Is it possible to introduce a new system message in the middle of a conversation?

[vedantroy]

It looks like the default template is as follows:

A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: What are the key differences between renewable and non-renewable energy sources?###Assistant: Renewable energy sources are those that can be replenished naturally in a relatively short amount of time, such as solar, wind, hydro, geothermal, and biomass. Non-renewable energy sources, on the other hand, are finite and will eventually be depleted, such as coal, oil, and natural gas. Here are some key differences between renewable and non-renewable energy sources:
1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable energy sources are finite and will eventually run out.
2. Environmental impact: Renewable energy sources have a much lower environmental impact than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, and other negative effects.
3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically have lower operational costs than non-renewable sources.
4. Reliability: Renewable energy sources are often more reliable and can be used in more remote locations than non-renewable sources.
5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different situations and needs, while non-renewable sources are more rigid and inflexible.
6. Sustainability: Renewable energy sources are more sustainable over the long term, while non-renewable sources are not, and their depletion can lead to economic and social instability.
###Human:

Where there is a single system message at the start of the prompt. I'm wondering, is it possible to to have multiple system messages?

[vedantroy]

Also, when formatting an input for Vicuna, do I always need to have the entire input be on a single line. (Since, presumably, this is how Vicuna was trained?)

[merrymercy]

The template you mentioned is for vicuna-v0 (https://github.com/lm-sys/FastChat/blob/73ea04dec7832de68783a68a424d374c85e3a29d/fastchat/conversation.py#L142) For vicuna-v1.1, we use a different one https://github.com/lm-sys/FastChat/blob/73ea04dec7832de68783a68a424d374c85e3a29d/fastchat/conversation.py#L181

I think you can play with different prompts and see how they work. Vicuna is trained on its default template, but I guess sometimes LLMs can generalize to other prompts well.