Update README.md

README.md

@@ -20,7 +20,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-This model is a fine-tuned version of Llama-3.1-8B optimized for question-answering tasks on Wikipedia content using instruction tuning and Chain-of-Thought (CoT) reasoning. The model was trained using the LoRA (Low-Rank Adaptation) method with rank 64 to efficiently adapt the base model while maintaining its core capabilities.
+This model is a fine-tuned version of Llama-3.1-8B optimized for Question-Answering (QA) tasks on VIETNAMESE Wikipedia content using Instruction Tuning and Chain-of-Thought (CoT) reasoning. The model was trained using the LoRA (Low-Rank Adaptation) method with rank 64 to efficiently adapt the base model while maintaining its core capabilities.
 
 ## How to use
 
@@ -36,7 +36,7 @@ from vllm import LLM, SamplingParams
 from vllm.lora.request import LoRARequest
 from huggingface_hub import snapshot_download
 from huggingface_hub.hf_api import HfFolder
-HfFolder.save_token('your token here')
+HfFolder.save_token('your hf token here')
 
 model_id = 'meta-llama/Llama-3.1-8B'
 lora_id = 'strongpear/Llama3.1-8B-QA_CoT-WIKI-Instruct-r64'