liberal commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -327,5 +327,7 @@ Training Scope Only LoRA weights updated; main model remains fixed
|
|
| 327 |
|
| 328 |
This approach enables self-corrective, explainable, and meta-aware learning, pushing beyond standard RLHF and toward autonomous reasoning agents.
|
| 329 |
|
| 330 |
-
|
|
|
|
|
|
|
| 331 |
|
|
|
|
| 327 |
|
| 328 |
This approach enables self-corrective, explainable, and meta-aware learning, pushing beyond standard RLHF and toward autonomous reasoning agents.
|
| 329 |
|
| 330 |
+
<p align="center">
|
| 331 |
+
<img src="https://huggingface.co/liberalusa/liberalmind_bin/resolve/main/kl_critic_plot.png" width="600"/>
|
| 332 |
+
</p>
|
| 333 |
|