Buckets:

hf-doc-build/doc / transformers /main /ja /bertology.html
HuggingFaceDocBuilder's picture
download
raw
8.69 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;BERTology&quot;,&quot;local&quot;:&quot;bertology&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/transformers/main/ja/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/entry/start.74d040a0.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/scheduler.0c7da001.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/singletons.3e6753ba.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/paths.7e00cf53.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/entry/app.24dfbe31.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/preload-helper.68965f5e.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/index.e0be4b2b.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/nodes/0.9f1fa257.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/nodes/6.5f33c781.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/CopyLLMTxtMenu.6767f26f.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/globals.7f7f1b26.js">
<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.27cfd80f.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;BERTology&quot;,&quot;local&quot;:&quot;bertology&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="bertology" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#bertology"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>BERTology</span></h1> <p data-svelte-h="svelte-w8tzfa">大規模なトランスフォーマー、例えばBERTの内部動作を調査する研究領域が急成長しています(これを「BERTology」とも呼びます)。この分野の良い例は以下です:</p> <ul data-svelte-h="svelte-fxh6wc"><li>BERT Rediscovers the Classical NLP Pipeline by Ian Tenney, Dipanjan Das, Ellie Pavlick:
<a href="https://huggingface.co/papers/1905.05950" rel="nofollow">論文リンク</a></li> <li>Are Sixteen Heads Really Better than One? by Paul Michel, Omer Levy, Graham Neubig: <a href="https://huggingface.co/papers/1905.10650" rel="nofollow">論文リンク</a></li> <li>What Does BERT Look At? An Analysis of BERT’s Attention by Kevin Clark, Urvashi Khandelwal, Omer Levy, Christopher D. Manning: <a href="https://huggingface.co/papers/1906.04341" rel="nofollow">論文リンク</a></li> <li>CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure: <a href="https://huggingface.co/papers/2210.04633" rel="nofollow">論文リンク</a></li></ul> <p data-svelte-h="svelte-14lagya">この新しい分野の発展を支援するために、BERT/GPT/GPT-2モデルにいくつかの追加機能を組み込み、人々が内部表現にアクセスできるようにしました。これらの機能は、主にPaul Michel氏の優れた研究(<a href="https://huggingface.co/papers/1905.10650" rel="nofollow">論文リンク</a>)に基づいています。具体的には、以下の機能が含まれています:</p> <ul data-svelte-h="svelte-80g5ig"><li>BERT/GPT/GPT-2のすべての隠れ状態にアクセスすることができます。</li> <li>BERT/GPT/GPT-2の各ヘッドの注意重みにアクセスできます。</li> <li>ヘッドの出力値と勾配を取得し、ヘッドの重要性スコアを計算し、<a href="https://huggingface.co/papers/1905.10650" rel="nofollow">論文リンク</a>で説明されているようにヘッドを削減できます。</li></ul> <p data-svelte-h="svelte-1ry02fd">これらの機能を理解し、使用するのを支援するために、特定のサンプルスクリプト「<a href="https://github.com/huggingface/transformers-research-projects/tree/main/bertology/run_bertology.py" rel="nofollow">bertology.py</a>」を追加しました。このスクリプトは、GLUEで事前トレーニングされたモデルから情報を抽出し、ヘッドを削減する役割を果たします。</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/ja/bertology.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>
<script>
{
__sveltekit_xgndyu = {
assets: "/docs/transformers/main/ja",
base: "/docs/transformers/main/ja",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/transformers/main/ja/_app/immutable/entry/start.74d040a0.js"),
import("/docs/transformers/main/ja/_app/immutable/entry/app.24dfbe31.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 6],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
8.69 kB
·
Xet hash:
ca835f08ce101e701978df3ff14de5d00defc0d2b6e5e96ba2c1316f997b5eb1

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.