mergekit-community/aka-test

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 jaspionjader/bh-62 as a base.

Models Merged

The following models were included in the merge:

• P0x0/Epos-8b
• FuseAI/FuseChat-Llama-3.1-8B-Instruct
• Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
• SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
• djuna/L3.1-Promissum_Mane-8B-Della-calc
• NeverSleep/Lumimaid-v0.2-8B
• DavidAU/L3.1-RP-Hero-Dirty_Harry-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: jaspionjader/bh-62
  - model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
  - model: FuseAI/FuseChat-Llama-3.1-8B-Instruct
  - model: DavidAU/L3.1-RP-Hero-Dirty_Harry-8B
  - model: NeverSleep/Lumimaid-v0.2-8B
  - model: djuna/L3.1-Promissum_Mane-8B-Della-calc
  - model: P0x0/Epos-8b
merge_method: sce
base_model: jaspionjader/bh-62
parameters:
  select_topk: 0.67
dtype: bfloat16