Skip to content

Commit

Permalink
update page
Browse files Browse the repository at this point in the history
  • Loading branch information
@btyu
btyu committed Feb 14, 2024
1 parent 07aa8ce commit dab3c33
Show file tree
Hide file tree
Showing 2 changed files with 121 additions and 70 deletions.
172 changes: 111 additions & 61 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script src="https://kit.fontawesome.com/f8ddf9854a.js" crossorigin="anonymous"></script>
<meta charset="utf-8">
<meta http-equiv="refresh" content="60"> <!-- TODO remove before production -->
<meta name="description" content="TODO">
<meta name="keywords"
content="Organic Chemistry, Small Molecules, Chemistry, Large Language Model, Large Multimodal Model, artificial intelligence, AI">
Expand Down Expand Up @@ -101,7 +100,8 @@
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title is-bold">
<img src="static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" />
<img src="static/images/llasmol.svg" style="width:2em;vertical-align: middle" alt="Logo" />
<p></p>
<span class="mmmu" style="vertical-align: middle">LlaSMol</span>
</h1>
<h2 class="subtitle is-3 publication-subtitle">
Expand Down Expand Up @@ -153,7 +153,7 @@ <h2 class="subtitle is-3 publication-subtitle">
</a>
</span>
<span class="link-block">
<a href="https://huggingface.co/datasets/osunlp/Mind2Web" target="_blank"
<a href="https://huggingface.co/datasets/osunlp/SMolInstruct" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<!-- <i class="far fa-images"></i> -->
Expand All @@ -164,7 +164,18 @@ <h2 class="subtitle is-3 publication-subtitle">
</a>
</span>
<span class="link-block">
<a href="https://github.com/OSU-NLP-Group/SeeAct" target="_blank"
<a href="https://huggingface.co/osunlp/LlaSMol-Mistral-7B" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<!-- <i class="far fa-images"></i> -->
<p style="font-size:18px">🤗</p>
<!-- 🔗 -->
</span>
<span>Model</span>
</a>
</span>
<span class="link-block">
<a href="https://github.com/OSU-NLP-Group/LlaSMol" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
Expand Down Expand Up @@ -199,16 +210,16 @@ <h2 class="subtitle is-3 publication-subtitle">
<!-- </a>-->
<!-- </span>-->
<!-- Twitter Link. -->
<span class="link-block">
<a href="https://twitter.com/ysu_nlp/status/1742398541660639637" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon has-text-white">
<i class="fa-brands fa-x-twitter"></i>
<!-- <span class="link-block"> -->
<!-- <a href="https://twitter.com/ysu_nlp/status/1742398541660639637" target="_blank" -->
<!-- class="external-link button is-normal is-rounded is-dark"> -->
<!-- <span class="icon has-text-white"> -->
<!-- <i class="fa-brands fa-x-twitter"></i> -->
<!-- <p style="font-size:18px">🌐</p> -->
</span>
<span>Twitter</span>
</a>
</span>
<!-- </span> -->
<!-- <span>Twitter</span> -->
<!-- </a> -->
<!-- </span> -->
</div>
</div>
</div>
Expand Down Expand Up @@ -243,7 +254,7 @@ <h2 class="subtitle is-3 publication-subtitle">
for training and evaluating LLMs for chemistry. Based on SMolInstruct, we
fine-tune a set of open-source LLMs, among which, we find that Mistral serves as
the best base model for chemistry tasks. We further conduct analysis on the impact
of trainable parameters, providing insights for future research
of trainable parameters, providing insights for future research.
</p>

</div>
Expand All @@ -255,8 +266,8 @@ <h2 class="subtitle is-3 publication-subtitle">
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<img src="/static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" />
<span class="mmmu" style="vertical-align: middle">Tasks</span>
<!-- <img src="/static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" /> -->
<span class="mmmu" style="vertical-align: middle">The SMolInstruct Dataset</span>
</h1>
</div>
</section>
Expand All @@ -265,17 +276,34 @@ <h1 class="title is-1 mmmu">
<div class="container">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">SMolInstruct Dataset</h2>
<!-- <h2 class="title is-3">Overview of SMolInstruct</h2> -->
<div class="content has-text-justified">
<p>
LlaSMol models are fine-tuned on SMolInstruct,
a dataset containing 14 meticulously selected chemistry
tasks and <strong>over 3 million</strong> high-quality
samples.
SMolInstruct is an instruction dataset for chemistry that focuses on small molecules.
It contains <strong>14 meticulously selected tasks</strong> and <strong>over 3M carefully curated samples</strong>.
The following image illustrates the tasks and corresponding samples.
</p>
<div class="content has-text-centered">
<img src="static/images/ChemLLMFig.svg" alt="14 tasks" class="center" style="width: 100%; height: auto;">
</div>
<p>
<strong>The merits of SMolInstruct</strong>:
</p>
<p>
(1) <strong>Large-Scale</strong>. SMolInstruct consists of 3.4M distinct samples and 1.6M distinct molecules,
with a diverse range of sizes, structures, and properties, showcasing an
extensive coverage of diverse chemical knowledge.
</p>
<p>
(2) <strong>Comprehensive</strong>. SMolInstruct contains 4 types of chemical tasks (14 tasks in total), emerging
as the most comprehensive instruction tuning dataset for small molecules. Notably, the tasks are
meticulously selected to build a strong chemistry foundation.
</p>
<p>
(3) <strong>High-Quality</strong>. Rigorous processing steps have been implemented to exclude problematic and low-
quality samples. Along with careful data splitting and canonicalization of SMILES representations
SMolInstruct stands as a high-quality resource valuable for future research.
</p>
</div>
</div>
</div>
Expand All @@ -287,8 +315,8 @@ <h2 class="title is-3">SMolInstruct Dataset</h2>
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<img src="static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" />
<span class="mmmu" style="vertical-align: middle">Experiments and Results</span>
<!-- <img src="static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" /> -->
<span class="mmmu" style="vertical-align: middle">The LlaSMol Models</span>
</h1>
</div>
</section>
Expand All @@ -297,47 +325,60 @@ <h1 class="title is-1 mmmu">
<div class="container">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3"></h2>
<!-- <h2 class="title is-3">Overview of SMolInstruct</h2> -->
<div class="content has-text-justified">
<div id="results-carousel" class="carousel results-carousel">
<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/tables/o_1.png" alt="TODO" width="80%" />
<p> TODO: description </p>
</div>
</div>

<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/tables/o_2.png" alt="TODO" width="80%" />
<p> TODO: descsription </p>
</div>
</div>
<p>
LlaSMol are a series of LLMs built for conducting various chemistry tasks.
Specifically, we use Galactica, Llama 2, Code Llama, and Mistral as the base models, and conduct instruction tuning with LoRA
on our SMolInstruct dataset. The resulting models are named as <strong>LlaSMol<sub>Galactica</sub></strong>,
<strong>LlaSMol<sub>Llama 2</sub></strong>, <strong>LlaSMol<sub>Code Llama</sub></strong>, <strong>LlaSMol<sub>Mistral</sub></strong>,
respectively.
</p>
</div>
</div>
</div>
</div>
</section>

<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/element_grounding_examples/example_image_annotation.svg"
alt="algebraic reasoning" width="50%" />
<p> An example of grounding via image annotation.</p>
</div>
</div>

<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/element_grounding_examples/example_element_attributes_1.svg"
alt="algebraic reasoning" width="50%" />
<p> An example of action generation in grounding via element attributes.</p>
</div>
</div>
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<!-- <img src="/static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" /> -->
<span class="mmmu" style="vertical-align: middle">Experiment</span>
</h1>
</div>
</section>

<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/element_grounding_examples/example_element_attributes_2.svg"
alt="algebraic reasoning" width="50%" />
<p> An example of grounding via element attributes after action generation. </p>
</div>
</div>
</div>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<!-- <h2 class="title is-3">Overview of SMolInstruct</h2> -->
<div class="content has-text-justified">
<p>
We comprehensively compare our LlasMol models with existing LLMs as well as the task-specific, non-LLM based SoTA models.
The main results are shown in the following tables.
</p>
</div>
<div class="content has-text-centered">
<p style="text-align:left;font-size:15px"> Results for name conversion (NC) and property prediction (PP) tasks. The metrics include exact match (EM), validity (Valid),
root mean square error (RMSE), and accuracy (Acc), where EM and Valid are in percentage. </p>
<img src="static/images/tables/o_1.png" alt="TODO" width="100%" />
<p></p>
<p style="text-align:left;font-size:15px"> Results for molecule captioning (MC), molecule generation (MG), forward synthesis (FS), and retrosynthesis (RS).
The metrics include METEOR score (METEOR), exact match (EM), Morgan fingerprint-based tanimoto similarity (FTS), and validity (Valid),
where EM, FTS, and Valid are in percentage. </p>
<img src="static/images/tables/o_2.png" alt="TODO" width="100%" />
<p></p>
<p style="text-align:left"><strong>Main takeaways:</strong></p>
<p style="text-align:left">(1) LlaSMol models significantly outperform the existing LLMs on all the tasks,
underscoring the effectiveness of the proposed SMolInstruct dataset and the benefits of fine-
tuning.</p>
<p style="text-align:left">(2) Our four LlaSMol models show substantial differences in their performance, and LlasMol<sub>Mistral</sub> achieves the best, emphasizing
the significant impact of base models on downstream tasks</p>
<p style="text-align:left">(3) Our LlaSMol models exhibit comparable performance to SoTA models even with only a small proportion of parameters being tuned (40M, 0.59%),
showing great potential to surpass task-specific models and work as universal models capable of addressing multiple chemistry tasks.</p>
</div>
</div>
</div>
Expand All @@ -346,9 +387,18 @@ <h2 class="title is-3"></h2>


<!-- @Botao TODO: update bibtex -->
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<!-- <img src="/static/images/llasmol.svg" style="width:1em;vertical-align: middle" alt="Logo" /> -->
<span class="mmmu" style="vertical-align: middle">Citation</span>
</h1>
</div>
</section>
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title is-3 has-text-centered">BibTeX</h2>
<!-- <h2 class="title is-3 has-text-centered">Citation</h2> -->
<p>If our paper or related resources prove valuable to your research, we kindly ask for citation. Please feel free to contact us with any inquiries.</p>
<pre><code>
@article{yu2024llasmol,
title={LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset},
Expand Down
19 changes: 10 additions & 9 deletions static/images/llasmol.svg
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit dab3c33

Please sign in to comment.