Chat template should be inside the tokenizer json

Hi

@krutrim-admin
,
I have done some changes, i.e, added the chat template in tokenizer config.
If we do this then we don't have to define this in the inference code.
Kindly review this from your side, will change the readme file too if this will works okay.

tokenizer_config.json

@@ -1753,5 +1753,6 @@
   "model_max_length": 4096,
   "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast",
+  "chat_template" :"{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|SYSTEM|> ' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|USER|> ' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|RESPONSE|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|RESPONSE|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|RESPONSE|>\n' }}{% endif %}{% endfor %}"
   "unk_token": "<unk>"
 }