Update README.md

README.md

@@ -22,7 +22,7 @@ pipeline_tag: text-generation
 This is a second RL fine tuned model of [Teknium](https://huggingface.co/teknium)'s [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) using the [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs) and [allenai/ultrafeedback_binarized_cleaned](https://huggingface.co/datasets/allenai/ultrafeedback_binarized_cleaned) preference datasets for reinforcement learning using Direct Preference Optimization (DPO)
 
 The difference between this model and the "v1" model is that the v1 model used argilla's version of the dataset that was not decontaminated of TruthfulQA data.
-DPOpenHermes is trained using LoRA.
+DPOpenHermes is trained using 16-bit LoRA.
 
 # Training Details