enkryptai
/

DeepSeek-R1-Distill-Llama-8B-Enkrypt-Aligned

Model card Files Files and versions Community

NitinBirur commited on 10 days ago

Commit

d4a4b84

·

verified ·

1 Parent(s): 1cbcf94

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ This alignment significantly **reduces toxicity, harmfulness, and jailbreak vuln
 ## Red Team Results
-TBD
-## Performance
 | Model | MMLU-Pro Score |
 |--------|----------------|
 | DeepSeek-R1-Distill-Llama-8B (Base) | **44.71** |
@@ -26,7 +26,7 @@ TBD
 ## Training Configuration
-The model was trained using the **SimPO (Simple Policy Optimization)** approach with the following hyperparameters:
 ```yaml
 cpo_config:

 ## Red Team Results
+![Safety Comparison](assets/safety_comparison.png)
+## Performance Results
 | Model | MMLU-Pro Score |
 |--------|----------------|
 | DeepSeek-R1-Distill-Llama-8B (Base) | **44.71** |
 ## Training Configuration
+The model was trained using the **SimPO (Simple Preference Optimization)** approach with the following hyperparameters:
 ```yaml
 cpo_config: