Pedro13543/experimental_merge_no4

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 Pedro13543/good_mix_r1 as a base.

Models Merged

The following models were included in the merge:

• bluuwhale/L3-SthenoMaidBlackroot-8B-V1
• Skywork/Skywork-o1-Open-Llama-3.1-8B
• huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
• Undi95/Meta-Llama-3.1-8B-Claude
• TheDrummer/Llama-3SOME-8B-v2
• Solshine/reflection-llama-3.1-8B-Solshine-Full

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  # Target models
  - model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
  - model: Skywork/Skywork-o1-Open-Llama-3.1-8B
  - model: Solshine/reflection-llama-3.1-8B-Solshine-Full
  - model : Undi95/Meta-Llama-3.1-8B-Claude
  - model : TheDrummer/Llama-3SOME-8B-v2

merge_method: sce
base_model: Pedro13543/good_mix_r1
parameters:
  select_topk: 1.0
dtype: bfloat16