Update README.md

README.md

@@ -6,10 +6,37 @@ language:
 - en
 pipeline_tag: text-generation
 ---
-# Model Card for Model ID
+
+### Model Card for Model ID
 base_model : [Ko-Llama3-Luxia-8B](https://huggingface.co/saltlux/Ko-Llama3-Luxia-8B)
 
-# Model Evaluation
+### Basic usage
+```python
+# pip install accelerate
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("MDDDDR/Ko-Luxia-8B-it-v0.3")
+model = AutoModelForCausalLM.from_pretrained(
+    "MDDDDR/Ko-Luxia-8B-it-v0.3",
+    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 : [kyujinpy/KOpen-platypus](https://huggingface.co/datasets/kyujinpy/KOpen-platypus)
+
+### Hardware
+RTX 3090 Ti 24GB x 1
+
+### Model Benchmark Results
 |      Tasks      |Version|Filter|n-shot|  Metric   |   |Value |   |Stderr|
 |-----------------|-------|------|-----:|-----------|---|-----:|---|------|
 |kobest_boolq     |      1|none  |     0|acc        |↑  |0.5278|±  |0.0133|