mirror of
https://github.com/ml-explore/mlx.git
synced 2025-09-19 19:38:16 +08:00
rebase
This commit is contained in:
Awni Hannun
committed by
CircleCI Docs
CircleCI Docs
parent
a68317ae17
commit
a35796f0ea
@@ -8,7 +8,7 @@
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
|
||||
|
||||
<title>mlx.nn.Transformer — MLX 0.18.0 documentation</title>
|
||||
<title>mlx.nn.Transformer — MLX 0.18.1 documentation</title>
|
||||
|
||||
|
||||
|
||||
@@ -36,7 +36,7 @@
|
||||
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=5b4479735964841361fd" />
|
||||
<script src="../../../_static/vendor/fontawesome/6.1.2/js/all.min.js?digest=5b4479735964841361fd"></script>
|
||||
|
||||
<script src="../../../_static/documentation_options.js?v=4033e70d"></script>
|
||||
<script src="../../../_static/documentation_options.js?v=fbcf6510"></script>
|
||||
<script src="../../../_static/doctools.js?v=888ff710"></script>
|
||||
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="../../../_static/scripts/sphinx-book-theme.js?v=efea14e4"></script>
|
||||
@@ -131,8 +131,8 @@
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/mlx_logo.png" class="logo__image only-light" alt="MLX 0.18.0 documentation - Home"/>
|
||||
<script>document.write(`<img src="../../../_static/mlx_logo_dark.png" class="logo__image only-dark" alt="MLX 0.18.0 documentation - Home"/>`);</script>
|
||||
<img src="../../../_static/mlx_logo.png" class="logo__image only-light" alt="MLX 0.18.1 documentation - Home"/>
|
||||
<script>document.write(`<img src="../../../_static/mlx_logo_dark.png" class="logo__image only-dark" alt="MLX 0.18.1 documentation - Home"/>`);</script>
|
||||
|
||||
|
||||
</a></div>
|
||||
@@ -370,6 +370,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.repeat.html">mlx.core.repeat</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.reshape.html">mlx.core.reshape</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.right_shift.html">mlx.core.right_shift</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.roll.html">mlx.core.roll</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.round.html">mlx.core.round</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.rsqrt.html">mlx.core.rsqrt</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.save.html">mlx.core.save</a></li>
|
||||
@@ -425,6 +426,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.random.truncated_normal.html">mlx.core.random.truncated_normal</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.random.uniform.html">mlx.core.random.uniform</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.random.laplace.html">mlx.core.random.laplace</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../_autosummary/mlx.core.random.permutation.html">mlx.core.random.permutation</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../transforms.html">Transforms</a><input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-6"><i class="fa-solid fa-chevron-down"></i></label><ul>
|
||||
@@ -881,18 +883,18 @@ mechanism.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>dims</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – The number of expected features in the
|
||||
<li><p><strong>dims</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><em>optional</em>) – The number of expected features in the
|
||||
encoder/decoder inputs. Default: <code class="docutils literal notranslate"><span class="pre">512</span></code>.</p></li>
|
||||
<li><p><strong>num_heads</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – The number of attention heads. Default:
|
||||
<li><p><strong>num_heads</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><em>optional</em>) – The number of attention heads. Default:
|
||||
<code class="docutils literal notranslate"><span class="pre">8</span></code>.</p></li>
|
||||
<li><p><strong>num_encoder_layers</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – The number of encoder layers in the
|
||||
<li><p><strong>num_encoder_layers</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><em>optional</em>) – The number of encoder layers in the
|
||||
Transformer encoder. Default: <code class="docutils literal notranslate"><span class="pre">6</span></code>.</p></li>
|
||||
<li><p><strong>num_decoder_layers</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – The number of decoder layers in the
|
||||
<li><p><strong>num_decoder_layers</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><em>optional</em>) – The number of decoder layers in the
|
||||
Transformer decoder. Default: <code class="docutils literal notranslate"><span class="pre">6</span></code>.</p></li>
|
||||
<li><p><strong>mlp_dims</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – The hidden dimension of the MLP block in each
|
||||
<li><p><strong>mlp_dims</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><em>optional</em>) – The hidden dimension of the MLP block in each
|
||||
Transformer layer. Defaults to <code class="docutils literal notranslate"><span class="pre">4*dims</span></code> if not provided. Default:
|
||||
<code class="docutils literal notranslate"><span class="pre">None</span></code>.</p></li>
|
||||
<li><p><strong>dropout</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>, </em><em>optional</em>) – The dropout value for the Transformer
|
||||
<li><p><strong>dropout</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><em>float</em></a><em>, </em><em>optional</em>) – The dropout value for the Transformer
|
||||
encoder and decoder. Dropout is used after each attention layer and
|
||||
the activation in the MLP layer. Default: <code class="docutils literal notranslate"><span class="pre">0.0</span></code>.</p></li>
|
||||
<li><p><strong>activation</strong> (<em>function</em><em>, </em><em>optional</em>) – the activation function for the MLP
|
||||
@@ -901,10 +903,10 @@ hidden layer. Default: <a class="reference internal" href="../_autosummary_funct
|
||||
standard Transformer encoder. Default: <code class="docutils literal notranslate"><span class="pre">None</span></code>.</p></li>
|
||||
<li><p><strong>custom_decoder</strong> (<a class="reference internal" href="../module.html#mlx.nn.Module" title="mlx.nn.Module"><em>Module</em></a><em>, </em><em>optional</em>) – A custom decoder to replace the
|
||||
standard Transformer decoder. Default: <code class="docutils literal notranslate"><span class="pre">None</span></code>.</p></li>
|
||||
<li><p><strong>norm_first</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a><em>, </em><em>optional</em>) – if <code class="docutils literal notranslate"><span class="pre">True</span></code>, encoder and decoder layers
|
||||
<li><p><strong>norm_first</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><em>bool</em></a><em>, </em><em>optional</em>) – if <code class="docutils literal notranslate"><span class="pre">True</span></code>, encoder and decoder layers
|
||||
will perform layer normalization before attention and MLP
|
||||
operations, otherwise after. Default: <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p></li>
|
||||
<li><p><strong>checkpoint</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a><em>, </em><em>optional</em>) – if <code class="docutils literal notranslate"><span class="pre">True</span></code> perform gradient checkpointing
|
||||
<li><p><strong>checkpoint</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><em>bool</em></a><em>, </em><em>optional</em>) – if <code class="docutils literal notranslate"><span class="pre">True</span></code> perform gradient checkpointing
|
||||
to reduce the memory usage at the expense of more computation.
|
||||
Default: <code class="docutils literal notranslate"><span class="pre">False</span></code>.</p></li>
|
||||
</ul>
|
||||
|
||||
Reference in New Issue
Block a user