Closed thomasiaticus closed 3 months ago
I will need more infomation, what model was used here? You may be using the incorrect instruct for your model.
Is it possible that you could provide an example Instruct for e.g. Llama3 or Gemma? I'm also having trouble getting the Instruct to work properly for the local inference.
There are presets for Llama3 and Gemma in the instruct menu. Closing this as this may not be app related, but configuration.
Every output of the AI appends
<|end|><|endoftext|>
at the end.