Llama tokenizer: remove space in template comment (#26788)

* Remove space in template comment

I think the space between the eos and bos tokens is not present in the actual template output. I'm using this documentation as a reference for everyone asking about prompting, so would like to clarify whether there's a space or not :)

* Update fast tokenizer too

* Apply to Code Llama

* Link to original code snippet.

src/transformers/models/code_llama/tokenization_code_llama.py

@@ -462,8 +462,12 @@ class CodeLlamaTokenizer(PreTrainedTokenizer):
 
         The output should look something like:
 
-        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos> <bos>[INST] Prompt [/INST] Answer <eos>
+        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos><bos>[INST] Prompt [/INST] Answer <eos>
         <bos>[INST] Prompt [/INST]
+
+        The reference for this chat template is [this code
+        snippet](https://github.com/facebookresearch/llama/blob/556949fdfb72da27c2f4a40b7f0e4cf0b8153a28/llama/generation.py#L320-L362)
+        in the original repository.
         """
 
         template = (

src/transformers/models/code_llama/tokenization_code_llama_fast.py

@@ -360,8 +360,12 @@ class CodeLlamaTokenizerFast(PreTrainedTokenizerFast):
 
         The output should look something like:
 
-        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos> <bos>[INST] Prompt [/INST] Answer <eos>
+        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos><bos>[INST] Prompt [/INST] Answer <eos>
         <bos>[INST] Prompt [/INST]
+
+        The reference for this chat template is [this code
+        snippet](https://github.com/facebookresearch/llama/blob/556949fdfb72da27c2f4a40b7f0e4cf0b8153a28/llama/generation.py#L320-L362)
+        in the original repository.
         """
 
         template = (

src/transformers/models/llama/tokenization_llama.py

@@ -423,8 +423,12 @@ class LlamaTokenizer(PreTrainedTokenizer):
 
         The output should look something like:
 
-        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos> <bos>[INST] Prompt [/INST] Answer <eos>
+        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos><bos>[INST] Prompt [/INST] Answer <eos>
         <bos>[INST] Prompt [/INST]
+
+        The reference for this chat template is [this code
+        snippet](https://github.com/facebookresearch/llama/blob/556949fdfb72da27c2f4a40b7f0e4cf0b8153a28/llama/generation.py#L320-L362)
+        in the original repository.
         """
 
         template = (

src/transformers/models/llama/tokenization_llama_fast.py

@@ -217,8 +217,12 @@ class LlamaTokenizerFast(PreTrainedTokenizerFast):
 
         The output should look something like:
 
-        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos> <bos>[INST] Prompt [/INST] Answer <eos>
+        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos><bos>[INST] Prompt [/INST] Answer <eos>
         <bos>[INST] Prompt [/INST]
+
+        The reference for this chat template is [this code
+        snippet](https://github.com/facebookresearch/llama/blob/556949fdfb72da27c2f4a40b7f0e4cf0b8153a28/llama/generation.py#L320-L362)
+        in the original repository.
         """
 
         template = (