Skip to content

Commit

Permalink
update research part
Browse files Browse the repository at this point in the history 
move inspired research out of research box
  • Loading branch information
@caris-mu
caris-mu committed Apr 17, 2024
1 parent 57769fb commit b585b67
Show file tree
Hide file tree
Showing 2 changed files with 12 additions and 32 deletions.
2 changes: 2 additions & 0 deletions assets/css/main.css
View file
Original file line number Diff line number Diff line change
Expand Up @@ -264,6 +264,8 @@ hr.major {
.row.gtr-uniform > * > :last-child {
margin-bottom: 0;}
.row.aln-left {
margin-top: -2.25em;
padding-top: 2.5em;
justify-content: flex-start; }
.row.aln-center {
justify-content: center; }
Expand Down
42 changes: 10 additions & 32 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -258,9 +258,8 @@ <h3 class="white">AmberSafe:</h3>
<h2>Research</h2>
</header>
<div class="box primary">
<div class="row gtr-150 gtr-uniform">
<div class="col-4 col-12-medium"> <!-- <div class="col-8 col-12-medium"> -->
<h3>LLM360 Paper</h3>
<div class="row aln-left">
<div class="col-5 col-12-medium">
<article>
<a class="image fit"><img src="images/llm360_paper.png" alt="" /></a>
<h4>LLM360: Towards Fully Transparent Open-Source LLMs</h4>
Expand All @@ -283,40 +282,19 @@ <h3>Crystal Paper</h3>
<li><a class="button3">Learn More</a></li>
</ul>
</article>
<article>
<a class="image fit"><img src="images/llm360_paper.png" alt="" /></a>
<h3>LLM360: Towards Fully Transparent Open-Source LLMs</h3>
<p>The recent surge in open-source Large Language Models (LLMs), such as LLaMA,
Falcon, and Mistral, provides diverse options for AI practitioners and researchers.
However, most LLMs have only released partial artifacts...</p>
<ul class="actions">
<li><a href="paper.html" target="_blank" class="button3">Learn More</a></li>
</ul>
</article>
</div>
</div>
</div>
<div class="col-4 col-12-medium">
<h3>Inspired Research</h3>
<!--
<div class="box alt">
<div class="posts">
-->
<article>
<a class="image fit"><img src="images/research_1.jpg" alt="" /></a>
<h4>Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models</h4>
<p>This paper explores the trustworthiness of large language models (LLMs) during pre-training, focusing on reliability, privacy, toxicity, fairness, and robustness using LLM360.</p>
<ul class="actions">
<li><a href="https://arxiv.org/pdf/2402.19465.pdf" target="_blank" rel="noopener" class="button3">Learn More</a></li>
</ul>
</article>
<!--
</div>
</div>
-->
</div>
</div>
</div>
<div style="margin: -2em 0 4em 0">
<header>
<h3>Inspired Research: </h3>
</header>
<!-- <a href="https://blog.eleuther.ai/fm-dev-cheatsheet/" target="_blank" class="image"><img src="images/research_1.jpg" alt="" /></a>-->
<a href="https://blog.eleuther.ai/fm-dev-cheatsheet/" target="_blank"><strong>EleutherAI:</strong> Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models</a>

</div>
</section>

<!-- Resources -->
Expand Down

0 comments on commit b585b67

Please sign in to comment.