[Update]Update model name

README.md

@@ -6,7 +6,7 @@ license: apache-2.0
 Introducing xinchen9/llama3-b8-ft, an advanced language model comprising 8 billion parameters. It has been fine-trained based on 
 [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B). 
 
-The llama3-b8 model was fine-tuning on dataset [CoT_ollection](https://huggingface.co/datasets/kaist-ai/CoT-Collection).
+The llama3-b8 model was fine-tuning on dataset [CoT_Collection](https://huggingface.co/datasets/kaist-ai/CoT-Collection).
 
 The training step is 30,000. The batch of each device is 8 and toal GPU is 5.
 
@@ -17,7 +17,7 @@ Here give some examples of how to use our model.
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
 
-model_name = "xinchen9/Llama3.1_CoT"
+model_name = "xinchen9/Llama3.1_CoT_V1"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
 model.generation_config = GenerationConfig.from_pretrained(model_name)