Update README.md

README.md

@@ -39,7 +39,7 @@ These are the merged version: after training the adapters, we merge the original
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 # model_name = "mistralai/Mistral-7B-v0.1" # Base Model
-model_name = "h-j-han/Mistral-7B-VocADT-50k-Mixed" # Vocabulary Adapted Model
+model_name = "h-j-han/Mistral-7B-VocADT-50k-All" # Vocabulary Adapted Model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
 prefix = "\nEnglish: Hello \nKorean: 안녕하세요 \nEnglish: Thank you\nKorean: 고맙습니다\nEnglish: "
@@ -49,7 +49,7 @@ prompt = prefix + line + suffix
 inputs = tokenizer(prompt, return_tensors="pt")
 for item in inputs:
     inputs[item] = inputs[item].cuda()
-outputs = model.generate(**inputs, max_new_tokens=88)
+outputs = model.generate(**inputs, max_new_tokens=5)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 # Base Model Output: "나는 학" # This short incomplete phrase in Korean is 5 tokens for the base model.
 # VocADT Output: "저는 학생입니다." # Complete and good output within 5 tokens