TareksTesting/Legion-V1.8-LLaMa-70B

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using TareksLab/M-BASE-SCE as a base.

Models Merged

The following models were included in the merge:

• TareksLab/M-MERGE4
• TareksLab/M-MERGE1
• TareksLab/M-MERGE3
• TareksLab/M-MERGE2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TareksLab/M-MERGE4
    parameters:
       select_topk: 0.15
  - model: TareksLab/M-MERGE3
    parameters:
       select_topk: 0.16
  - model: TareksLab/M-MERGE2
    parameters:
       select_topk: 0.17
  - model: TareksLab/M-MERGE1
    parameters:
       select_topk: 0.18
merge_method: sce
base_model: TareksLab/M-BASE-SCE
parameters:
  int8_mask: true
chat_template: llama3
tokenizer:
  source: TareksLab/M-TOKENIZER-SCE
dtype: bfloat16