kunoichi-lemon-royale-hamansu-v1-32k-7B

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

The model is subtly damaged, but the result might still have entertainment value.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• grimjim/kunoichi-lemon-royale-v2experiment1-32K-7B
• Delta-Vector/Hamanasu-7B-instruct

Configuration

The following YAML configuration was used to produce this model:

base_model: grimjim/kunoichi-lemon-royale-v2experiment1-32K-7B
dtype: bfloat16
merge_method: slerp
slices:
- sources:
  - model: grimjim/kunoichi-lemon-royale-v2experiment1-32K-7B
    layer_range: [0, 32]
  - model: Delta-Vector/Hamanasu-7B-instruct
    layer_range: [0, 32]
    value: 0.5
parameters:
  t:
    - filter: embed_tokens
      value: 0.5
    - filter: lm_head
      value: 0.5
    - value: 0.5