shadowlilac/lilax-UE-awq

Low-latency Large Language Model (LLM) optimized for fast response times.

Key Features:

Speed: Designed for minimal latency.
Quantized: Utilizes AWQ (Adaptive Weight Quantization) for efficiency.
Style: Inspired by the writing style of VRChat AI VTuber LilacAI. Outputs of this model do NOT represent anything ever said/any statements by LilacAI.
Provided as-is. May have some unwanted features in it's speech style