kunoichi-lemon-royale-v2experiment1-32K-7B

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

The result appears to be a successful adapatation to the v0.3 tokenizer, with the resulting model being coherent, although there is some evident damage.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• grimjim/mistralai-Mistral-7B-Instruct-v0.3
• grimjim/kunoichi-lemon-royale-v2ext-32K-7B

Configuration

The following YAML configuration was used to produce this model:

base_model: grimjim/mistralai-Mistral-7B-Instruct-v0.3
dtype: bfloat16
merge_method: slerp
slices:
- sources:
  - model: grimjim/mistralai-Mistral-7B-Instruct-v0.3
    layer_range: [0, 32]
  - model: grimjim/kunoichi-lemon-royale-v2ext-32K-7B
    layer_range: [0, 32]
    value: 0.8
parameters:
  t:
    - filter: embed_tokens
      value: 0.0
    - filter: lm_head
      value: 0.0
    - value: 0.8