Update README.md

README.md

@@ -2,17 +2,16 @@
 library_name: transformers
 tags: []
 ---
+# Mistral 7b Self-Alignment DPO Model
 
-# Mistral 7b Self-Alignment SFT Model
+The Mistral 7b Self-Alignment DPO Model is an adapter fine-tuned for self-alignment and harmlessness using the Direct Preference Optimization (DPO) technique. It has been trained utilizing the Mistral Self-Alignment Preference Dataset, accessible [here](https://huggingface.co/datasets/August4293/Preference-Dataset).
 
-The Mistral 7b Self-Alignment SFT Model is an adapter fine-tuned specifically for self-alignment and harmlessness. It has been trained using the Mistral Self-Alignment Preference Dataset, which can be accessed [here](https://huggingface.co/datasets/August4293/Preference-Dataset). 
-
-The fine-tuning process is detailed on the corresponding [GitHub page](https://github.com/August-murr/Lab/tree/main/Mistral%20Self%20Alignment), providing insights into the methodology and purpose behind the model's adaptation.
+Detailed information about the DPO fine-tuning process and its application for self-alignment can be found on the corresponding [GitHub page](https://github.com/August-murr/Lab/tree/main/Mistral%20Self%20Alignment).
 
 ## Model Details:
 - **Base Model:** Mistral 7b
 - **Fine-Tuning Purpose:** Self-Alignment and Harmlessness
-- **Fine-Tuning Dataset:** Mistral Self-Alignment Preference Dataset
-
+- **Fine-Tuning Method:** Direct Preference Optimization (DPO)
+- **Fine-Tuning Dataset:** [Mistral Self-Alignment Preference Dataset](https://huggingface.co/datasets/August4293/Preference-Dataset)