alpha-wabisabi01

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

Merge Details

Merge Method

This model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• Local-Novel-LLM-project/WabiSabi-V1
• stabilityai/japanese-stablelm-base-gamma-7b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Local-Novel-LLM-project/WabiSabi-V1
    parameters:
      
      weight: 1.0
  - model: stabilityai/japanese-stablelm-base-gamma-7b
    parameters:
      
      weight: 1.0 # weight gradient

merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
  int8_mask: true
dtype: float16