mergeduucsxwdd

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297 as a base.

Models Merged

The following models were included in the merge:

  • /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
  • /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297

Configuration

The following YAML configuration was used to produce this model:

base_model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 8]
    model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
    parameters:
      density: 0.9161252112124398
      weight: 0.42684262949748975
  - layer_range: [0, 8]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297
    parameters:
      density: 1.0
      weight: -0.07053838122379857
  - layer_range: [0, 8]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
    parameters:
      density: 1.0
      weight: 0.4849672857861172
- sources:
  - layer_range: [8, 16]
    model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
    parameters:
      density: 0.9761877279283722
      weight: 0.3012299838842449
  - layer_range: [8, 16]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297
    parameters:
      density: 0.7543807288499863
      weight: 0.1659536938628454
  - layer_range: [8, 16]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
    parameters:
      density: 0.9492212435976857
      weight: 0.18099531810782998
- sources:
  - layer_range: [16, 24]
    model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
    parameters:
      density: 1.0
      weight: 0.41688362670746804
  - layer_range: [16, 24]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297
    parameters:
      density: 1.0
      weight: 0.6151231122002006
  - layer_range: [16, 24]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
    parameters:
      density: 0.8807907336263985
      weight: 0.16825198717141238
- sources:
  - layer_range: [24, 32]
    model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
    parameters:
      density: 0.9156909340084007
      weight: 0.5326292576896499
  - layer_range: [24, 32]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297
    parameters:
      density: 1.0
      weight: 0.30104879006559454
  - layer_range: [24, 32]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
    parameters:
      density: 0.7478687683572947
      weight: 0.24780060115002012
- sources:
  - layer_range: [32, 40]
    model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
    parameters:
      density: 0.7970703509952921
      weight: 0.36719110728431165
  - layer_range: [32, 40]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297
    parameters:
      density: 0.9371578433786855
      weight: 0.3915882680301583
  - layer_range: [32, 40]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
    parameters:
      density: 0.625508665655407
      weight: 0.5087374040978708
- sources:
  - layer_range: [40, 48]
    model: /workspace/mergekit/evol_storage/input_models/SeQwence-14Bv1_904318297
    parameters:
      density: 0.844183840774721
      weight: 0.5421089451732982
  - layer_range: [40, 48]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-MegaMerge-pt2_1305659297
    parameters:
      density: 0.961154402903748
      weight: 0.30023482616059033
  - layer_range: [40, 48]
    model: /workspace/mergekit/evol_storage/input_models/Qwen2.5-14B-Wernicke_200578629
    parameters:
      density: 0.8135033850596236
      weight: 0.3232815470411797
Downloads last month
43
Safetensors
Model size
14.8B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for CultriX/SeQwence-14B-EvolMergev1

Quantizations
2 models