Page History

Description

The predictive power of Large Language Models (LLMs) has increasingly made it a go-to method across the scientific domains. This presents scientists with new challenges and even greater opportunities as they explore various approaches and drive changes in data production, data usage, and scientific understanding. The workshop will focus on introductory hands-on tutorials for researchers of all backgrounds using LLMs and improving results by prompt engineering.

...

https://anu.zoom.us/meeting/register/tZEqdOyrrjkoHtQ7DqRokcsLITGNDoAVApZG

Before The Day

Complete the following steps BEFORE the tutorial

1. Setup NCI Account 

   if you don’t have one:

   1.                   Go to https://my.nci.org.au/mancini

   2.                   Click on the "Sign up" button to start your registration form.

   3.                   Complete all steps in the registration form. (Note: you must provide a current email address from your institution or place of work, not a personal email.)

   4.                   Select the option to join project vp91 at Step 3 of the form.

   5.                   Click "Finish" on the final page of the form to complete your registration request.

   or 

                apply to join project vp91:

   1.                   Login to your NCI account https://my.nci.org.au/mancini

   2.                   Select Project and Groups on the left-side menu

   3.                   Select Find project or group on the top tab and search vp91 to apply for membership

2. 🤗 Hugging Face: Account and Access Token

   Hugging Face Instructions
   • Sign up for a huggingface account and obtain an access token: https://huggingface.co
   • Sign Up (top bar) Log into huggingface and get an access token:
     • Login -> Settings (left pane) -> Access Tokens (left pane) -> New token (center pane)

1. 🦙 Request access to Llama-2 model

   Llama-2 Access Instructions
   • Visit this https://huggingface.co/meta-llama/Llama-2-7b-hf and request access to the model
   • vist meta website and accept the terms https://ai.meta.com/resources/models-and-libraries/llama-downloads/
   • Note: Your Hugging Face account email address MUST match the email you provide on the Meta website, or your request will not be approved.

More information coming soon.