Generative AI: 1. Ethics 2.CLIP: Difference between revisions

From FDHwiki
Jump to navigation Jump to search
Line 62: Line 62:


!scope="row"|Week 9
!scope="row"|Week 9
|
|
|
* ETHICS dataset formatting for Llama fine-tuning and evaluation.
* ETHICS dataset formatting for Llama fine-tuning and evaluation.
|
* Llama supervised model fine-tuning
|  
|  
*  
*  
Line 74: Line 75:
|
|
|
|
|
|  
| Mid-term Presentation & Start to write the Wikipedia page with the plan
* Evaluation of Llama model before and after fine-tuning with ETHICS dataset.
|  
* Mid-term Presentation & Start writing the Wikipedia page with the plan.
|-
|-



Revision as of 20:04, 1 December 2023

Project Plan and Milestones

Weekly Plan

Date Exploration Application Evaluation Report
Week 4
  • Paper reading
  • Existing RLHF and RLAIF exploring
  • Red-teaming dataset exploring
Week 5
  • Familiarizing with Dromedary, SALMON, Llama base models.
Week 6
  • Evaluation of different base models.
  • Choice of using Llama 2 model as our baseline.
Week 7
  • Red teaming dataset exploration.
  • Reading about ethical theories.
Week 8
  • ETHICS dataset discovering.
Week 9
  • ETHICS dataset formatting for Llama fine-tuning and evaluation.
  • Llama supervised model fine-tuning
Week 10
  • Evaluation of Llama model before and after fine-tuning with ETHICS dataset.
  • Mid-term Presentation & Start writing the Wikipedia page with the plan.
Week 11
Week 12
Week 13
Week 14 Write the Wikipedia page & Final presentation

Milestone 1

  • Read papers and define potential directions for our project.

Milestone 2

  • Understand different ethical theories.
  • Fine-tune supervised model

Milestone 3

  • Model Evaluation