彙嵌入初始化嵌入參數(推薦) 如果您選擇從現有的嵌入權重初始化虛擬token嵌入,您可以在模型的配置中提供您想用於初始化的單詞字符串。這個字符串將被分詞並鋪平或截斷,以匹配您希望使用的虛擬token總數(total_virtual_tokens)。詞彙嵌入被複製並用於為每個任務初始化軟提示嵌入矩陣。詞彙嵌入本身在prompt tuning過程中不更新或改變。 * **P-Tuning** * [GPT Understands, Too]() ![image.png](https://hackmd.io/_uploads/HJfVC5_ma.png =800x) > - 圖a(Discrete Prompt Search)即所謂的以自然語言提示 > - 在這個過程中,一個提示生成器(Prompt Generator)被用來為一個給定的輸入和目標創建一個或多個discrete prompts(離散提示)。 > - 例如,"The capital of Britain is [MASK]",其中"[MASK]"是要模型預測的部分。 > 提示(橙色區域)是根據輸入(藍色區域)而生成的,而模型則根據這些提示生成對應的輸出。在這個過程中,提示是不可微分的,並且通常是通過試錯來進行優化的。 > - 圖b(P-Tuning) > - 在P-Tuning過程中,一個稱為prompt encoder的結構(通常是一個LSTM)被用來生成prompt的嵌入。與Prompt Search不同的是,P-Tuning中的prompt是連續的(可以微分的),這意味著prompt的嵌入和prompt encoder可以通過梯度下降(反向傳播)來優化。 > - 在這個例子中,prompt encoder產生一系列的prompt嵌入(P0到Pj),它們與輸入一起進行處理,以協助模型預測出隱藏的詞("[MASK]") > - 這種方法的好處是,它允許**對提示進行微調**,以最大化性能,而不僅僅是依賴於固定的、離散的提示 在p-tuning中,使用一個LSTM模型來預測虛擬token嵌入。我們將這個LSTM模型稱為prompt_encoder。LSTM參數在p-tuning開始時隨機初始化。所有GPT模型參數被凍結,只有LSTM權重在每個訓練步驟中更新。LSTM**參數所有任務間共享**,但LSTM模型為每個任務輸出唯一的虛擬token嵌入。LSTM預測的虛擬token以與prompt-tuning完全相同的方式插入到離散token輸入中。您仍然通過設置total_virtual_tokens來指定您想使用的虛擬token數量,每個虛擬token嵌入仍然是大小為hidden_size的1D向量。 - **Using Both Prompt and P-Tuning** - 可以同時使用 - p-tuning通常需要較少的虛擬token來達到好的結果,但相較於prompt-tuning,使用的參數數量更多 由於**p-tuning在訓練期間在任務間共享參數**,因此在多個相似任務上對模型進行p-tuning可能會使您的模型在任務間分享洞察力。同樣地,一次在許多非常不同的任務上進行p-tuning可能比prompt tuning表現更差,**後者為每個任務調整一套獨立的參數**。通常我們推薦使用p-tuning而不是prompt tuning。 > Soft prompts can be trained for the input layer only (Liu et al.,2021; Lester et al., 2021) or for all layers (Li and Liang, 2021).

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password

    or

    By clicking below, you agree to our terms of service.

    Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully