Update README.md

README.md

@@ -19,8 +19,9 @@ We explore supervised multitask pre-training by proposing ***Instruction Pre-Tra
 </p>
 
 **************************** **Updates** ****************************
+* 2024/8/29: Updated [guidelines](https://huggingface.co/instruction-pretrain/finance-Llama3-8B) on evaluating any 🤗Huggingface models on the domain-specific tasks
 * 2024/7/31: Updated pre-training suggestions in the `Advanced Usage` section of [instruction-synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer)
-* 2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M! Below, we show the performance trend on downstream tasks throughout the pre-training process:
+* 2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M. Below, we show the performance trend on downstream tasks throughout the pre-training process:
 <p align='left'>
     <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/0okCfRkC6uALTfuNxt0Fa.png" width="500">
 </p>
@@ -71,7 +72,7 @@ print(pred)
 ```
 
 ### 2. evaluate any Huggingface LMs on domain-dpecific tasks (💡New!)
-You can use the following scripts to reproduce our results and evaluate any other Huggingface models on domain-specific tasks. Note that these scripts are not applicable to models that require specific prompt templates (e.g., Llama2-chat, Llama3-Instruct).
+You can use the following script to reproduce our results and evaluate any other Huggingface models on domain-specific tasks. Note that the script is NOT applicable to models that require specific prompt templates (e.g., Llama2-chat, Llama3-Instruct).
 
 1). Set Up Dependencies
    ```bash