saishf/Extended-Mega-Mash-262K-8B-L3

merge

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

Merge Details

Experimental

This model is a attempt to push saishf/SOVL-Mega-Mash-V2-L3-8B (my personal favourite model) to support 32K+ context.

Merge Method

This model was merged using the Model Stock merge method using saishf/Long-Neural-SOVLish-Devil-8B-L3-262K as a base.

Models Merged

The following models were included in the merge:

• saishf/Merge-Mayhem-L3-V2
• saishf/Neural-SOVLish-Devil-8B-L3
• saishf/SOVLish-Maid-L3-8B
• saishf/Merge-Mayhem-L3-V2.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: saishf/Neural-SOVLish-Devil-8B-L3
  - model: saishf/Merge-Mayhem-L3-V2
  - model: saishf/Merge-Mayhem-L3-V2.1
  - model: saishf/SOVLish-Maid-L3-8B
merge_method: model_stock
base_model: saishf/Long-Neural-SOVLish-Devil-8B-L3-262K
dtype: bfloat16