jvh/Mistral-NeuralBeagle14-OpenOrca-Turdus

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• udkai/Turdus
• Open-Orca/Mistral-7B-OpenOrca
• mlabonne/NeuralBeagle14-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/NeuralBeagle14-7B
    parameters:
      weight: 0.55
  - model: udkai/Turdus
    parameters:
      weight: 0.15
  - model: Open-Orca/Mistral-7B-OpenOrca
    parameters:
      weight: 0.3
merge_method: linear
dtype: float16

# slices:
#   - sources:
#       - model: Open-Orca/Mistral-7B-OpenOrca
#         layer_range: [0, 32]
#       - model: mlabonne/NeuralBeagle14-7B
#         layer_range: [0, 32]
# merge_method: slerp
# base_model: Open-Orca/Mistral-7B-OpenOrca
# 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: 0.5
# dtype: bfloat16