title | menu_title | menu_icon |
---|---|---|
Hackathon resources |
Resources |
journal-code |
-
Langchain demo - an overview of the capabilities of LangChain.
{% include youtube.html video="zaYTXQFR0_s" title="" %}
Huggingface walkthrough -- very quick overview of the most important functionalities of HuggingFace
{% include youtube.html video="QEaBAZQCtwE" title="" %}
-
## Project inspirations
Paper QA -- doing question and answering from PDFs or text files (e.g. papers)
<script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>I packed-up a full-text paper scraper, vector database, and LLM into a CLI to answer questions from only highly-cited peer-reviewed papers. Feels unreal to be able instantly get answers by an LLM "reading" dozens of papers. 1/2 pic.twitter.com/a6PWxWyuc1
— Andrew White ⏣🧪 (@andrewwhite01) February 25, 2023Few-shot predictions for chemistry using GPT-4 -- A very interesting recent finding is that LLMs can give surprisingly good predictions on chemistry examples without any training, only with a few examples in the prompt.
<script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>One of my favorite examples in our preprint (https://t.co/ojby0bSaoj) with @SmitBerend and @pschwllr and @aortegaguerrerowas about photoswitches curated by @Ryan__Rhys.
— Kevin Jablonka (@kmjablonka) March 15, 2023
I now asked #GPT-4 a few questions about it. pic.twitter.com/O7O1078mibMARVIS --- Text/Voice-control for VMD.
<script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>Here's a text demo of Marvis from @glenhocky and me. Info: https://t.co/DQLKYpwZsX Code: https://t.co/LjzwjS4zR9 pic.twitter.com/wn3PNBrpmb
— Andrew White ⏣🧪 (@andrewwhite01) May 12, 2021 -
## Guidelines
Submission - The hackathon's workflow for submissions