fix: get_prompt goes wrong for Llama-2

[yangjunx21]

trafficstars

Why are these changes needed?

When adding the first user flag (with a message of "None"), and then check the conversation prompt like this:

conv_template.append_message(conv_template.roles[0], None)
conv_template.get_prompt()

The output is "[INST] [INST]". I think this must be a tiny hidden bug for function get_prompt (Llama-2), and I figure out how to fix it.

Related issue number (if applicable)

Some other open-source repositories will use this function to mark the specific slices in the conversation. So this bug may trigger some subtle bug or hard code.

Checks

• [x] I've run format.sh to lint the changes in this PR.
• [x] I've included any doc changes needed.
• [x] I've made sure the relevant tests are passing (if applicable).