Create README.md

README.md

@@ -0,0 +1,45 @@
+### Model Card for Model ID
+base_model : [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it)
+
+### Basic usage
+```python
+# pip install accelerate
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("MDDDDR/gemma-7b-it-v0.1")
+model = AutoModelForCausalLM.from_pretrained(
+    "MDDDDR/gemma-7b-it-v0.1",
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+)
+
+input_text = "사과가 뭐야?"
+input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
+
+outputs = model.generate(**input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+### Training dataset
+dataset : [sean0042/KorMedMCQA](https://huggingface.co/datasets/sean0042/KorMedMCQA)
+
+### lora_config and bnb_config in Training
+```python
+bnd_config = BitsAndBytesConfig(
+  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 = 32,
+  lora_alpha = 32,
+  lora_dropout = 0.05,
+  target_modules = ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']
+)
+```
+
+### Hardware
+A100 40GB x 1