Mixcraftz-123b-v3

A gradient SLERP of GigaMag-Behemoth and Tess-3-Mistral-Large-2-123B. See configuration yaml below.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

  • bruhzair/Mixcraftz-123b
  • migtissera/Tess-3-Mistral-Large-2-123B

Configuration

The following YAML configuration was used to produce this model:

base_model: /workspace/GigaMag-Behemoth
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.1, 0.3, 0.5, 0.7, 0.9, 1.0]
  - filter: mlp
    value: [1.0, 0.9, 0.7, 0.5, 0.3, 0.1, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 88]
    model: /workspace/GigaMag-Behemoth
  - layer_range: [0, 88]
    model: /workspace/cache/models--migtissera--Tess-3-Mistral-Large-2-123B/snapshots/c07f8a90214a71fa303394d3d52443d392dad771
Downloads last month
3
Safetensors
Model size
123B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bruhzair/Mixcraftz-123b-v3

Quantizations
2 models