qwp4w3hyb's picture
Improve README.md
8c1ce2a unverified
|
raw
history blame
920 Bytes
metadata
base_model: Vezora/Mistral-22B-v0.1
tags:
  - moe
  - mistral
  - mixtral
  - merge
  - importance matrix
  - imatrix
language:
  - fr
  - it
  - de
  - es
  - en
model-index:
  - name: Mistral-22B-v0.1-iMat-GGUF
    results: []
license: apache-2.0

Vezora/Mistral-22B-v0.1 GGUFs created with an importance matrix

Source Model: Vezora/Mistral-22B-v0.1

Quantized with llama.cpp commit 5dc9dd7152dedc6046b646855585bd070c91e8c8 (master from 2024-04-09)

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