Update README.md

README.md

@@ -1,5 +1,13 @@
+---
+datasets:
+- sean0042/KorMedMCQA
+language:
+- ko
+- en
+pipeline_tag: text-generation
+---
 ### Model Card for Model ID
-base_model : [Ko-Llama3-Luxia-8B](https://huggingface.co/saltlux/Ko-Llama3-Luxia-8B)
+base_model : [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it)
 
 ### Basic usage
 ```python
@@ -22,21 +30,24 @@ print(tokenizer.decode(outputs[0]))
 ```
 
 ### Training dataset
-dataset : [kyujinpy/KOpen-platypus](https://huggingface.co/datasets/kyujinpy/KOpen-platypus)
+dataset : [sean0042/KorMedMCQA](https://huggingface.co/datasets/sean0042/KorMedMCQA)
 
 ### lora_config and bnb_config in Training
 ```python
 bnd_config = BitsAndBytesConfig(
-  load_in_4bit = True
+  load_in_4bit = True,
+  bnb_4bit_use_double_quant = True,
+  bnb_4bit_quant_type = 'nf4',
+  bnb_4bit_compute_dtype = torch.bfloat16
 )
 
 lora_config = LoraConfig(
-  r = 16,
-  lora_alpha = 16,
+  r = 32,
+  lora_alpha = 32,
   lora_dropout = 0.05,
-  target_modules = ['gate_proj', 'up_proj', 'down_proj']
+  target_modules = ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']
 )
 ```
 
 ### Hardware
-RTX 3090 Ti 24GB x 1
+A100 40GB x 1