Update README.md

README.md

@@ -15,7 +15,7 @@ A reproduced LLaVA LVLM based on Llama-3-8B LLM backbone. Not an official implem
 Please follow my reproduced implementation [LLaVA-Llama-3](https://github.com/Victorwz/LLaVA-Llama-3/) for more details on fine-tuning LLaVA model with Llama-3 as the foundatiaon LLM.
 
 ## Model Details
-Follows LLavA-1.5 pre-train and supervised fine-tuning pipeline. You do not need to change the LLaVA codebase to accomodate for Llama-3. 
+Follows LLavA-1.5 pre-train and supervised fine-tuning pipeline. You do not need to change the LLaVA codebase to accommodate Llama-3. 
 
 ## How to Use
 
@@ -72,10 +72,10 @@ The image features a blue and orange double-decker bus parked on a street. The b
 In the background, there are two cars parked on the street, one on the left side and the other on the right side. Additionally, there is a traffic light visible in the scene, indicating that the bus is stopped at an intersection.
 ```
 
+# Fine-Tune LLaVA-Llama-3 on Your Visual Instruction Data
+Please refer to a forked [LLaVA-Llama-3](https://github.com/Victorwz/LLaVA-Llama-3) git repo for fine-tuning data preparation and scripts. The data loading function and fastchat conversation template are changed due to a different tokenizer.
 
-Please refer to a forked [LLaVA-Llama-3](https://github.com/Victorwz/LLaVA-Llama-3) git repo for usage. The data loading function and fastchat conversation template are changed due to a different tokenizer.
-
-## Results
+## Benchmark Results
 
 
 | Model                 |      MMMU Val     |