Are there any downsides in fine-turning models with non-proprietary chat templates?
As en example, if I fine-tune llama3 with the Alpaca chat template, will it be performing worse than using the original llama3 chat template?
For reference, llama3 uses:
You are a helpful AI assistant for travel tips and recommendations<|eot_id|><|start_header_id|>user<|end_header_id|>
What can you help me with?<|eot_id|><|start_header_id|>assistant<|end_header_id|>```
While the Alpaca one is:
```Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}```
Can I use any templates with any models?