metadata

base_model: AetherResearch/Cerebrum-1.0-8x7b
tags:
  - Mixtral
  - instruct
  - finetune
  - imatrix
model-index:
  - name: Cerebrum-1.0-8x7b-iMat-GGUF
    results: []
license: apache-2.0

Cerebrum-1.0-8x7b-iMat-GGUF

Source Model: AetherResearch/Cerebrum-1.0-8x7b Quantized with llama.cpp commit 46acb3676718b983157058aecf729a2064fc7d34 Imatrix was generated from the f16 gguf via this command:

./imatrix -c 512 -m $out_path/$base_quant_name -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat

Using the dataset from here