Knobi3/Evomerge2

Evolutionary model merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using NeuralBeagle14-7B as a base. Evaluated over 100 merges.

Models Merged

The following models were included in the merge:

• Starling-LM-7B-beta_581094980
• Mistral-7B-v0.1-flashback-v2-instruct_3664132380
• NeuralBeagle14-7B_2368216670

Configuration

The following YAML configuration was used to produce this model:

base_model: /content/evol_merge_storage/input_models/NeuralBeagle14-7B_2368216670
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 8]
    model: /content/evol_merge_storage/input_models/NeuralBeagle14-7B_2368216670
    parameters:
      weight: 0.6116678110210994
  - layer_range: [0, 8]
    model: /content/evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      weight: -0.24959657782037278
  - layer_range: [0, 8]
    model: /content/evol_merge_storage/input_models/Mistral-7B-v0.1-flashback-v2-instruct_3664132380
    parameters:
      weight: 0.540324494683666
- sources:
  - layer_range: [8, 16]
    model: /content/evol_merge_storage/input_models/NeuralBeagle14-7B_2368216670
    parameters:
      weight: 0.3293682339424332
  - layer_range: [8, 16]
    model: /content/evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      weight: -0.023694567670847724
  - layer_range: [8, 16]
    model: /content/evol_merge_storage/input_models/Mistral-7B-v0.1-flashback-v2-instruct_3664132380
    parameters:
      weight: -0.1930115458123503
- sources:
  - layer_range: [16, 24]
    model: /content/evol_merge_storage/input_models/NeuralBeagle14-7B_2368216670
    parameters:
      weight: 0.27340593188424295
  - layer_range: [16, 24]
    model: /content/evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      weight: 0.08277665681111157
  - layer_range: [16, 24]
    model: /content/evol_merge_storage/input_models/Mistral-7B-v0.1-flashback-v2-instruct_3664132380
    parameters:
      weight: -0.04650853736971121
- sources:
  - layer_range: [24, 32]
    model: /content/evol_merge_storage/input_models/NeuralBeagle14-7B_2368216670
    parameters:
      weight: 0.22175238436196998
  - layer_range: [24, 32]
    model: /content/evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      weight: 0.3692597806977656
  - layer_range: [24, 32]
    model: /content/evol_merge_storage/input_models/Mistral-7B-v0.1-flashback-v2-instruct_3664132380
    parameters:
      weight: 0.5617035813353589