Update README.md

README.md

@@ -7,7 +7,7 @@ pipeline_tag: conversational
 ---
 
 ## ChatLM 
-It is a chat Large Language model finetuned with pretrained [Falcon-1B model](https://huggingface.co/tiiuae/falcon-rw-1b)
+It is a chat Large Language Model finetuned with pretrained [Falcon-1B model](https://huggingface.co/tiiuae/falcon-rw-1b)
 and trained on [chat-bot-instructions prompts dataset](https://huggingface.co/datasets/ayoolaolafenwa/sft-data).
 ChatLM was trained on a dataset containing normal day to day human conversations, due to limited data used in training
 it does not generalize well for tasks like coding and current affairs. 
@@ -123,12 +123,12 @@ new_data = pd.DataFrame({"prompt": prompts, "response": responses})
 # Write the new dataframe to a csv file
 new_data.to_csv("MyData/chatbot_instruction_prompts_train.csv", index=False)
 ```
-The user's prompts in the dataset are appended with the tag <user> and the corresponding responses with the tag <chatbot>.
+The users` prompts in the dataset are appended with the tag <user> and the corresponding responses with the tag <chatbot>.
 Check the the modified dataset https://huggingface.co/datasets/ayoolaolafenwa/sft-data .
 
 ### Training 
 
 ChatLM was supervised finetuned with pretrained [Falcon 1-Billion parameters model](https://huggingface.co/tiiuae/falcon-rw-1b) trained on 350-Billion tokens 
-of RefinedWeb. It was trained with a single H100 GPU for 1 epoch. Check the full code for supervised finetune 
+of RefinedWeb. It was trained with a single H100 GPU for 1 epoch. It achieves Perplexity *1.738*.  Check the full code for supervised finetune 
 training on its github repository https://github.com/ayoolaolafenwa/ChatLM/tree/main