use tokenizer.chat_template by default for instruction type tasks

[TK-21st]

Changes

Use tokenizer.chat_template (if exists) for instruction type tasks by default.

Issue Addressed

This address the issue for models such as google/gemma-2-2b-it, where the instruction tokens are

--instruction_tokens "<start_of_turn>user\n","<end_of_turn>\n","<start_of_turn>model\n"

However, in the current implementation, because of string escaping, the prompt template escapes \n to \\n, which makes the final template different from the model's actual template. Additionally the current implementation doesn't add <bos> for tokenizers that use them by default.

Notes

Only tested on instruct-humaneval for google/gemma-2-2b-it and meta-llama/Llama-3.2-1B-Instruct for now.