Update README.md

README.md

@@ -10,9 +10,9 @@ library_name: transformers
 inference: true
 ---
 
-# SAFEPATH-R-7B
+# SAFEPATH-R-8B
 
-This model is the **SAFEPATH-aligned version of DeepSeek-R1-Distill-Qwen-7B**, fine-tuned using prefix-only safety priming.
+This model is the **SAFEPATH-aligned version of DeepSeek-R1-Distill-Llama-8B**, fine-tuned using prefix-only safety priming.
 
 ## Model Description
 
@@ -20,7 +20,7 @@ SAFEPATH applies a minimal alignment technique by inserting the phrase: *Let's t
 
 - 🔐 **Improved Safety**: Reduces harmful outputs (e.g., StrongReject, BeaverTails) and is robust to jailbreak attacks
 - 🧠 **Preserved Reasoning**: Maintains accuracy on MATH500, GPQA, and AIME24
-- ⚡ **Efficiency**: Fine-tuned with only 100 steps
+- ⚡ **Efficiency**: Fine-tuned with only 20 steps
 
 ## Intended Use