|
|
@@ -66,7 +66,7 @@
|
|
|
These models were trained using CBOW with position-weights, in dimension 300, with character n-grams of length 5, a window of size 5 and 10 negatives.
|
|
|
We also distribute three new word analogy datasets, for French, Hindi and Polish.</p>
|
|
|
<h3><a class="anchor" aria-hidden="true" id="download-directly-with-command-line-or-from-python"></a><a href="#download-directly-with-command-line-or-from-python" aria-hidden="true" class="hash-link"><svg class="hash-link-icon" aria-hidden="true" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>Download directly with command line or from python</h3>
|
|
|
-<p>In order to download with command line or from python code, you must have installed the python package as <a href="http://localhost:3000/docs/en/support.html#building-fasttext-python-module">described here</a>.</p>
|
|
|
+<p>In order to download with command line or from python code, you must have installed the python package as <a href="/docs/en/support.html#building-fasttext-python-module">described here</a>.</p>
|
|
|
<div class="tabs"><div class="nav-tabs"><div id="tab-group-16-tab-17" class="nav-link active" data-group="group_16" data-tab="tab-group-16-content-17">Command line</div><div id="tab-group-16-tab-18" class="nav-link" data-group="group_16" data-tab="tab-group-16-content-18">Python</div></div><div class="tab-content"><div id="tab-group-16-content-17" class="tab-pane active" data-group="group_16" tabindex="-1"><div><span><pre><code class="hljs css language-bash">$ ./download_model.py en <span class="hljs-comment"># English</span><br />Downloading https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.bin.gz<br /> (19.78%) [=========> ]<br /></code></pre>
|
|
|
<p>Once the download is finished, use the model as usual:</p>
|
|
|
<pre><code class="hljs css language-bash">$ ./fasttext nn cc.en.300.bin 10<br />Query word?<br /></code></pre>
|
|
|
@@ -74,7 +74,7 @@ We also distribute three new word analogy datasets, for French, Hindi and Polish
|
|
|
</span></div></div></div></div>
|
|
|
<h3><a class="anchor" aria-hidden="true" id="adapt-the-dimension"></a><a href="#adapt-the-dimension" aria-hidden="true" class="hash-link"><svg class="hash-link-icon" aria-hidden="true" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>Adapt the dimension</h3>
|
|
|
<p>The pre-trained word vectors we distribute have dimension 300. If you need a smaller size, you can use our dimension reducer.
|
|
|
-In order to use that feature, you must have installed the python package as <a href="http://localhost:3000/docs/en/support.html#building-fasttext-python-module">described here</a>.</p>
|
|
|
+In order to use that feature, you must have installed the python package as <a href="/docs/en/support.html#building-fasttext-python-module">described here</a>.</p>
|
|
|
<p>For example, in order to get vectors of dimension 100:</p>
|
|
|
<div class="tabs"><div class="nav-tabs"><div id="tab-group-19-tab-20" class="nav-link active" data-group="group_19" data-tab="tab-group-19-content-20">Command line</div><div id="tab-group-19-tab-21" class="nav-link" data-group="group_19" data-tab="tab-group-19-content-21">Python</div></div><div class="tab-content"><div id="tab-group-19-content-20" class="tab-pane active" data-group="group_19" tabindex="-1"><div><span><pre><code class="hljs css language-bash">$ ./reduce_model.py cc.en.300.bin 100<br />Loading model<br />Reducing matrix dimensions<br />Saving model<br />cc.en.100.bin saved<br /></code></pre>
|
|
|
<p>Then you can use the <code>cc.en.100.bin</code> model file as usual.</p>
|
Website Deployment Script