README.md

metadata

base_model: grimjim/MagTie-v1-12B
base_model_relation: quantized
quanted_by: grimjim
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
  - mergekit
  - merge
  - GGUF

MagTie-v1-12B-GGUF

This repo is a set of GGUF quants of a grimjim/MagTie-v1-12B, a merge of pre-trained language models created using mergekit.

llama.cpp was used to make the following quants:

• Q4_0
• Q4_K_M
• Q5_K_M
• Q6_K
• Q8_0