Update README.md

README.md

@@ -4,6 +4,8 @@ language:
 - ko
 library_name: transformers
 pipeline_tag: text-generation
+datasets:
+- maywell/ko_Ultrafeedback_binarized
 ---
 **Model Name**
 - Open_Ko_SOLAR_DPO_Merge_v0.1
@@ -14,6 +16,10 @@ pipeline_tag: text-generation
 **Training Corpus**
 - [maywell/ko_Ultrafeedback_binarized](https://huggingface.co/datasets/maywell/ko_Ultrafeedback_binarized)
 
+**Explanation**
+- With base model, apply DPO to the small amount of layers with the dataset written above, saved just an adapter part.
+- Merge the base model and the tuned adapter together.
+
 **Log**
 - 2024.01.25: Initial version Upload
 
@@ -33,4 +39,16 @@ pipeline_tag: text-generation
   
   ```
 
-**Acknowledgements**
+**Model**
+``` python
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+model = AutoModelForCausalLM.from_pretrained(
+        "dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1",
+        low_cpu_mem_usage = True,
+        torch_dtype = torch.float16,
+        device_map = device_map,
+    )
+
+tokenizer = AutoTokenizer.from_pretrained("dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1")
+
+```