escape pipe

README.md

@@ -6,9 +6,9 @@ The 'llama-recipes' repository is a companion to the [Llama 2 model](https://git
 > Llama 3 has a new prompt template and special tokens (based on the tiktoken tokenizer).
 > | Token | Description |
 > |---|---|
-> `<|begin_of_text|>` | This is equivalent to the BOS token. |
-> `<|eot_id|>` | This signifies the end of the message in a turn. This is equivalent to the EOS token. |
-> `<|start_header_id|>{role}<|end_header_id|>` | These tokens enclose the role for a particular message. The possible roles can be: system, user, assistant. |
+> `<\|begin_of_text\|>` | This is equivalent to the BOS token. |
+> `<\|eot_id\|>` | This signifies the end of the message in a turn. This is equivalent to the EOS token. |
+> `<\|start_header_id\|>{role}<\|end_header_id\|>` | These tokens enclose the role for a particular message. The possible roles can be: system, user, assistant. |
 > 
 > A multiturn-conversation with Llama 3 follows this prompt template:
 > ```