---
base_model: Sao10K/MN-12B-Lyra-v1
language:
- en
license: other
pipeline_tag: text-generation
quantized_by: Reiterate3680
---
Original Model: https://huggingface.co./Sao10K/MN-12B-Lyra-v1

made with https://huggingface.co./FantasiaFoundry/GGUF-Quantization-Script 

Models Q2_K_L, Q4_K_L, Q5_K_L, Q6_K_L, are using Q_8 output tensors and token embeddings

using bartowski's imatrix dataset