Generative AI: 1. Ethics 2.CLIP: Difference between revisions
Jump to navigation
Jump to search
| Line 14: | Line 14: | ||
Paper reading. <br> | Paper reading. <br> | ||
Existing RLHF and RLAIF exploring. <br> | Existing RLHF and RLAIF exploring. <br> | ||
Red-teaming dataset exploring | Red-teaming dataset exploring. | ||
|- | |- | ||
| Line 50: | Line 50: | ||
!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 | Llama supervised model fine-tuning | ||
| | |||
|- | |- | ||
| Line 71: | Line 71: | ||
Re-formatting deontology dataset. <br> | Re-formatting deontology dataset. <br> | ||
Creation of the preference model. | Creation of the preference model. | ||
|- | |- | ||
Revision as of 21:35, 4 December 2023
Project Plan and Milestones
Weekly Plan
| Date | Task | Completion |
|---|---|---|
| Week 4 |
Paper reading. | |
| Week 5 |
Familiarizing with Dromedary, SALMON, Llama base models. | |
| Week 6 |
Evaluation of different base models. |
|
| Week 7 |
Red teaming dataset exploration. |
|
| 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 |
Read about Reinforcement learning using PPO. |
Re-formatting deontology dataset. |
| Week 12 | ||
| Week 13 | ||
| Week 14 | Write the Wikipedia page & Final presentation |
Milestone 1
- Choose the project subject.
- Read papers about the existing studies in this field.
- Define our research questions.
Milestone 2
- Refine our research questions.
- Explore different ethical theories.
- Find an appropriate dataset.
- Evaluate our fine-tuned supervised model.
Milestone 3
- Get our Preference and the Reinforcement learning models.
- Analyze the results.
- Write the Wikipedia page.