[See Previous Models]
  |
Lyra-v4a1
  |
  ------------> Lyra-v4 [Seperate RL Step targeting Instruct and Coherency over Base Nemo instead of SFT First, Result is Merged with Lyra-v4a1, fixes most quant-based issues. Somehow.]

<|im_start|>system
This is the system prompt.<|im_end|>
<|im_start|>user
Instructions placed here.<|im_end|>
<|im_start|>assistant
The model's response will be here.<|im_end|>
--------------------------------------------------
[INST]system
This is another system prompt.[/INST]
[INST]user
Your instructions placed here.[/INST]
[INST]assistant
The model's response will be here.[/INST]

Temperature: 0.6 - 1 # Make sure min_p is set before Temperature in Sampler Orders
min_p: 0.1 - 0.2 # Crucial for NeMo

<|im_end|>
</s>
[/INST]