Mutant-Writer-123b

Slerp merge of Behemoth 1.2 and gghfez/Writer-Large-2411-v2.1

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

  • /workspace/cache/models--TheDrummer--Behemoth-123B-v1.2/snapshots/51354019a02b742aa5a73fe16800225ff719c46d
  • /workspace/cache/models--gghfez--Writer-Large-2411-v2.1/snapshots/cb12d12db43e04ae42ac7a3c3ac987c867fd4757

Configuration

The following YAML configuration was used to produce this model:

base_model: /workspace/cache/models--TheDrummer--Behemoth-123B-v1.2/snapshots/51354019a02b742aa5a73fe16800225ff719c46d
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.1, 0.25, 0.4, 0.7, 0.4, 0.25, 0.1]
  - filter: mlp
    value: [0.1, 0.25, 0.4, 0.7, 0.4, 0.25, 0.1]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 88]
    model: /workspace/cache/models--TheDrummer--Behemoth-123B-v1.2/snapshots/51354019a02b742aa5a73fe16800225ff719c46d
  - layer_range: [0, 88]
    model: /workspace/cache/models--gghfez--Writer-Large-2411-v2.1/snapshots/cb12d12db43e04ae42ac7a3c3ac987c867fd4757
Downloads last month
11
Safetensors
Model size
123B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for bruhzair/Mutant-Writer-123b

Quantizations
2 models