Update README.md

README.md

@@ -4,11 +4,13 @@ license_name: other
 license_link: https://ai.meta.com/llama/license
 ---
 Repairing the chat template for the model.
-There is a slight problem with your chat template. If you train a model with that current chat template the model starts to output as the first token <|eot_id|> and naturally the script will then halt generation. the model learns to see this:
+There is a slight problem with the eorigianl llam 3.2 chat template. If you train a model with that current chat template and if the training script builds the prompts
+frmm a json file with the chat temaplte the model starts to output as its first token <|eot_id|> and naturally the script will then halt generation. 
+the model learns to see this:
 
 <|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|><|start_header_id|>assistant<|end_header_id|>
+<|image|>Wite Haiku: <|eot_id|><|start_header_id|>assistant<|end_header_id|>
 
 Here is a haiku for the image: