Files
2024-08-16 16:35:25 +05:30

493 lines
37 KiB
HTML

<!DOCTYPE html>
<html lang="zh">
<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="gpt2.py"/>
<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/lora/gpt2.html"/>
<meta property="og:title" content="gpt2.py"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="gpt2.py"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="gpt2.py"/>
<meta property="og:description" content=""/>
<title>gpt2.py</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/lora/gpt2.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">lora</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/lora/gpt2.py" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">1</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">2</span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
<span class="lineno">3</span><span class="kn">from</span> <span class="nn">labml_nn.lora</span> <span class="kn">import</span> <span class="n">Linear</span><span class="p">,</span> <span class="n">Embedding</span></pre></div>
</div>
</div>
<div class='section' id='section-1'>
<div class='docs'>
<div class='section-link'>
<a href='#section-1'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">6</span><span class="k">class</span> <span class="nc">FFN</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'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">7</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">dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_embed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">r</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
<span class="lineno">8</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</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>
<p>lin1 </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">10</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_fc</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">n_embed</span><span class="p">,</span> <span class="n">dim</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">)</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>lin2 </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">12</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_proj</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">dim</span><span class="p">,</span> <span class="n">n_embed</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="lineno">13</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">functional</span><span class="o">.</span><span class="n">gelu</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">15</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">hidden_states</span><span class="p">):</span>
<span class="lineno">16</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">17</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">18</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_proj</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">19</span> <span class="k">return</span> <span class="n">hidden_states</span></pre></div>
</div>
</div>
<div class='section' id='section-6'>
<div class='docs'>
<div class='section-link'>
<a href='#section-6'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">22</span><span class="k">class</span> <span class="nc">MultiHeadAttention</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-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">23</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">n_embed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">r</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
<span class="lineno">24</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">25</span> <span class="bp">self</span><span class="o">.</span><span class="n">embed_dim</span> <span class="o">=</span> <span class="n">n_embed</span>
<span class="lineno">26</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_heads</span> <span class="o">=</span> <span class="n">n_embed</span>
<span class="lineno">27</span> <span class="bp">self</span><span class="o">.</span><span class="n">head_dim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embed_dim</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_heads</span>
<span class="lineno">28</span> <span class="bp">self</span><span class="o">.</span><span class="n">split_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embed_dim</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>qkv </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">31</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_att</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">n_embed</span><span class="p">,</span> <span class="n">n_embed</span> <span class="o">*</span> <span class="mi">3</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">True</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>out </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">33</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_proj</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">n_embed</span><span class="p">,</span> <span class="n">n_embed</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-10'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
<p> Splits hidden_size dim into attn_head_size and num_heads</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">35</span> <span class="k">def</span> <span class="nf">_split_heads</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tensor</span><span class="p">,</span> <span class="n">num_heads</span><span class="p">,</span> <span class="n">attn_head_size</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>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">39</span> <span class="n">new_shape</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">size</span><span class="p">()[:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="p">(</span><span class="n">num_heads</span><span class="p">,</span> <span class="n">attn_head_size</span><span class="p">)</span>
<span class="lineno">40</span> <span class="n">tensor</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">new_shape</span><span class="p">)</span>
<span class="lineno">41</span> <span class="k">return</span> <span class="n">tensor</span><span class="o">.</span><span class="n">permute</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span> <span class="c1"># (batch, head, seq_length, head_features)</span></pre></div>
</div>
</div>
<div class='section' id='section-12'>
<div class='docs'>
<div class='section-link'>
<a href='#section-12'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">43</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">hidden_states</span><span class="p">):</span>
<span class="lineno">44</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">seq_length</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">hidden_states</span><span class="o">.</span><span class="n">size</span><span class="p">()</span>
<span class="lineno">45</span>
<span class="lineno">46</span> <span class="n">query</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_att</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">split_size</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
<span class="lineno">47</span>
<span class="lineno">48</span> <span class="n">query</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_split_heads</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_heads</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">head_dim</span><span class="p">)</span>
<span class="lineno">49</span> <span class="n">key</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_split_heads</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_heads</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">head_dim</span><span class="p">)</span>
<span class="lineno">50</span> <span class="n">value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_split_heads</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_heads</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">head_dim</span><span class="p">)</span>
<span class="lineno">51</span>
<span class="lineno">52</span> <span class="n">attn_output</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">functional</span><span class="o">.</span><span class="n">scaled_dot_product_attention</span><span class="p">(</span>
<span class="lineno">53</span> <span class="n">query</span><span class="p">,</span>
<span class="lineno">54</span> <span class="n">key</span><span class="p">,</span>
<span class="lineno">55</span> <span class="n">value</span><span class="p">,</span>
<span class="lineno">56</span> <span class="n">attn_mask</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="lineno">57</span> <span class="n">dropout_p</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="lineno">58</span> <span class="n">is_causal</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="c1"># for the triangular mask</span>
<span class="lineno">59</span> <span class="p">)</span>
<span class="lineno">60</span>
<span class="lineno">61</span> <span class="n">attn_output</span> <span class="o">=</span> <span class="n">attn_output</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">contiguous</span><span class="p">()</span>
<span class="lineno">62</span> <span class="n">attn_output</span> <span class="o">=</span> <span class="n">attn_output</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">seq_length</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">embed_dim</span><span class="p">)</span>
<span class="lineno">63</span>
<span class="lineno">64</span> <span class="n">attn_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">c_proj</span><span class="p">(</span><span class="n">attn_output</span><span class="p">)</span>
<span class="lineno">65</span>
<span class="lineno">66</span> <span class="k">return</span> <span class="n">attn_output</span></pre></div>
</div>
</div>
<div class='section' id='section-13'>
<div class='docs'>
<div class='section-link'>
<a href='#section-13'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">69</span><span class="k">class</span> <span class="nc">Block</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-14'>
<div class='docs'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">70</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">n_embed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">layer_norm_epsilon</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">r</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
<span class="lineno">71</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">72</span> <span class="bp">self</span><span class="o">.</span><span class="n">pre_norm</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">n_embed</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">layer_norm_epsilon</span><span class="p">)</span>
<span class="lineno">73</span> <span class="bp">self</span><span class="o">.</span><span class="n">attn</span> <span class="o">=</span> <span class="n">MultiHeadAttention</span><span class="p">(</span><span class="n">n_embed</span><span class="p">,</span> <span class="n">r</span><span class="p">)</span>
<span class="lineno">74</span> <span class="bp">self</span><span class="o">.</span><span class="n">post_norm</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">n_embed</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">layer_norm_epsilon</span><span class="p">)</span>
<span class="lineno">75</span> <span class="bp">self</span><span class="o">.</span><span class="n">ffn</span> <span class="o">=</span> <span class="n">FFN</span><span class="p">(</span><span class="n">n_embed</span> <span class="o">*</span> <span class="mi">4</span><span class="p">,</span> <span class="n">n_embed</span><span class="p">,</span> <span class="n">r</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">77</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">hidden_states</span><span class="p">):</span>
<span class="lineno">78</span> <span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="lineno">79</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pre_norm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">80</span>
<span class="lineno">81</span> <span class="n">attn_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">attn</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">82</span>
<span class="lineno">83</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="n">attn_output</span> <span class="o">+</span> <span class="n">residual</span>
<span class="lineno">84</span> <span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="lineno">85</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">post_norm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">86</span> <span class="n">feed_forward_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ffn</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="lineno">87</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="n">feed_forward_output</span> <span class="o">+</span> <span class="n">residual</span>
<span class="lineno">88</span>
<span class="lineno">89</span> <span class="k">return</span> <span class="n">hidden_states</span></pre></div>
</div>
</div>
<div class='section' id='section-16'>
<div class='docs'>
<div class='section-link'>
<a href='#section-16'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">92</span><span class="k">class</span> <span class="nc">GPTModel</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-17'>
<div class='docs'>
<div class='section-link'>
<a href='#section-17'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">93</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">layer_norm_epsilon</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">n_embd</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_layer</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_positions</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="lineno">94</span> <span class="n">vocab_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">r</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
<span class="lineno">95</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">96</span>
<span class="lineno">97</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_embedding</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">vocab_size</span><span class="p">,</span> <span class="n">n_embd</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">)</span>
<span class="lineno">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">position_embedding</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">n_positions</span><span class="p">,</span> <span class="n">n_embd</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">)</span>
<span class="lineno">99</span>
<span class="lineno">100</span> <span class="bp">self</span><span class="o">.</span><span class="n">blocks</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">Block</span><span class="p">(</span><span class="n">n_embd</span><span class="p">,</span> <span class="n">layer_norm_epsilon</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">)</span>
<span class="lineno">101</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_layer</span><span class="p">)])</span>
<span class="lineno">102</span>
<span class="lineno">103</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_norm</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">n_embd</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">layer_norm_epsilon</span><span class="p">)</span>
<span class="lineno">104</span>
<span class="lineno">105</span> <span class="bp">self</span><span class="o">.</span><span class="n">lm_head</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">n_embd</span><span class="p">,</span> <span class="n">vocab_size</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">r</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-18'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">input_ids</span></code>
has shape <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">seq_len</span><span class="p">]</span></code>
</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">107</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">input_ids</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-19'>
<div class='docs'>
<div class='section-link'>
<a href='#section-19'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">111</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">seq_len</span> <span class="o">=</span> <span class="n">input_ids</span><span class="o">.</span><span class="n">shape</span></pre></div>
</div>
</div>
<div class='section' id='section-20'>
<div class='docs'>
<div class='section-link'>
<a href='#section-20'>#</a>
</div>
<p>Get token embeddings </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">114</span> <span class="n">token_embeddings</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_embedding</span><span class="p">(</span><span class="n">input_ids</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>
<p>Get position ids </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">116</span> <span class="n">position_ids</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="n">seq_len</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">input_ids</span><span class="o">.</span><span class="n">device</span><span class="p">)[</span><span class="kc">None</span><span class="p">,</span> <span class="p">:]</span></pre></div>
</div>
</div>
<div class='section' id='section-22'>
<div class='docs'>
<div class='section-link'>
<a href='#section-22'>#</a>
</div>
<p>Get position embeddings </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">118</span> <span class="n">position_embeddings</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">position_embedding</span><span class="p">(</span><span class="n">position_ids</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>Add position embeddings </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">121</span> <span class="n">x</span> <span class="o">=</span> <span class="n">token_embeddings</span> <span class="o">+</span> <span class="n">position_embeddings</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>Run through transformer blocks </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">124</span> <span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">blocks</span><span class="p">:</span>
<span class="lineno">125</span> <span class="n">x</span> <span class="o">=</span> <span class="n">block</span><span class="p">(</span><span class="n">x</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>Final normalization </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">128</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_norm</span><span class="p">(</span><span class="n">x</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>Get logits from projection layer </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">130</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">lm_head</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='footer'>
<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>