knifeayumu/Magnum-v4-Cydonia-v1.2-22B-GGUF

Llamacpp Quantizations of knifeayumu/Magnum-v4-Cydonia-v1.2-22B

Using llama.cpp release b3985 for quantization.

Original model: knifeayumu/Magnum-v4-Cydonia-v1.2-22B

Quant Types:

Filename	Quant type	File Size
Magnum-v4-Cydonia-v1.2-22B-F16.gguf	F16	44.5 GB
Magnum-v4-Cydonia-v1.2-22B-Q8_0.gguf	Q8_0	23.6 GB
Magnum-v4-Cydonia-v1.2-22B-Q6_K.gguf	Q6_K	18.3 GB
Magnum-v4-Cydonia-v1.2-22B-Q5_K_M.gguf	Q5_K_M	15.7 GB
Magnum-v4-Cydonia-v1.2-22B-Q5_K_S.gguf	Q5_K_S	15.3 GB
Magnum-v4-Cydonia-v1.2-22B-Q4_K_M.gguf	Q4_K_M	13.3 GB
Magnum-v4-Cydonia-v1.2-22B-Q4_K_S.gguf	Q4_K_S	12.7 GB
Magnum-v4-Cydonia-v1.2-22B-Q3_K_L.gguf	Q3_K_L	11.7 GB
Magnum-v4-Cydonia-v1.2-22B-Q3_K_M.gguf	Q3_K_M	10.8 GB
Magnum-v4-Cydonia-v1.2-22B-Q3_K_S.gguf	Q3_K_S	9.64 GB
Magnum-v4-Cydonia-v1.2-22B-Q2_K.gguf	Q2_K	8.27 GB

Magnum? More like Deagle (dies in cringe)

Cydonia-v1.2-Magnum-v4-22B but inverse... Some prefer anthracite-org/magnum-v4-22b over TheDrummer/Cydonia-22B-v1.2 so this merge is born.

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• TheDrummer/Cydonia-22B-v1.2
• anthracite-org/magnum-v4-22b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org/magnum-v4-22b
  - model: TheDrummer/Cydonia-22B-v1.2
merge_method: slerp
base_model: anthracite-org/magnum-v4-22b
parameters:
  t: [0.1, 0.3, 0.6, 0.3, 0.1]
dtype: bfloat16