Skip to content

resources.md

Latest commit

 

History

History
357 lines (345 loc) · 19.6 KB

resources.md

File metadata and controls

357 lines (345 loc) · 19.6 KB
Raw
layout page
title Resources
description Access essential resources for the LLM Hackathon, including datasets, and documentation to help you succeed in your projects.
keywords Hackathon Resources, LLM Tools, Datasets, AI Documentation, Materials Science Resources, Chemistry Resources

Welcome to your curated resource list for the hackathon. This guide provides a starting point for learning key techniques, finding datasets, and exploring the essential tools and research papers at the intersection of Large Language Models (LLMs), materials science, and chemistry.

Tutorials & Learning Resources

Foundational LLM Concepts

Intro to Large Language Models

A general-audience overview of how LLMs are trained and the key concepts behind their operation, including pre-training, fine-tuning, and RLHF.

Let's build GPT: from scratch, in code, spelled out

A deep, code-first dive into the Transformer architecture that powers models like GPT.

LLM Course on GitHub

A comprehensive course covering LLM fundamentals, the science of building LLMs, and the engineering of LLM-based applications.

<h3>Library-Specific Tutorials</h3>
<div class="resource-grid">
    <div class="resource-card">
        <h4>RDKit</h4>
        <p>RDKit is a collection of cheminformatics and machine-learning software written in C++ and Python.</p>
        <p><b>Official Documentation:</b> The "Getting Started with the RDKit in Python" guide is the best
            place to begin.
            <a href="https://www.rdkit.org/docs/GettingStartedInPython.html" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
        <p><b>YouTube Tutorial:</b> Video tutorial by <a
                href="https://scholar.google.com/citations?user=lOz-SVQAAAAJ&hl=en">Jan Jensen</a> is
            another great resource to start with. <a
                href="https://www.youtube.com/playlist?list=PLzfVULc1l7TdDSIfgDm12v21Y8jG_B6uh"
                target="_blank" rel="noopener" aria-label="external-link"><i
                    class="fas fa-external-link-alt"></i></a></p>
    </div>
    <div class="resource-card">
        <h4>PySCF</h4>
        <p>The Python-based Simulations of Chemistry Framework (PySCF) is an open-source library for quantum
            chemistry calculations. It is highly extensible and designed for simplicity, both for users and
            developers.</p>
        <p><b>Official Documentation:</b> The 'User Guide' and 'Tutorials' are great starting points.
            <a href="https://pyscf.org/" target="_blank" rel="noopener" aria-label="external-link"><i
                    class="fas fa-external-link-alt"></i></a>
        </p>
    </div>
    <div class="resource-card">
        <h4>Atomic Simulation Environment (ASE)</h4>
        <p>The Atomic Simulation Environment (ASE) is a set of tools and Python modules for setting up,
            manipulating, running, visualizing and analyzing atomistic simulations.</p>
        <p><b>Official Documentation:</b> The 'ASE Tutorials' is the best place to begin with.
            <a href="https://wiki.fysik.dtu.dk/ase/tutorials/tutorials.html" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
    </div>
    <div class="resource-card">
        <h4>Pymatgen</h4>
        <p>Pymatgen (Python Materials Genomics) is a robust, open-source Python library for materials
            analysis.</p>
        <p><b>Official Documentation:</b> The pymatgen API Documentation is the best place to begin with.
            <a href="https://pymatgen.org/pymatgen.html" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
        <p><b>YouTube Tutorial:</b> Video tutorial by <a
                href="https://scholar.google.com/citations?user=IKUUbNwAAAAJ&hl=en">Anubhav Jain</a>,
            developer of pymatgen, is
            another great resource to start with. <a
                href="https://www.youtube.com/playlist?list=PL7gkuUui8u7_M47KrV4tS4pLwhe7mDAjT"
                target="_blank" rel="noopener" aria-label="external-link"><i
                    class="fas fa-external-link-alt"></i></a></p>
    </div>
    <div class="resource-card">
        <h4>LangChain</h4>
        <p>LangChain is an open-source library specifically designed for creating applications using large
            language models (LLMs).</p>
        <p>
            <b>Official Documentation:</b> The best place to begin is the official LangChain documentation.
            It offers a comprehensive overview of the framework, from installation to advanced use cases.
            <a href="https://python.langchain.com/docs/introduction/" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
        <p>
            <b>YouTube Tutorial:</b> For visual learners, <b>aiwithbrandon</b> YouTube channel provides a
            wealth of tutorials. The "LangChain Master Class For Beginners 2024" video is an excellent starting point.
            <a href="https://youtu.be/yF9kGESAi3M?si=HA8392wjKJBhMigS" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
    </div>
    <div class="resource-card">
        <h4>LangGraph</h4>
        <p>LangGraph, created by LangChain, is an open source AI agent framework designed to build, deploy
            and manage complex generative AI agent workflows.</p>
        <p>
            <b>Official Documentation:</b> To dive into building stateful, multi-actor applications, the
            LangGraph documentation is your go-to resource.
            <a href="https://langchain-ai.github.io/langgraph/" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
        <p>
            <b>YouTube Tutorial:</b> A great video tutorial by LangChain on "Building Effective Agents with
            LangGraph" provides a practical introduction to creating sophisticated agents.
            <a href="https://youtu.be/aHCDrAbH_go?si=8vfcsHGY8befW8vk" target="_blank" rel="noopener"
                aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
        </p>
    </div>
</div>

<h3>Technique-Specific Guides</h3>
<div class="resource-grid">
    <div class="resource-card">
        <h4>Fine-Tuning LLMs</h4>
        <p>Fine-tuning allows you to adapt pre-trained models to specific tasks or domains, making them more effective for specialized applications in materials science and chemistry.</p>
        <a href="https://huggingface.co/docs/transformers/training" target="_blank" rel="noopener"
            aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
    </div>
    <div class="resource-card">
        <h4>Retrieval-Augmented Generation (RAG)</h4>
        <p>RAG combines the power of retrieval systems with language generation, allowing LLMs to access and use external knowledge bases effectively.</p>
        <a href="https://python.langchain.com/docs/tutorials/rag/" target="_blank" rel="noopener"
            aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
    </div>
    <div class="resource-card">
        <h4>Prompt Engineering</h4>
        <p>Learn how to craft effective prompts to get the best results from language models in scientific applications.</p>
        <a href="https://www.promptingguide.ai/" target="_blank" rel="noopener"
            aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
    </div>
</div>

<h3>Materials Science & Chemistry Datasets</h3>
<div class="resource-grid">
    <div class="resource-card">
        <h4>Materials Science Datasets Compilation</h4>
        <p>A curated list of awesome materials and chemistry datasets by <a
                href="https://scholar.google.com/citations?user=J-x5n7IAAAAJ&hl=en" rel="noopener">Ben
                Blaiszik</a>.</p>
        <a href="https://github.com/blaiszik/awesome-matchem-datasets" target="_blank" rel="noopener"
            aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
    </div>
</div>

<h3>General Datasets</h3>
<div class="resource-grid">
    <div class="resource-card">
        <h4>arXiv Preprints</h4>
        <p>The entire collection of preprints from arXiv is available for bulk download, providing a massive
            corpus for text mining the latest scientific research.</p>
        <a href="https://arxiv.org/" target="_blank" rel="noopener" aria-label="external-link"><i
                class="fas fa-external-link-alt"></i></a>
    </div>
    <div class="resource-card">
        <h4>Hugging Face Datasets</h4>
        <p>A central hub for thousands of datasets, including a growing number for materials science and
            chemistry.</p>
        <a href="https://huggingface.co/datasets" target="_blank" rel="noopener"
            aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
    </div>
    <div class="resource-card">
        <h4>Kaggle Datasets</h4>
        <p>A platform hosting a wide variety of public datasets, including many relevant to chemistry and
            materials science.</p>
        <a href="https://www.kaggle.com/datasets" target="_blank" rel="noopener"
            aria-label="external-link"><i class="fas fa-external-link-alt"></i></a>
    </div>
</div>

Key Research Papers & Reviews

Examples & Reviews on LLMs in Materials & Chemistry

Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

In the 2nd global hackathon for LLMs applications for materials and chemistry 34 teams used large language models to create applications for materials science and chemistry research across seven different areas like property prediction, molecular design, and scientific communication.

14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon

In the 1st global hackathon for LLMs applications for materials and chemistry participants used large language models like GPT-4 to build working prototypes for chemistry and materials science applications in just two days.

A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools

A comprehensive review on how large AI foundation models (like ChatGPT-style systems) are being used to accelerate materials science research across six key areas from data analysis to discovering new materials.

A review of large language models and autonomous agents in chemistry

The authors reviewed how large language models and AI agents are being used in chemistry for tasks like molecule design and laboratory automation, and created a repository to track ongoing research in this rapidly evolving field.

General Tools

🎬 Slide Design + MVP Recording

<h3>🌀 Website Builder + Landing Page Mockup</h3>
<div class="resource-grid general-tools-grid">
    <a href="https://www.wix.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Wix</h4>
    </a>
    <a href="https://www.weebly.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Weebly</h4>
    </a>
    <a href="https://www.squarespace.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Squarespace</h4>
    </a>
    <a href="https://canva.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Canva</h4>
    </a>
</div>

<h3>💻 No Code MVP + Prototyping Tools</h3>
<div class="resource-grid general-tools-grid">
    <a href="https://www.moqups.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Moqups</h4>
    </a>
    <a href="https://www.marvelapp.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Marvel Apps</h4>
    </a>
    <a href="https://www.origami.design/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Origami</h4>
    </a>
    <a href="https://www.invisionapp.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>InVision</h4>
    </a>
    <a href="https://www.framer.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Framer</h4>
    </a>
</div>

<h3>🎨 Design + Artwork + Creative Tools</h3>
<div class="resource-grid general-tools-grid">
    <a href="https://www.unsplash.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Unsplash</h4>
    </a>
    <a href="https://www.thenounproject.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Noun Project</h4>
    </a>
    <a href="https://www.icons8.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Icons8</h4>
    </a>
    <a href="https://www.feathericons.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Feather Icons</h4>
    </a>
    <a href="https://www.freepik.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>FreePik</h4>
    </a>
    <a href="https://www.undraw.co/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Undraw</h4>
    </a>
    <a href="https://www.artboard.studio/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Artboard.Studio</h4>
    </a>
</div>

<h3>✏️ Marketing Copy</h3>
<div class="resource-grid general-tools-grid">
    <a href="https://www.goodemailcopy.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>Good Email Copy</h4>
    </a>
    <a href="https://www.copy.ai/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>CopyAI</h4>
    </a>
    <a href="https://www.reallygoodemails.com/" target="_blank" rel="noopener" aria-label="external-link"
        class="resource-card resource-card-general">
        <h4>ReallyGoodEmails</h4>
    </a>
</div>