Update README.md

README.md

@@ -208,10 +208,10 @@ Several issues were observed during initial evaluations:
 Amongst all tested models 'Command r plus' showed highest precision especially noted for its critical analysis capabilities and adherence to structured prompts.
 
 **4.Model Training & Results:**
-The final model was developed using full DPO finetune technique on VAGOsolutions/SauerkrautLM-1.5b which is based on qwen2 architecture achieving an impressive accuracy rate close approximating that seen with ‘Command r plus’. 
+The final model was developed using full ORPO finetune technique on VAGOsolutions/SauerkrautLM-1.5b which is based on qwen2 architecture achieving an impressive accuracy rate close approximating that seen with ‘Command r plus’. 
 
 Training specifics included:
-   * Dataset size : 250k unique entries
+   * Dataset size : 500k unique entries
    * Epochs : One 
    * Batch Size : 64