chore: import upstream snapshot with attribution

This commit is contained in:
wehub-resource-sync
2026-07-13 12:19:01 +08:00
commit 3b90d1192f
2172 changed files with 594509 additions and 0 deletions
@@ -0,0 +1,622 @@
<!DOCTYPE html>
<html lang="si">
<head>
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
<meta name="description" content="මෙය එන්එල්පී ස්වයංක්රීය ප්රතිගාමීත්වය පිළිබඳ සරල ට්රාන්ස්ෆෝමර් ආකෘතියක් පුහුණු කරයි."/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta name="twitter:title" content="ට්රාන්ස්ෆෝමර් ස්වයංක්රීය ප්රතිගාමී අත්හදා බැලීම"/>
<meta name="twitter:description" content="මෙය එන්එල්පී ස්වයංක්රීය ප්රතිගාමීත්වය පිළිබඳ සරල ට්රාන්ස්ෆෝමර් ආකෘතියක් පුහුණු කරයි."/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/transformers/basic/autoregressive_experiment.html"/>
<meta property="og:title" content="ට්රාන්ස්ෆෝමර් ස්වයංක්රීය ප්රතිගාමී අත්හදා බැලීම"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="ට්රාන්ස්ෆෝමර් ස්වයංක්රීය ප්රතිගාමී අත්හදා බැලීම"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="ට්රාන්ස්ෆෝමර් ස්වයංක්රීය ප්රතිගාමී අත්හදා බැලීම"/>
<meta property="og:description" content="මෙය එන්එල්පී ස්වයංක්රීය ප්රතිගාමීත්වය පිළිබඳ සරල ට්රාන්ස්ෆෝමර් ආකෘතියක් පුහුණු කරයි."/>
<title>ට්රාන්ස්ෆෝමර් ස්වයංක්රීය ප්රතිගාමී අත්හදා බැලීම</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/transformers/basic/autoregressive_experiment.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag() {
dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-4V3HC8HBLH');
</script>
</head>
<body>
<div id='container'>
<div id="background"></div>
<div class='section'>
<div class='docs'>
<p>
<a class="parent" href="/">home</a>
<a class="parent" href="../index.html">transformers</a>
<a class="parent" href="index.html">basic</a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
<img alt="Github"
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
style="max-width:100%;"/></a>
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
<img alt="Twitter"
src="https://img.shields.io/twitter/follow/labmlai?style=social"
style="max-width:100%;"/></a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/basic/autoregressive_experiment.py" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1>ට්රාන්ස්ෆෝමර් ස්වයංක්රීය ප්රතිගාමී අත්හදා බැලීම</h1>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/transformers/basic/autoregressive_experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>
<p>මෙය හඳුන්වා දී ඇති සරල ට්රාන්ස්ෆෝමරයක් පුහුණු කරයි <a href="https://papers.labml.ai/paper/1706.03762">අවධානය එන්එල්පී ස්වයංක්රීය-ප්රතිගාමී කාර්යයක් සඳහා ඔබට අවශ්ය සියල්ල</a> (කුඩා ෂේක්ස්පියර් දත්ත කට්ටලය සමඟ).</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">16</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
<span class="lineno">18</span>
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span>
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">option</span>
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml_nn.experiments.nlp_autoregression</span> <span class="kn">import</span> <span class="n">NLPAutoRegressionConfigs</span>
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml_nn.transformers</span> <span class="kn">import</span> <span class="n">TransformerConfigs</span><span class="p">,</span> <span class="n">Encoder</span>
<span class="lineno">23</span><span class="kn">from</span> <span class="nn">labml_nn.transformers.utils</span> <span class="kn">import</span> <span class="n">subsequent_mask</span></pre></div>
</div>
</div>
<div class='section' id='section-1'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-1'>#</a>
</div>
<h2>ස්වයංක්රීයප්රතිගාමී ආකෘතිය</h2>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">26</span><span class="k">class</span> <span class="nc">AutoregressiveTransformer</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-2'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">encoder</span></code>
ට්රාන්ස්ෆෝමර් <a href="../models.html#Encoder">එන්කෝඩරය</a> </li>
<li><code class="highlight"><span></span><span class="n">src_embed</span></code>
යනු ටෝකන් <a href="../models.html#EmbeddingsWithLearnedPositionalEncoding">කාවැද්දීමේ මොඩියුලය (ස්ථානීය කේතීකරණ සමඟ)</a> </li>
<li><code class="highlight"><span></span><span class="n">generator</span></code>
යනු පිවිසුම් ලබා දෙන <a href="../models.html#Generator">අවසාන පූර්ණ සම්බන්ධිත ස්ථරයයි</a> . </li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">30</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">encoder</span><span class="p">:</span> <span class="n">Encoder</span><span class="p">,</span> <span class="n">src_embed</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">,</span> <span class="n">generator</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-3'>
<div class='docs'>
<div class='section-link'>
<a href='#section-3'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">37</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="lineno">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">src_embed</span> <span class="o">=</span> <span class="n">src_embed</span>
<span class="lineno">39</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoder</span> <span class="o">=</span> <span class="n">encoder</span>
<span class="lineno">40</span> <span class="bp">self</span><span class="o">.</span><span class="n">generator</span> <span class="o">=</span> <span class="n">generator</span></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p>පළමුඇමතුමෙන් වෙස්මුහුණ ආරම්භ කරනු ඇත </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">43</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</span> <span class="o">=</span> <span class="kc">None</span></pre></div>
</div>
</div>
<div class='section' id='section-5'>
<div class='docs'>
<div class='section-link'>
<a href='#section-5'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">45</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-6'>
<div class='docs'>
<div class='section-link'>
<a href='#section-6'>#</a>
</div>
<p>වෙස්මුහුණආරම්භ කර නොමැති නම් හෝ වෙස් මුහුණෙහි ප්රමාණය වෙනස් නම් පසුකාලීන වෙස්මුහුණක් සාදන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">48</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
<p>පසුකාලීනවෙස්මුහුණ, අනාගත ටෝකන දැකීමෙන් ටෝකන වසං කරනු ඇත </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">50</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</span> <span class="o">=</span> <span class="n">subsequent_mask</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">))</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-8'>
<div class='docs'>
<div class='section-link'>
<a href='#section-8'>#</a>
</div>
<p>ස්ථානීයකේතන ක්රම සමඟ ටෝකන් කාවැද්දීම් ලබා ගන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">52</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">src_embed</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-9'>
<div class='docs'>
<div class='section-link'>
<a href='#section-9'>#</a>
</div>
<p>ට්රාන්ස්ෆෝමර්එන්කෝඩරය </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">54</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoder</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-10'>
<div class='docs'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
<p>පිවිසුම්ලබා ගන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">56</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">generator</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-11'>
<div class='docs'>
<div class='section-link'>
<a href='#section-11'>#</a>
</div>
<p>ප්රතිලාභප්රති results ල (දෙවන අගය රාජ්ය සඳහා වේ, මන්ද අපගේ පුහුණුකරු RNs සමඟ ද භාවිතා කරයි) </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">60</span> <span class="k">return</span> <span class="n">x</span><span class="p">,</span> <span class="kc">None</span></pre></div>
</div>
</div>
<div class='section' id='section-12'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-12'>#</a>
</div>
<h2>වින්යාසකිරීම්</h2>
<p>මෙයඋරුම වන්නේ <a href="../../experiments/nlp_autoregression.html#NLPAutoRegressionConfigs"><code class="highlight"><span></span><span class="n">NLPAutoRegressionConfigs</span></code>
</a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">63</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">NLPAutoRegressionConfigs</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-13'>
<div class='docs'>
<div class='section-link'>
<a href='#section-13'>#</a>
</div>
<p>GPTආකෘතිය </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">72</span> <span class="n">model</span><span class="p">:</span> <span class="n">AutoregressiveTransformer</span></pre></div>
</div>
</div>
<div class='section' id='section-14'>
<div class='docs'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
<p>ට්රාන්ස්ෆෝමර් </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">74</span> <span class="n">transformer</span><span class="p">:</span> <span class="n">TransformerConfigs</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
<h3>ට්රාන්ස්ෆෝමර්වින්යාසයන්</h3>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">77</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">transformer</span><span class="p">,</span> <span class="s1">&#39;Transformer&#39;</span><span class="p">)</span>
<span class="lineno">78</span><span class="k">def</span> <span class="nf">_transformer_configs</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-16'>
<div class='docs'>
<div class='section-link'>
<a href='#section-16'>#</a>
</div>
<p>අපගේ <a href="../configs.html#TransformerConfigs">වින්යාසගත කළ හැකි ට්රාන්ස්ෆෝමර් ක්රියාත්මක කිරීම</a> භාවිතා කරමු </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">TransformerConfigs</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-17'>
<div class='docs'>
<div class='section-link'>
<a href='#section-17'>#</a>
</div>
<p>කාවැද්දීම්සහ පිවිසුම් උත්පාදනය සඳහා වචන මාලාව ප්රමාණ සකසන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">87</span> <span class="n">conf</span><span class="o">.</span><span class="n">n_src_vocab</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">n_tokens</span>
<span class="lineno">88</span> <span class="n">conf</span><span class="o">.</span><span class="n">n_tgt_vocab</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">n_tokens</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs'>
<div class='section-link'>
<a href='#section-18'>#</a>
</div>
<p> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">90</span> <span class="n">conf</span><span class="o">.</span><span class="n">d_model</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">d_model</span></pre></div>
</div>
</div>
<div class='section' id='section-19'>
<div class='docs'>
<div class='section-link'>
<a href='#section-19'>#</a>
</div>
<p> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">93</span> <span class="k">return</span> <span class="n">conf</span></pre></div>
</div>
</div>
<div class='section' id='section-20'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-20'>#</a>
</div>
<p> GPTආකෘතිය සාදන්න සහ බර ආරම්භ කරන්න</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">96</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
<span class="lineno">97</span><span class="k">def</span> <span class="nf">_model</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-21'>
<div class='docs'>
<div class='section-link'>
<a href='#section-21'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">101</span> <span class="n">m</span> <span class="o">=</span> <span class="n">AutoregressiveTransformer</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">encoder</span><span class="p">,</span>
<span class="lineno">102</span> <span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">src_embed</span><span class="p">,</span>
<span class="lineno">103</span> <span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">generator</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
<span class="lineno">104</span>
<span class="lineno">105</span> <span class="k">return</span> <span class="n">m</span></pre></div>
</div>
</div>
<div class='section' id='section-22'>
<div class='docs'>
<div class='section-link'>
<a href='#section-22'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">108</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span></pre></div>
</div>
</div>
<div class='section' id='section-23'>
<div class='docs'>
<div class='section-link'>
<a href='#section-23'>#</a>
</div>
<p>අත්හදාබැලීම සාදන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">110</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">&quot;transformer&quot;</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-24'>
<div class='docs'>
<div class='section-link'>
<a href='#section-24'>#</a>
</div>
<p>වින්යාසසාදන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">112</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-25'>
<div class='docs'>
<div class='section-link'>
<a href='#section-25'>#</a>
</div>
<p>වින්යාසයන්අභිබවා යන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">114</span> <span class="n">experiment</span><span class="o">.</span><span class="n">configs</span><span class="p">(</span><span class="n">conf</span><span class="p">,</span> <span class="p">{</span></pre></div>
</div>
</div>
<div class='section' id='section-26'>
<div class='docs'>
<div class='section-link'>
<a href='#section-26'>#</a>
</div>
<p>අක්ෂරමට්ටමේ ටෝකනයිසර් භාවිතා කරන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">116</span> <span class="s1">&#39;tokenizer&#39;</span><span class="p">:</span> <span class="s1">&#39;character&#39;</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-27'>
<div class='docs'>
<div class='section-link'>
<a href='#section-27'>#</a>
</div>
<p>කඩිනම්බෙදුම්කරු හිස් ය </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">118</span> <span class="s1">&#39;prompt_separator&#39;</span><span class="p">:</span> <span class="s1">&#39;&#39;</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-28'>
<div class='docs'>
<div class='section-link'>
<a href='#section-28'>#</a>
</div>
<p>නියැදීමසඳහා විමසුමක් ආරම්භ කිරීම </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">120</span> <span class="s1">&#39;prompt&#39;</span><span class="p">:</span> <span class="s1">&#39;It is &#39;</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-29'>
<div class='docs'>
<div class='section-link'>
<a href='#section-29'>#</a>
</div>
<p>කුඩාෂේක්ස්පියර් දත්ත කට්ටලය භාවිතා කරන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">122</span> <span class="s1">&#39;text&#39;</span><span class="p">:</span> <span class="s1">&#39;tiny_shakespeare&#39;</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-30'>
<div class='docs'>
<div class='section-link'>
<a href='#section-30'>#</a>
</div>
<p>කසන්දර්භය ප්රමාණය භාවිතා <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">256</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">125</span> <span class="s1">&#39;seq_len&#39;</span><span class="p">:</span> <span class="mi">512</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-31'>
<div class='docs'>
<div class='section-link'>
<a href='#section-31'>#</a>
</div>
<p>32වයස අවුරුදු සඳහා දුම්රිය </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">127</span> <span class="s1">&#39;epochs&#39;</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-32'>
<div class='docs'>
<div class='section-link'>
<a href='#section-32'>#</a>
</div>
<p>කණ්ඩායම්ප්රමාණය <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">32</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">129</span> <span class="s1">&#39;batch_size&#39;</span><span class="p">:</span> <span class="mi">16</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-33'>
<div class='docs'>
<div class='section-link'>
<a href='#section-33'>#</a>
</div>
<p>එක් <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">10</span></span></span></span></span> යුගයකට වරක් පුහුණුව සහ වලංගු කිරීම අතර මාරු වන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">132</span> <span class="s1">&#39;inner_iterations&#39;</span><span class="p">:</span> <span class="mi">10</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-34'>
<div class='docs'>
<div class='section-link'>
<a href='#section-34'>#</a>
</div>
<p>ආදර්ශප්රමාණය </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">135</span> <span class="s1">&#39;d_model&#39;</span><span class="p">:</span> <span class="mi">256</span><span class="p">,</span>
<span class="lineno">136</span> <span class="s1">&#39;transformer.n_heads&#39;</span><span class="p">:</span> <span class="mi">16</span><span class="p">,</span>
<span class="lineno">137</span> <span class="s1">&#39;transformer.ffn.d_ff&#39;</span><span class="p">:</span> <span class="mi">1024</span><span class="p">,</span></pre></div>
</div>
</div>
<div class='section' id='section-35'>
<div class='docs'>
<div class='section-link'>
<a href='#section-35'>#</a>
</div>
<p><a href="../../optimizers/noam.html">නෝම් ප්රශස්තකරණය</a> භාවිතා කරන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">140</span> <span class="s1">&#39;optimizer.optimizer&#39;</span><span class="p">:</span> <span class="s1">&#39;Noam&#39;</span><span class="p">,</span>
<span class="lineno">141</span> <span class="s1">&#39;optimizer.learning_rate&#39;</span><span class="p">:</span> <span class="mf">1.</span><span class="p">,</span>
<span class="lineno">142</span> <span class="p">})</span></pre></div>
</div>
</div>
<div class='section' id='section-36'>
<div class='docs'>
<div class='section-link'>
<a href='#section-36'>#</a>
</div>
<p>ඉතිරිකිරීම සහ පැටවීම සඳහා ආකෘති සකසන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">145</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_pytorch_models</span><span class="p">({</span><span class="s1">&#39;model&#39;</span><span class="p">:</span> <span class="n">conf</span><span class="o">.</span><span class="n">model</span><span class="p">})</span></pre></div>
</div>
</div>
<div class='section' id='section-37'>
<div class='docs'>
<div class='section-link'>
<a href='#section-37'>#</a>
</div>
<p>අත්හදාබැලීම ආරම්භ කරන්න </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">148</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span></pre></div>
</div>
</div>
<div class='section' id='section-38'>
<div class='docs'>
<div class='section-link'>
<a href='#section-38'>#</a>
</div>
<p>පුහුණුධාවනය </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">150</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-39'>
<div class='docs'>
<div class='section-link'>
<a href='#section-39'>#</a>
</div>
<p> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">154</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="lineno">155</span> <span class="n">main</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='footer'>
<a href="https://papers.labml.ai">Trending Research Papers</a>
<a href="https://labml.ai">labml.ai</a>
</div>
</div>
<script src=../../interactive.js?v=1"></script>
<script>
function handleImages() {
var images = document.querySelectorAll('p>img')
for (var i = 0; i < images.length; ++i) {
handleImage(images[i])
}
}
function handleImage(img) {
img.parentElement.style.textAlign = 'center'
var modal = document.createElement('div')
modal.id = 'modal'
var modalContent = document.createElement('div')
modal.appendChild(modalContent)
var modalImage = document.createElement('img')
modalContent.appendChild(modalImage)
var span = document.createElement('span')
span.classList.add('close')
span.textContent = 'x'
modal.appendChild(span)
img.onclick = function () {
console.log('clicked')
document.body.appendChild(modal)
modalImage.src = img.src
}
span.onclick = function () {
document.body.removeChild(modal)
}
}
handleImages()
</script>
</body>
</html>
+115
View File
@@ -0,0 +1,115 @@
<!DOCTYPE html>
<html lang="si">
<head>
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
<meta name="description" content=""/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta name="twitter:title" content=""/>
<meta name="twitter:description" content=""/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/transformers/basic/index.html"/>
<meta property="og:title" content=""/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content=""/>
<meta property="og:type" content="object"/>
<meta property="og:title" content=""/>
<meta property="og:description" content=""/>
<title></title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/transformers/basic/index.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag() {
dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-4V3HC8HBLH');
</script>
</head>
<body>
<div id='container'>
<div id="background"></div>
<div class='section'>
<div class='docs'>
<p>
<a class="parent" href="/">home</a>
<a class="parent" href="../index.html">transformers</a>
<a class="parent" href="index.html">basic</a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
<img alt="Github"
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
style="max-width:100%;"/></a>
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
<img alt="Twitter"
src="https://img.shields.io/twitter/follow/labmlai?style=social"
style="max-width:100%;"/></a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/basic/__init__.py" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='footer'>
<a href="https://papers.labml.ai">Trending Research Papers</a>
<a href="https://labml.ai">labml.ai</a>
</div>
</div>
<script src=../../interactive.js?v=1"></script>
<script>
function handleImages() {
var images = document.querySelectorAll('p>img')
for (var i = 0; i < images.length; ++i) {
handleImage(images[i])
}
}
function handleImage(img) {
img.parentElement.style.textAlign = 'center'
var modal = document.createElement('div')
modal.id = 'modal'
var modalContent = document.createElement('div')
modal.appendChild(modalContent)
var modalImage = document.createElement('img')
modalContent.appendChild(modalImage)
var span = document.createElement('span')
span.classList.add('close')
span.textContent = 'x'
modal.appendChild(span)
img.onclick = function () {
console.log('clicked')
document.body.appendChild(modal)
modalImage.src = img.src
}
span.onclick = function () {
document.body.removeChild(modal)
}
}
handleImages()
</script>
</body>
</html>