LoRa @ Inference Time.

[Clarie-Starling]

Hi,
Despite it not being said do the Model Configs in .env.local Support the OpenAI lora: option?
during a chat/completion invoke? Or even static in the server config?

I.e

MODELS=`[
{
"name": "Local microsoft/Phi-3-mini-4k-instruct-gguf",
"tokenizer": "microsoft/Phi-3-mini-4k-instruct-gguf",
"lora": "My/LoRa/Path/backwards.safetensors",

This is a big need due to apps needing AI personality is becoming more and more prevalent (System prompts don't cut it anymore)