👁 image/png

Thanks to both Bartwowski & Lewdiculus for Quants <3 : Regular GGUF + Imatrix Bartowski Lewdiculous ARM and Imatrix GGUF's 4bpw Exl2

Instruct/Context import + Textgen preset combined available: Here

👁 image/png

The following models were included in the merge:

• Nitral-AI/Captain_BMO-12B-ChatMLified
• Epiculous/Violet_Twilight-v0.2

The following YAML configuration was used to produce this model:

slices:
 - sources:
 - model: Epiculous/Violet_Twilight-v0.2
 layer_range: [0, 40]
 - model: Nitral-AI/Captain_BMO-12B-ChatMLified
 layer_range: [0, 40]
merge_method: slerp
base_model: Epiculous/Violet_Twilight-v0.2
parameters:
 t:
 - filter: self_attn
 value: [0, 0.5, 0.3, 0.7, 1]
 - filter: mlp
 value: [1, 0.5, 0.7, 0.3, 0]
 - value: 0.420
dtype: bfloat16