Update README.md

README.md

@@ -45,7 +45,7 @@ We explore supervised multitask pre-training by proposing ***Instruction Pre-Tra
 ## Domain-Adaptive Continued Pre-Training
 Following [AdaptLLM](https://huggingface.co/AdaptLLM/finance-chat), we augment the domain-specific raw corpora with instruction-response pairs generated by our [context-based instruction synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer).
 
-### 1. chat with the finance-Llama3-8B model:
+### 1. To chat with the finance-Llama3-8B model:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -71,7 +71,7 @@ pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)
 print(pred)
 ```
 
-### 2. evaluate any Huggingface LMs on domain-dpecific tasks (💡New!)
+### 2. To evaluate any Huggingface LMs on domain-specific tasks (💡New!)
 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