Jayant-Kernel commited on
Commit Β·
4520926
1
Parent(s): 4f7ce24
update: add YouTube video link
Browse files
README.md
CHANGED
|
@@ -1,10 +1,3 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: DECEIT
|
| 3 |
-
colorFrom: red
|
| 4 |
-
colorTo: purple
|
| 5 |
-
sdk: docker
|
| 6 |
-
pinned: false
|
| 7 |
-
---
|
| 8 |
|
| 9 |
# DECEIT π β An RL Environment for Training Honest LLMs
|
| 10 |
|
|
@@ -27,7 +20,7 @@ pinned: false
|
|
| 27 |
| π» GitHub Repo | https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment- |
|
| 28 |
| π Training Logs W&B | https://wandb.ai/jayantmcom-polaris-school-of-technol/deceit-full |
|
| 29 |
| π Training Notebook | https://colab.research.google.com/github/Jayant-kernel/DECEIT-the-ai-truth-environment-/blob/main/training/sanity_run.ipynb |
|
| 30 |
-
| π₯ Video |
|
| 31 |
|
| 32 |
## The Problem
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
# DECEIT π β An RL Environment for Training Honest LLMs
|
| 3 |
|
|
|
|
| 20 |
| π» GitHub Repo | https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment- |
|
| 21 |
| π Training Logs W&B | https://wandb.ai/jayantmcom-polaris-school-of-technol/deceit-full |
|
| 22 |
| π Training Notebook | https://colab.research.google.com/github/Jayant-kernel/DECEIT-the-ai-truth-environment-/blob/main/training/sanity_run.ipynb |
|
| 23 |
+
| π₯ Video | https://www.youtube.com/watch?v=_VGFpqI5uKc |
|
| 24 |
|
| 25 |
## The Problem
|
| 26 |
|