disco.europe.naverlabs.com
Open in
urlscan Pro
217.109.185.194
Public Scan
URL:
https://disco.europe.naverlabs.com/
Submission: On February 27 via automatic, source certstream-suspicious — Scanned from FR
Submission: On February 27 via automatic, source certstream-suspicious — Scanned from FR
Form analysis
1 forms found in the DOMName: mc-embedded-subscribe-form — POST https://naverlabs.us20.list-manage.com/subscribe/post?u=02674ee40d31529a370700212&id=e3a0ed705f
<form action="https://naverlabs.us20.list-manage.com/subscribe/post?u=02674ee40d31529a370700212&id=e3a0ed705f" method="post" id="mc-embedded-subscribe-form" name="mc-embedded-subscribe-form" class="validate" target="_blank"
novalidate="novalidate">
<div id="mc_embed_signup_scroll">
<div class="indicates-required"><span class="asterisk">*</span> indicates required</div>
<div class="mc-field-group">
<label for="mce-EMAIL">Email Address <span class="asterisk">*</span>
</label>
<input type="email" value="" name="EMAIL" class="required email" id="mce-EMAIL" aria-required="true">
</div>
<div class="mc-field-group">
<label for="mce-FNAME">First Name </label>
<input type="text" value="" name="FNAME" class="" id="mce-FNAME">
</div>
<div class="mc-field-group">
<label for="mce-LNAME">Last Name </label>
<input type="text" value="" name="LNAME" class="" id="mce-LNAME">
</div>
<!--<div class="mc-field-group size1of2">
<label for="mce-BIRTHDAY-month">Birthday </label>
<div class="datefield">
<span class="subfield monthfield"><input class="birthday " type="text" pattern="[0-9]*" value="" placeholder="MM" size="2" maxlength="2" name="BIRTHDAY[month]" id="mce-BIRTHDAY-month"></span> /
<span class="subfield dayfield"><input class="birthday " type="text" pattern="[0-9]*" value="" placeholder="DD" size="2" maxlength="2" name="BIRTHDAY[day]" id="mce-BIRTHDAY-day"></span>
<span class="small-meta nowrap">( mm / dd )</span>
</div>-->
</div>
<div id="mce-responses" class="clear">
<div class="response" id="mce-error-response" style="display:none"></div>
<div class="response" id="mce-success-response" style="display:none"></div>
</div> <!-- real people should not fill this in and expect good things - do not remove this or risk form bot signups-->
<div style="position: absolute; left: -5000px;" aria-hidden="true"><input type="text" name="b_02674ee40d31529a370700212_e3a0ed705f" tabindex="-1" value=""></div>
<div class="clear"><input type="submit" value="Subscribe" name="subscribe" id="mc-embedded-subscribe" class="button"></div>
</form>
Text Content
Distributional Control Menu * Documentation * GitHub * DISTRIBUTIONAL CONTROL 🕺🏽 disco allows you to flexibly control the generation from language models and other generative models. Get it with pip install disco-generation. Try it now! Subscribe to updates example.py | constrain GPT-2 to always include "amazing" # load a language model distribution = LMDistribution("gpt2") # define the feature we want to control for: # "amazing" appears in the generated text amazing = BooleanScorer(lambda s, c: "amazing" in s.text) # define our target distribution: # the feature amazing should appear 100% of the time target = base.constrain([amazing], [1.0]) # create a model to fine-tune model = LMDistribution("gpt2", freeze=False) # fine-tune the model to approximate the target distribution tuner = DPGTuner(model, target) tuner.tune() # generate amazing texts samples, log_scores = model.sample() for s in samples: print(s.text) © Naver Labs Europe 2021. All Rights Reserved. SUBSCRIBE * indicates required Email Address * First Name Last Name