ghost_neural3_08_08_08_07_65

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• model_llm/neural-chat-7b-v3-3
• model_llm/ghost-7b-v0.9.1

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: model_llm/ghost-7b-v0.9.1
        layer_range: [0, 32]
      - model: model_llm/neural-chat-7b-v3-3
        layer_range: [0, 32]
merge_method: slerp
base_model: model_llm/ghost-7b-v0.9.1
parameters:
  t:
    - filter: self_attn
      value: [0.8, 0.8, 0.8, 0.7, 0.65]
    - filter: mlp
      value: [0.2, 0.2, 0.2, 0.3, 0.35]
    - value: 0.5
  embed_slerp: true
dtype: bfloat16