Update README.md

README.md

@@ -390,8 +390,9 @@ Dapper and dignified
 Country cottage charm<|eot_id|>
 
 and so the model learns to do this in its first output:
+
 <|eot_id|><|start_header_id|>assistant<|end_header_id|>
-which naturally messes up the training. can you please put a new line character after the eot_id or prior to the start header id in the chat template: so that the format is like so :
+which naturally messes up the training. so i put a new line character after the eot_id or prior to the start header id in the chat template: so that the format is like so :
 <|begin_of_text|><|start_header_id|>user<|end_header_id|>
 
 <|image|>If I had to write a haiku for this one, it would be: <|eot_id|>
@@ -411,8 +412,8 @@ If I had to write a haiku for this one, it would be:<|eot_id|>#notice that this
 <|start_header_id|>assistant<|end_header_id|>
 
 ['A rabbit on a sunny day']
-this is an example of the 3.1 models chat template. i have not examined your one yet however i have examined the output of it above. to prevent the model learning that eot comes first there need to be a clearer distinction made with a \n
-
+this is an example of the 3.1 models chat template.. to prevent the model learning that eot comes first there need to be a clearer distinction made with a \n
+which Is done in this template
 
   Llama 3.2 Version Release Date: September 25, 2024