Update README.md

README.md

@@ -189,9 +189,6 @@ https://huggingface.co/datasets/won75/text_to_sql_ko
 
 https://github.com/100suping/train_with_unsloth
 
-```
-
-```
 
 ### Preprocess Functions
 
@@ -247,6 +244,29 @@ def formatting_prompts_func(examples):
   - CPU 16 vCore
   - Memory 192 GiB
   - Storage 100 GiB
+- **Memory-Used(GPU VRAM):** ~60GB
+
+## For Continuous Instruction-tuning
+
+To use this LoRA adapter, refer to the following code:
+
+```
+from peft import PeftModel
+
+bnb_config = get_bnb_config(bit=bit)
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_name,
+    dtype=None,
+    quantization_config=bnb_config,
+)
+
+model = PeftModel.from_pretrained(model, adapter_path, is_trainable=True)
+model = FastLanguageModel.patch_peft_model(model, use_gradient_checkpointing="unsloth")
+
+model.print_trainable_parameters()
+```
+
 
 ## Citation [optional]
 
@@ -267,13 +287,10 @@ def formatting_prompts_func(examples):
 }
 ```
 
-## Model Card Authors [optional]
+## Model Card Authors
 
 joonavel[https://github.com/joonavel] from 100suping [https://github.com/100suping]
 
-## Model Card Contact
-
-[More Information Needed]
 ### Framework versions
 
 - PEFT 0.13.2