admin-leeway-raiment-20251126t180549

merge_output

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:

• mistralai/Mistral-7B-Instruct-v0.3
• DogOnKeyboard/Mistral-7B-Heretic-V2

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: DogOnKeyboard/Mistral-7B-Heretic-V2
    layer_range:
    - 0
    - 32
  - model: mistralai/Mistral-7B-Instruct-v0.3
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: DogOnKeyboard/Mistral-7B-Heretic-V2
parameters:
  t:
  - filter: embed_tokens
    value: 0.5
  - filter: input_layernorm
    value: 0.7
  - filter: lm_head
    value: 0.5
  - filter: mlp
    value: 0.39
  - filter: norm
    value: 0.5
  - filter: post_attention_layernorm
    value: 0.65
  - filter: self_attn
    value: 0.5
  - value: 0.5
dtype: bfloat16