Update README.md

README.md

@@ -1,22 +1,14 @@
 This model was trained as part of a series of experiments testing the performance of pure DPO vs SFT vs ORPO, all supported by Unsloth/Huggingface TRL.
 
-Rank: 8
-
-Alpha: 16
-
-Learning rate: 5e-6
-
-Beta: 0.1
-
-Batch size: 8
-
+Dataset: https://huggingface.co/datasets/argilla/dpo-mix-7k 
+Rank: 8 
+Alpha: 16 
+Learning rate: 5e-6 
+Beta: 0.1 
+Batch size: 8 
 Epochs: 1
-
-Learning rate schedulers: Linear
-
-Prompt Format: 
-
-```You are a helpful assistant.<s>[INST] PROMPT [/INST]RESPONSE</s>```
+Learning rate scheduler: Linear
+Prompt Format: ```You are a helpful assistant.<s>[INST] PROMPT [/INST]RESPONSE</s>```
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65a5c0e82823ba72ed2cee7d/Tg3dknWsTvfqM96Fab2YJ.png)